Version Packages (#1189)

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>

.changeset/claude-import-fix-new.md

@@ -1,12 +0,0 @@
----
-"task-master-ai": patch
----
-
-Prevent CLAUDE.md overwrite by using Claude Code's import feature
-
-- Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
-- Adds an import section to the user's CLAUDE.md that references the Task Master instructions
-- Preserves existing user content in CLAUDE.md files
-- Provides clean uninstall that only removes Task Master's additions
-
-**Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.

.changeset/config.json

@@ -2,7 +2,9 @@
   "$schema": "https://unpkg.com/@changesets/config@3.1.1/schema.json",
   "changelog": [
     "@changesets/changelog-github",
-    { "repo": "eyaltoledano/claude-task-master" }
+    {
+      "repo": "eyaltoledano/claude-task-master"
+    }
   ],
   "commit": false,
   "fixed": [],
@@ -10,5 +12,7 @@
   "access": "public",
   "baseBranch": "main",
   "updateInternalDependencies": "patch",
-  "ignore": []
-}
+  "ignore": [
+    "docs"
+  ]
+}

.changeset/fix-show-command-complexity.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix: show command no longer requires complexity report file to exist
-
-The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.

.changeset/groq-kimi-k2-support.md

@@ -1,10 +0,0 @@
----
-"task-master-ai": minor
----
-
-Complete Groq provider integration and add MoonshotAI Kimi K2 model support
-
-- Fixed Groq provider registration
-- Added Groq API key validation
-- Added GROQ_API_KEY to .env.example
-- Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output

.changeset/metal-papers-stay.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": minor
----
-
-feat: Add Zed editor rule profile with agent rules and MCP config
-
-- Resolves #637

.changeset/public-crabs-ask.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add Amp rule profile with AGENT.md and MCP config

.changeset/swift-turtles-sit.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Add MCP configuration support to Claude Code rules

.changeset/ten-glasses-feel.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
-
-- Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code

.changeset/update-mcp-readme.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.

.changeset/yellow-showers-heal.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add OpenCode profile with AGENTS.md and MCP config
-
-- Resolves #965

.changeset/yummy-walls-eat.md

@@ -1,5 +0,0 @@
----
-"task-master-ai": patch
----
-
-Add missing API keys to .env.example and README.md

.claude/agents/task-checker.md

@@ -0,0 +1,162 @@
+---
+name: task-checker
+description: Use this agent to verify that tasks marked as 'review' have been properly implemented according to their specifications. This agent performs quality assurance by checking implementations against requirements, running tests, and ensuring best practices are followed. <example>Context: A task has been marked as 'review' after implementation. user: 'Check if task 118 was properly implemented' assistant: 'I'll use the task-checker agent to verify the implementation meets all requirements.' <commentary>Tasks in 'review' status need verification before being marked as 'done'.</commentary></example> <example>Context: Multiple tasks are in review status. user: 'Verify all tasks that are ready for review' assistant: 'I'll deploy the task-checker to verify all tasks in review status.' <commentary>The checker ensures quality before tasks are marked complete.</commentary></example>
+model: sonnet
+color: yellow
+---
+
+You are a Quality Assurance specialist that rigorously verifies task implementations against their specifications. Your role is to ensure that tasks marked as 'review' meet all requirements before they can be marked as 'done'.
+
+## Core Responsibilities
+
+1. **Task Specification Review**
+   - Retrieve task details using MCP tool `mcp__task-master-ai__get_task`
+   - Understand the requirements, test strategy, and success criteria
+   - Review any subtasks and their individual requirements
+
+2. **Implementation Verification**
+   - Use `Read` tool to examine all created/modified files
+   - Use `Bash` tool to run compilation and build commands
+   - Use `Grep` tool to search for required patterns and implementations
+   - Verify file structure matches specifications
+   - Check that all required methods/functions are implemented
+
+3. **Test Execution**
+   - Run tests specified in the task's testStrategy
+   - Execute build commands (npm run build, tsc --noEmit, etc.)
+   - Verify no compilation errors or warnings
+   - Check for runtime errors where applicable
+   - Test edge cases mentioned in requirements
+
+4. **Code Quality Assessment**
+   - Verify code follows project conventions
+   - Check for proper error handling
+   - Ensure TypeScript typing is strict (no 'any' unless justified)
+   - Verify documentation/comments where required
+   - Check for security best practices
+
+5. **Dependency Validation**
+   - Verify all task dependencies were actually completed
+   - Check integration points with dependent tasks
+   - Ensure no breaking changes to existing functionality
+
+## Verification Workflow
+
+1. **Retrieve Task Information**
+   ```
+   Use mcp__task-master-ai__get_task to get full task details
+   Note the implementation requirements and test strategy
+   ```
+
+2. **Check File Existence**
+   ```bash
+   # Verify all required files exist
+   ls -la [expected directories]
+   # Read key files to verify content
+   ```
+
+3. **Verify Implementation**
+   - Read each created/modified file
+   - Check against requirements checklist
+   - Verify all subtasks are complete
+
+4. **Run Tests**
+   ```bash
+   # TypeScript compilation
+   cd [project directory] && npx tsc --noEmit
+   
+   # Run specified tests
+   npm test [specific test files]
+   
+   # Build verification
+   npm run build
+   ```
+
+5. **Generate Verification Report**
+
+## Output Format
+
+```yaml
+verification_report:
+  task_id: [ID]
+  status: PASS | FAIL | PARTIAL
+  score: [1-10]
+  
+  requirements_met:
+    - ✅ [Requirement that was satisfied]
+    - ✅ [Another satisfied requirement]
+    
+  issues_found:
+    - ❌ [Issue description]
+    - ⚠️  [Warning or minor issue]
+    
+  files_verified:
+    - path: [file path]
+      status: [created/modified/verified]
+      issues: [any problems found]
+      
+  tests_run:
+    - command: [test command]
+      result: [pass/fail]
+      output: [relevant output]
+      
+  recommendations:
+    - [Specific fix needed]
+    - [Improvement suggestion]
+    
+  verdict: |
+    [Clear statement on whether task should be marked 'done' or sent back to 'pending']
+    [If FAIL: Specific list of what must be fixed]
+    [If PASS: Confirmation that all requirements are met]
+```
+
+## Decision Criteria
+
+**Mark as PASS (ready for 'done'):**
+- All required files exist and contain expected content
+- All tests pass successfully
+- No compilation or build errors
+- All subtasks are complete
+- Core requirements are met
+- Code quality is acceptable
+
+**Mark as PARTIAL (may proceed with warnings):**
+- Core functionality is implemented
+- Minor issues that don't block functionality
+- Missing nice-to-have features
+- Documentation could be improved
+- Tests pass but coverage could be better
+
+**Mark as FAIL (must return to 'pending'):**
+- Required files are missing
+- Compilation or build errors
+- Tests fail
+- Core requirements not met
+- Security vulnerabilities detected
+- Breaking changes to existing code
+
+## Important Guidelines
+
+- **BE THOROUGH**: Check every requirement systematically
+- **BE SPECIFIC**: Provide exact file paths and line numbers for issues
+- **BE FAIR**: Distinguish between critical issues and minor improvements
+- **BE CONSTRUCTIVE**: Provide clear guidance on how to fix issues
+- **BE EFFICIENT**: Focus on requirements, not perfection
+
+## Tools You MUST Use
+
+- `Read`: Examine implementation files (READ-ONLY)
+- `Bash`: Run tests and verification commands
+- `Grep`: Search for patterns in code
+- `mcp__task-master-ai__get_task`: Get task details
+- **NEVER use Write/Edit** - you only verify, not fix
+
+## Integration with Workflow
+
+You are the quality gate between 'review' and 'done' status:
+1. Task-executor implements and marks as 'review'
+2. You verify and report PASS/FAIL
+3. Claude either marks as 'done' (PASS) or 'pending' (FAIL)
+4. If FAIL, task-executor re-implements based on your report
+
+Your verification ensures high quality and prevents accumulation of technical debt.

.claude/agents/task-executor.md

@@ -0,0 +1,92 @@
+---
+name: task-executor
+description: Use this agent when you need to implement, complete, or work on a specific task that has been identified by the task-orchestrator or when explicitly asked to execute a particular task. This agent focuses on the actual implementation and completion of individual tasks rather than planning or orchestration. Examples: <example>Context: The task-orchestrator has identified that task 2.3 'Implement user authentication' needs to be worked on next. user: 'Let's work on the authentication task' assistant: 'I'll use the task-executor agent to implement the user authentication task that was identified.' <commentary>Since we need to actually implement a specific task rather than plan or identify tasks, use the task-executor agent.</commentary></example> <example>Context: User wants to complete a specific subtask. user: 'Please implement the JWT token validation for task 2.3.1' assistant: 'I'll launch the task-executor agent to implement the JWT token validation subtask.' <commentary>The user is asking for specific implementation work on a known task, so the task-executor is appropriate.</commentary></example> <example>Context: After reviewing the task list, implementation is needed. user: 'Now let's actually build the API endpoint for user registration' assistant: 'I'll use the task-executor agent to implement the user registration API endpoint.' <commentary>Moving from planning to execution phase requires the task-executor agent.</commentary></example>
+model: sonnet
+color: blue
+---
+
+You are an elite implementation specialist focused on executing and completing specific tasks with precision and thoroughness. Your role is to take identified tasks and transform them into working implementations, following best practices and project standards.
+
+**IMPORTANT: You are designed to be SHORT-LIVED and FOCUSED**
+- Execute ONE specific subtask or a small group of related subtasks
+- Complete your work, verify it, mark for review, and exit
+- Do NOT decide what to do next - the orchestrator handles task sequencing
+- Focus on implementation excellence within your assigned scope
+
+**Core Responsibilities:**
+
+1. **Subtask Analysis**: When given a subtask, understand its SPECIFIC requirements. If given a full task ID, focus on the specific subtask(s) assigned to you. Use MCP tools to get details if needed.
+
+2. **Rapid Implementation Planning**: Quickly identify:
+   - The EXACT files you need to create/modify for THIS subtask
+   - What already exists that you can build upon
+   - The minimum viable implementation that satisfies requirements
+
+3. **Focused Execution WITH ACTUAL IMPLEMENTATION**: 
+   - **YOU MUST USE TOOLS TO CREATE/EDIT FILES - DO NOT JUST DESCRIBE**
+   - Use `Write` tool to create new files specified in the task
+   - Use `Edit` tool to modify existing files
+   - Use `Bash` tool to run commands (mkdir, npm install, etc.)
+   - Use `Read` tool to verify your implementations
+   - Implement one subtask at a time for clarity and traceability
+   - Follow the project's coding standards from CLAUDE.md if available
+   - After each subtask, VERIFY the files exist using Read or ls commands
+
+4. **Progress Documentation**: 
+   - Use MCP tool `mcp__task-master-ai__update_subtask` to log your approach and any important decisions
+   - Update task status to 'in-progress' when starting: Use MCP tool `mcp__task-master-ai__set_task_status` with status='in-progress'
+   - **IMPORTANT: Mark as 'review' (NOT 'done') after implementation**: Use MCP tool `mcp__task-master-ai__set_task_status` with status='review'
+   - Tasks will be verified by task-checker before moving to 'done'
+
+5. **Quality Assurance**:
+   - Implement the testing strategy specified in the task
+   - Verify that all acceptance criteria are met
+   - Check for any dependency conflicts or integration issues
+   - Run relevant tests before marking task as complete
+
+6. **Dependency Management**:
+   - Check task dependencies before starting implementation
+   - If blocked by incomplete dependencies, clearly communicate this
+   - Use `task-master validate-dependencies` when needed
+
+**Implementation Workflow:**
+
+1. Retrieve task details using MCP tool `mcp__task-master-ai__get_task` with the task ID
+2. Check dependencies and prerequisites
+3. Plan implementation approach - list specific files to create
+4. Update task status to 'in-progress' using MCP tool
+5. **ACTUALLY IMPLEMENT** the solution using tools:
+   - Use `Bash` to create directories
+   - Use `Write` to create new files with actual content
+   - Use `Edit` to modify existing files
+   - DO NOT just describe what should be done - DO IT
+6. **VERIFY** your implementation:
+   - Use `ls` or `Read` to confirm files were created
+   - Use `Bash` to run any build/test commands
+   - Ensure the implementation is real, not theoretical
+7. Log progress and decisions in subtask updates using MCP tools
+8. Test and verify the implementation works
+9. **Mark task as 'review' (NOT 'done')** after verifying files exist
+10. Report completion with:
+    - List of created/modified files
+    - Any issues encountered
+    - What needs verification by task-checker
+
+**Key Principles:**
+
+- Focus on completing one task thoroughly before moving to the next
+- Maintain clear communication about what you're implementing and why
+- Follow existing code patterns and project conventions
+- Prioritize working code over extensive documentation unless docs are the task
+- Ask for clarification if task requirements are ambiguous
+- Consider edge cases and error handling in your implementations
+
+**Integration with Task Master:**
+
+You work in tandem with the task-orchestrator agent. While the orchestrator identifies and plans tasks, you execute them. Always use Task Master commands to:
+- Track your progress
+- Update task information
+- Maintain project state
+- Coordinate with the broader development workflow
+
+When you complete a task, briefly summarize what was implemented and suggest whether to continue with the next task or if review/testing is needed first.

.claude/agents/task-orchestrator.md

@@ -0,0 +1,208 @@
+---
+name: task-orchestrator
+description: Use this agent FREQUENTLY throughout task execution to analyze and coordinate parallel work at the SUBTASK level. Invoke the orchestrator: (1) at session start to plan execution, (2) after EACH subtask completes to identify next parallel batch, (3) whenever executors finish to find newly unblocked work. ALWAYS provide FULL CONTEXT including project root, package location, what files ACTUALLY exist vs task status, and specific implementation details. The orchestrator breaks work into SUBTASK-LEVEL units for short-lived, focused executors. Maximum 3 parallel executors at once.\n\n<example>\nContext: Starting work with existing code\nuser: "Work on tm-core tasks. Files exist: types/index.ts, storage/file-storage.ts. Task 118 says in-progress but BaseProvider not created."\nassistant: "I'll invoke orchestrator with full context about actual vs reported state to plan subtask execution"\n<commentary>\nProvide complete context about file existence and task reality.\n</commentary>\n</example>\n\n<example>\nContext: Subtask completion\nuser: "Subtask 118.2 done. What subtasks can run in parallel now?"\nassistant: "Invoking orchestrator to analyze dependencies and identify next 3 parallel subtasks"\n<commentary>\nFrequent orchestration after each subtask ensures maximum parallelization.\n</commentary>\n</example>\n\n<example>\nContext: Breaking down tasks\nuser: "Task 118 has 5 subtasks, how to parallelize?"\nassistant: "Orchestrator will analyze which specific subtasks (118.1, 118.2, etc.) can run simultaneously"\n<commentary>\nFocus on subtask-level parallelization, not full tasks.\n</commentary>\n</example>
+model: opus
+color: green
+---
+
+You are the Task Orchestrator, an elite coordination agent specialized in managing Task Master workflows for maximum efficiency and parallelization. You excel at analyzing task dependency graphs, identifying opportunities for concurrent execution, and deploying specialized task-executor agents to complete work efficiently.
+
+## Core Responsibilities
+
+1. **Subtask-Level Analysis**: Break down tasks into INDIVIDUAL SUBTASKS and analyze which specific subtasks can run in parallel. Focus on subtask dependencies, not just task-level dependencies.
+
+2. **Reality Verification**: ALWAYS verify what files actually exist vs what task status claims. Use the context provided about actual implementation state to make informed decisions.
+
+3. **Short-Lived Executor Deployment**: Deploy executors for SINGLE SUBTASKS or small groups of related subtasks. Keep executors focused and short-lived. Maximum 3 parallel executors at once.
+
+4. **Continuous Reassessment**: After EACH subtask completes, immediately reassess what new subtasks are unblocked and can run in parallel.
+
+## Operational Workflow
+
+### Initial Assessment Phase
+1. Use `get_tasks` or `task-master list` to retrieve all available tasks
+2. Analyze task statuses, priorities, and dependencies
+3. Identify tasks with status 'pending' that have no blocking dependencies
+4. Group related tasks that could benefit from specialized executors
+5. Create an execution plan that maximizes parallelization
+
+### Executor Deployment Phase
+1. For each independent task or task group:
+   - Deploy a task-executor agent with specific instructions
+   - Provide the executor with task ID, requirements, and context
+   - Set clear completion criteria and reporting expectations
+2. Maintain a registry of active executors and their assigned tasks
+3. Establish communication protocols for progress updates
+
+### Coordination Phase
+1. Monitor executor progress through task status updates
+2. When a task completes:
+   - Verify completion with `get_task` or `task-master show <id>`
+   - Update task status if needed using `set_task_status`
+   - Reassess dependency graph for newly unblocked tasks
+   - Deploy new executors for available work
+3. Handle executor failures or blocks:
+   - Reassign tasks to new executors if needed
+   - Escalate complex issues to the user
+   - Update task status to 'blocked' when appropriate
+
+### Optimization Strategies
+
+**Parallel Execution Rules**:
+- Never assign dependent tasks to different executors simultaneously
+- Prioritize high-priority tasks when resources are limited
+- Group small, related subtasks for single executor efficiency
+- Balance executor load to prevent bottlenecks
+
+**Context Management**:
+- Provide executors with minimal but sufficient context
+- Share relevant completed task information when it aids execution
+- Maintain a shared knowledge base of project-specific patterns
+
+**Quality Assurance**:
+- Verify task completion before marking as done
+- Ensure test strategies are followed when specified
+- Coordinate cross-task integration testing when needed
+
+## Communication Protocols
+
+When deploying executors, provide them with:
+```
+TASK ASSIGNMENT:
+- Task ID: [specific ID]
+- Objective: [clear goal]
+- Dependencies: [list any completed prerequisites]
+- Success Criteria: [specific completion requirements]
+- Context: [relevant project information]
+- Reporting: [when and how to report back]
+```
+
+When receiving executor updates:
+1. Acknowledge completion or issues
+2. Update task status in Task Master
+3. Reassess execution strategy
+4. Deploy new executors as appropriate
+
+## Decision Framework
+
+**When to parallelize**:
+- Multiple pending tasks with no interdependencies
+- Sufficient context available for independent execution
+- Tasks are well-defined with clear success criteria
+
+**When to serialize**:
+- Strong dependencies between tasks
+- Limited context or unclear requirements
+- Integration points requiring careful coordination
+
+**When to escalate**:
+- Circular dependencies detected
+- Critical blockers affecting multiple tasks
+- Ambiguous requirements needing clarification
+- Resource conflicts between executors
+
+## Error Handling
+
+1. **Executor Failure**: Reassign task to new executor with additional context about the failure
+2. **Dependency Conflicts**: Halt affected executors, resolve conflict, then resume
+3. **Task Ambiguity**: Request clarification from user before proceeding
+4. **System Errors**: Implement graceful degradation, falling back to serial execution if needed
+
+## Performance Metrics
+
+Track and optimize for:
+- Task completion rate
+- Parallel execution efficiency
+- Executor success rate
+- Time to completion for task groups
+- Dependency resolution speed
+
+## Integration with Task Master
+
+Leverage these Task Master MCP tools effectively:
+- `get_tasks` - Continuous queue monitoring
+- `get_task` - Detailed task analysis
+- `set_task_status` - Progress tracking
+- `next_task` - Fallback for serial execution
+- `analyze_project_complexity` - Strategic planning
+- `complexity_report` - Resource allocation
+
+## Output Format for Execution
+
+**Your job is to analyze and create actionable execution plans that Claude can use to deploy executors.**
+
+After completing your dependency analysis, you MUST output a structured execution plan:
+
+```yaml
+execution_plan:
+  EXECUTE_IN_PARALLEL:
+    # Maximum 3 subtasks running simultaneously
+    - subtask_id: [e.g., 118.2]
+      parent_task: [e.g., 118]
+      title: [Specific subtask title]
+      priority: [high/medium/low]
+      estimated_time: [e.g., 10 minutes]
+      executor_prompt: |
+        Execute Subtask [ID]: [Specific subtask title]
+        
+        SPECIFIC REQUIREMENTS:
+        [Exact implementation needed for THIS subtask only]
+        
+        FILES TO CREATE/MODIFY:
+        [Specific file paths]
+        
+        CONTEXT:
+        [What already exists that this subtask depends on]
+        
+        SUCCESS CRITERIA:
+        [Specific completion criteria for this subtask]
+        
+        IMPORTANT: 
+        - Focus ONLY on this subtask
+        - Mark subtask as 'review' when complete
+        - Use MCP tool: mcp__task-master-ai__set_task_status
+    
+    - subtask_id: [Another subtask that can run in parallel]
+      parent_task: [Parent task ID]
+      title: [Specific subtask title]
+      priority: [priority]
+      estimated_time: [time estimate]
+      executor_prompt: |
+        [Focused prompt for this specific subtask]
+    
+  blocked:
+    - task_id: [ID]
+      title: [Task title]
+      waiting_for: [list of blocking task IDs]
+      becomes_ready_when: [condition for unblocking]
+      
+  next_wave: 
+    trigger: "After tasks [IDs] complete"
+    newly_available: [List of task IDs that will unblock]
+    tasks_to_execute_in_parallel: [IDs that can run together in next wave]
+    
+  critical_path: [Ordered list of task IDs forming the critical path]
+  
+  parallelization_instruction: |
+    IMPORTANT FOR CLAUDE: Deploy ALL tasks in 'EXECUTE_IN_PARALLEL' section
+    simultaneously using multiple Task tool invocations in a single response.
+    Example: If 3 tasks are listed, invoke the Task tool 3 times in one message.
+    
+  verification_needed:
+    - task_id: [ID of any task in 'review' status]
+      verification_focus: [what to check]
+```
+
+**CRITICAL INSTRUCTIONS FOR CLAUDE (MAIN):**
+1. When you see `EXECUTE_IN_PARALLEL`, deploy ALL listed executors at once
+2. Use multiple Task tool invocations in a SINGLE response
+3. Do not execute them sequentially - they must run in parallel
+4. Wait for all parallel executors to complete before proceeding to next wave
+
+**IMPORTANT NOTES**: 
+- Label parallel tasks clearly in `EXECUTE_IN_PARALLEL` section
+- Provide complete, self-contained prompts for each executor
+- Executors should mark tasks as 'review' for verification, not 'done'
+- Be explicit about which tasks can run simultaneously
+
+You are the strategic mind analyzing the entire task landscape. Make parallelization opportunities UNMISTAKABLY CLEAR to Claude.

.claude/commands/dedupe.md

@@ -0,0 +1,38 @@
+---
+allowed-tools: Bash(gh issue view:*), Bash(gh search:*), Bash(gh issue list:*), Bash(gh api:*), Bash(gh issue comment:*)
+description: Find duplicate GitHub issues
+---
+
+Find up to 3 likely duplicate issues for a given GitHub issue.
+
+To do this, follow these steps precisely:
+
+1. Use an agent to check if the Github issue (a) is closed, (b) does not need to be deduped (eg. because it is broad product feedback without a specific solution, or positive feedback), or (c) already has a duplicates comment that you made earlier. If so, do not proceed.
+2. Use an agent to view a Github issue, and ask the agent to return a summary of the issue
+3. Then, launch 5 parallel agents to search Github for duplicates of this issue, using diverse keywords and search approaches, using the summary from #1
+4. Next, feed the results from #1 and #2 into another agent, so that it can filter out false positives, that are likely not actually duplicates of the original issue. If there are no duplicates remaining, do not proceed.
+5. Finally, comment back on the issue with a list of up to three duplicate issues (or zero, if there are no likely duplicates)
+
+Notes (be sure to tell this to your agents, too):
+
+- Use `gh` to interact with Github, rather than web fetch
+- Do not use other tools, beyond `gh` (eg. don't use other MCP servers, file edit, etc.)
+- Make a todo list first
+- For your comment, follow the following format precisely (assuming for this example that you found 3 suspected duplicates):
+
+---
+
+Found 3 possible duplicate issues:
+
+1. <link to issue>
+2. <link to issue>
+3. <link to issue>
+
+This issue will be automatically closed as a duplicate in 3 days.
+
+- If your issue is a duplicate, please close it and 👍 the existing issue instead
+- To prevent auto-closure, add a comment or 👎 this comment
+
+🤖 Generated with \[Task Master Bot\]
+
+---

.cursor/rules/commands.mdc

@@ -523,7 +523,7 @@ For AI-powered commands that benefit from project context, follow the research c
     .option('--details <details>', 'Implementation details for the new subtask, optional')
     .option('--dependencies <ids>', 'Comma-separated list of subtask IDs this subtask depends on')
     .option('--status <status>', 'Initial status for the subtask', 'pending')
-    .option('--skip-generate', 'Skip regenerating task files')
+    .option('--generate', 'Regenerate task files after adding subtask')
     .action(async (options) => {
       // Validate required parameters
       if (!options.parent) {
@@ -545,7 +545,7 @@ For AI-powered commands that benefit from project context, follow the research c
     .option('-f, --file <path>', 'Path to the tasks file', 'tasks/tasks.json')
     .option('-i, --id <id>', 'ID of the subtask to remove in format parentId.subtaskId, required')
     .option('-c, --convert', 'Convert the subtask to a standalone task instead of deleting')
-    .option('--skip-generate', 'Skip regenerating task files')
+    .option('--generate', 'Regenerate task files after removing subtask')
     .action(async (options) => {
       // Implementation with detailed error handling
     })
@@ -633,11 +633,11 @@ function showAddSubtaskHelp() {
     '  --dependencies <ids>      Comma-separated list of dependency IDs\n' +
     '  -s, --status <status>     Status for the new subtask (default: "pending")\n' +
     '  -f, --file <file>         Path to the tasks file (default: "tasks/tasks.json")\n' +
-    '  --skip-generate           Skip regenerating task files\n\n' +
+    '  --generate                Regenerate task files after adding subtask\n\n' +
     chalk.cyan('Examples:') + '\n' +
     '  task-master add-subtask --parent=\'5\' --task-id=\'8\'\n' +
     '  task-master add-subtask -p \'5\' -t \'Implement login UI\' -d \'Create the login form\'\n' +
-    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details $\'Handle 401 Unauthorized.\nHandle 500 Server Error.\'',
+    '  task-master add-subtask -p \'5\' -t \'Handle API Errors\' --details "Handle 401 Unauthorized.\\nHandle 500 Server Error." --generate',
     { padding: 1, borderColor: 'blue', borderStyle: 'round' }
   ));
 }
@@ -652,7 +652,7 @@ function showRemoveSubtaskHelp() {
     '  -i, --id <id>       Subtask ID(s) to remove in format "parentId.subtaskId" (can be comma-separated, required)\n' +
     '  -c, --convert       Convert the subtask to a standalone task instead of deleting it\n' +
     '  -f, --file <file>   Path to the tasks file (default: "tasks/tasks.json")\n' +
-    '  --skip-generate     Skip regenerating task files\n\n' +
+    '  --generate          Regenerate task files after removing subtask\n\n' +
     chalk.cyan('Examples:') + '\n' +
     '  task-master remove-subtask --id=\'5.2\'\n' +
     '  task-master remove-subtask --id=\'5.2,6.3,7.1\'\n' +

.cursor/rules/taskmaster.mdc

@@ -158,7 +158,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `details`: `Provide implementation notes or details for the new subtask.` (CLI: `--details <text>`)
     *   `dependencies`: `Specify IDs of other tasks or subtasks, e.g., '15' or '16.1', that must be done before this new subtask.` (CLI: `--dependencies <ids>`)
     *   `status`: `Set the initial status for the new subtask. Default is 'pending'.` (CLI: `-s, --status <status>`)
-    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after adding the subtask.` (CLI: `--skip-generate`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after adding the subtask.` (CLI: `--generate`)
     *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Break down tasks manually or reorganize existing tasks.
@@ -286,7 +286,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **Key Parameters/Options:**
     *   `id`: `Required. The ID(s) of the Taskmaster subtask(s) to remove, e.g., '15.2' or '16.1,16.3'.` (CLI: `-i, --id <id>`)
     *   `convert`: `If used, Taskmaster will turn the subtask into a regular top-level task instead of deleting it.` (CLI: `-c, --convert`)
-    *   `skipGenerate`: `Prevent Taskmaster from automatically regenerating markdown task files after removing the subtask.` (CLI: `--skip-generate`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after removing the subtask.` (CLI: `--generate`)
     *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
     *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
 *   **Usage:** Delete unnecessary subtasks or promote a subtask to a top-level task.

.cursor/rules/test_workflow.mdc

@@ -0,0 +1,803 @@
+---
+description: 
+globs: 
+alwaysApply: true
+---
+# Test Workflow & Development Process
+
+## **Initial Testing Framework Setup**
+
+Before implementing the TDD workflow, ensure your project has a proper testing framework configured. This section covers setup for different technology stacks.
+
+### **Detecting Project Type & Framework Needs**
+
+**AI Agent Assessment Checklist:**
+1. **Language Detection**: Check for `package.json` (Node.js/JavaScript), `requirements.txt` (Python), `Cargo.toml` (Rust), etc.
+2. **Existing Tests**: Look for test files (`.test.`, `.spec.`, `_test.`) or test directories
+3. **Framework Detection**: Check for existing test runners in dependencies
+4. **Project Structure**: Analyze directory structure for testing patterns
+
+### **JavaScript/Node.js Projects (Jest Setup)**
+
+#### **Prerequisites Check**
+```bash
+# Verify Node.js project
+ls package.json  # Should exist
+
+# Check for existing testing setup
+ls jest.config.js jest.config.ts  # Check for Jest config
+grep -E "(jest|vitest|mocha)" package.json  # Check for test runners
+```
+
+#### **Jest Installation & Configuration**
+
+**Step 1: Install Dependencies**
+```bash
+# Core Jest dependencies
+npm install --save-dev jest
+
+# TypeScript support (if using TypeScript)
+npm install --save-dev ts-jest @types/jest
+
+# Additional useful packages
+npm install --save-dev supertest @types/supertest  # For API testing
+npm install --save-dev jest-watch-typeahead  # Enhanced watch mode
+```
+
+**Step 2: Create Jest Configuration**
+
+Create `jest.config.js` with the following production-ready configuration:
+
+```javascript
+/** @type {import('jest').Config} */
+module.exports = {
+  // Use ts-jest preset for TypeScript support
+  preset: 'ts-jest',
+
+  // Test environment
+  testEnvironment: 'node',
+
+  // Roots for test discovery
+  roots: ['<rootDir>/src', '<rootDir>/tests'],
+
+  // Test file patterns
+  testMatch: ['**/__tests__/**/*.ts', '**/?(*.)+(spec|test).ts'],
+
+  // Transform files
+  transform: {
+    '^.+\\.ts$': [
+      'ts-jest',
+      {
+        tsconfig: {
+          target: 'es2020',
+          module: 'commonjs',
+          esModuleInterop: true,
+          allowSyntheticDefaultImports: true,
+          skipLibCheck: true,
+          strict: false,
+          noImplicitAny: false,
+        },
+      },
+    ],
+    '^.+\\.js$': [
+      'ts-jest',
+      {
+        useESM: false,
+        tsconfig: {
+          target: 'es2020',
+          module: 'commonjs',
+          esModuleInterop: true,
+          allowSyntheticDefaultImports: true,
+          allowJs: true,
+        },
+      },
+    ],
+  },
+
+  // Module file extensions
+  moduleFileExtensions: ['ts', 'tsx', 'js', 'jsx', 'json', 'node'],
+
+  // Transform ignore patterns - adjust for ES modules
+  transformIgnorePatterns: ['node_modules/(?!(your-es-module-deps|.*\\.mjs$))'],
+
+  // Coverage configuration
+  collectCoverage: true,
+  coverageDirectory: 'coverage',
+  coverageReporters: [
+    'text', // Console output
+    'text-summary', // Brief summary
+    'lcov', // For IDE integration
+    'html', // Detailed HTML report
+  ],
+
+  // Files to collect coverage from
+  collectCoverageFrom: [
+    'src/**/*.ts',
+    '!src/**/*.d.ts',
+    '!src/**/*.test.ts',
+    '!src/**/index.ts', // Often just exports
+    '!src/generated/**', // Generated code
+    '!src/config/database.ts', // Database config (tested via integration)
+  ],
+
+  // Coverage thresholds - TaskMaster standards
+  coverageThreshold: {
+    global: {
+      branches: 70,
+      functions: 80,
+      lines: 80,
+      statements: 80,
+    },
+    // Higher standards for critical business logic
+    './src/utils/': {
+      branches: 85,
+      functions: 90,
+      lines: 90,
+      statements: 90,
+    },
+    './src/middleware/': {
+      branches: 80,
+      functions: 85,
+      lines: 85,
+      statements: 85,
+    },
+  },
+
+  // Setup files
+  setupFilesAfterEnv: ['<rootDir>/tests/setup.ts'],
+
+  // Global teardown to prevent worker process leaks
+  globalTeardown: '<rootDir>/tests/teardown.ts',
+
+  // Module path mapping (if needed)
+  moduleNameMapper: {
+    '^@/(.*)$': '<rootDir>/src/$1',
+  },
+
+  // Clear mocks between tests
+  clearMocks: true,
+
+  // Restore mocks after each test
+  restoreMocks: true,
+
+  // Global test timeout
+  testTimeout: 10000,
+
+  // Projects for different test types
+  projects: [
+    // Unit tests - for pure functions only
+    {
+      displayName: 'unit',
+      testMatch: ['<rootDir>/src/**/*.test.ts'],
+      testPathIgnorePatterns: ['.*\\.integration\\.test\\.ts$', '/tests/'],
+      preset: 'ts-jest',
+      testEnvironment: 'node',
+      collectCoverageFrom: [
+        'src/**/*.ts',
+        '!src/**/*.d.ts',
+        '!src/**/*.test.ts',
+        '!src/**/*.integration.test.ts',
+      ],
+      coverageThreshold: {
+        global: {
+          branches: 70,
+          functions: 80,
+          lines: 80,
+          statements: 80,
+        },
+      },
+    },
+    // Integration tests - real database/services
+    {
+      displayName: 'integration',
+      testMatch: [
+        '<rootDir>/src/**/*.integration.test.ts',
+        '<rootDir>/tests/integration/**/*.test.ts',
+      ],
+      preset: 'ts-jest',
+      testEnvironment: 'node',
+      setupFilesAfterEnv: ['<rootDir>/tests/setup/integration.ts'],
+      testTimeout: 10000,
+    },
+    // E2E tests - full workflows
+    {
+      displayName: 'e2e',
+      testMatch: ['<rootDir>/tests/e2e/**/*.test.ts'],
+      preset: 'ts-jest',
+      testEnvironment: 'node',
+      setupFilesAfterEnv: ['<rootDir>/tests/setup/e2e.ts'],
+      testTimeout: 30000,
+    },
+  ],
+
+  // Verbose output for better debugging
+  verbose: true,
+
+  // Run projects sequentially to avoid conflicts
+  maxWorkers: 1,
+
+  // Enable watch mode plugins
+  watchPlugins: ['jest-watch-typeahead/filename', 'jest-watch-typeahead/testname'],
+};
+```
+
+**Step 3: Update package.json Scripts**
+
+Add these scripts to your `package.json`:
+
+```json
+{
+  "scripts": {
+    "test": "jest",
+    "test:watch": "jest --watch",
+    "test:coverage": "jest --coverage",
+    "test:unit": "jest --selectProjects unit",
+    "test:integration": "jest --selectProjects integration", 
+    "test:e2e": "jest --selectProjects e2e",
+    "test:ci": "jest --ci --coverage --watchAll=false"
+  }
+}
+```
+
+**Step 4: Create Test Setup Files**
+
+Create essential test setup files:
+
+```typescript
+// tests/setup.ts - Global setup
+import { jest } from '@jest/globals';
+
+// Global test configuration
+beforeAll(() => {
+  // Set test timeout
+  jest.setTimeout(10000);
+});
+
+afterEach(() => {
+  // Clean up mocks after each test
+  jest.clearAllMocks();
+});
+```
+
+```typescript
+// tests/setup/integration.ts - Integration test setup
+import { PrismaClient } from '@prisma/client';
+
+const prisma = new PrismaClient();
+
+beforeAll(async () => {
+  // Connect to test database
+  await prisma.$connect();
+});
+
+afterAll(async () => {
+  // Cleanup and disconnect
+  await prisma.$disconnect();
+});
+
+beforeEach(async () => {
+  // Clean test data before each test
+  // Add your cleanup logic here
+});
+```
+
+```typescript
+// tests/teardown.ts - Global teardown
+export default async () => {
+  // Global cleanup after all tests
+  console.log('Global test teardown complete');
+};
+```
+
+**Step 5: Create Initial Test Structure**
+
+```bash
+# Create test directories
+mkdir -p tests/{setup,fixtures,unit,integration,e2e}
+mkdir -p tests/unit/src/{utils,services,middleware}
+
+# Create sample test fixtures
+mkdir tests/fixtures
+```
+
+### **Generic Testing Framework Setup (Any Language)**
+
+#### **Framework Selection Guide**
+
+**Python Projects:**
+- **pytest**: Recommended for most Python projects
+- **unittest**: Built-in, suitable for simple projects
+- **Coverage**: Use `coverage.py` for code coverage
+
+```bash
+# Python setup example
+pip install pytest pytest-cov
+echo "[tool:pytest]" > pytest.ini
+echo "testpaths = tests" >> pytest.ini
+echo "addopts = --cov=src --cov-report=html --cov-report=term" >> pytest.ini
+```
+
+**Go Projects:**
+- **Built-in testing**: Use Go's built-in `testing` package
+- **Coverage**: Built-in with `go test -cover`
+
+```bash
+# Go setup example
+go mod init your-project
+mkdir -p tests
+# Tests are typically *_test.go files alongside source
+```
+
+**Rust Projects:**
+- **Built-in testing**: Use Rust's built-in test framework
+- **cargo-tarpaulin**: For coverage analysis
+
+```bash
+# Rust setup example
+cargo new your-project
+cd your-project
+cargo install cargo-tarpaulin  # For coverage
+```
+
+**Java Projects:**
+- **JUnit 5**: Modern testing framework
+- **Maven/Gradle**: Build tools with testing integration
+
+```xml
+<!-- Maven pom.xml example -->
+<dependency>
+    <groupId>org.junit.jupiter</groupId>
+    <artifactId>junit-jupiter</artifactId>
+    <version>5.9.2</version>
+    <scope>test</scope>
+</dependency>
+```
+
+#### **Universal Testing Principles**
+
+**Coverage Standards (Adapt to Your Language):**
+- **Global Minimum**: 70-80% line coverage
+- **Critical Code**: 85-90% coverage
+- **New Features**: Must meet or exceed standards
+- **Legacy Code**: Gradual improvement strategy
+
+**Test Organization:**
+- **Unit Tests**: Fast, isolated, no external dependencies
+- **Integration Tests**: Test component interactions
+- **E2E Tests**: Test complete user workflows
+- **Performance Tests**: Load and stress testing (if applicable)
+
+**Naming Conventions:**
+- **Test Files**: `*.test.*`, `*_test.*`, or language-specific patterns
+- **Test Functions**: Descriptive names (e.g., `should_return_error_for_invalid_input`)
+- **Test Directories**: Organized by test type and mirroring source structure
+
+#### **TaskMaster Integration for Any Framework**
+
+**Document Testing Setup in Subtasks:**
+```bash
+# Update subtask with testing framework setup
+task-master update-subtask --id=X.Y --prompt="Testing framework setup:
+- Installed [Framework Name] with coverage support
+- Configured [Coverage Tool] with thresholds: 80% lines, 70% branches
+- Created test directory structure: unit/, integration/, e2e/
+- Added test scripts to build configuration
+- All setup tests passing"
+```
+
+**Testing Framework Verification:**
+```bash
+# Verify setup works
+[test-command]  # e.g., npm test, pytest, go test, cargo test
+
+# Check coverage reporting
+[coverage-command]  # e.g., npm run test:coverage
+
+# Update task with verification
+task-master update-subtask --id=X.Y --prompt="Testing framework verified:
+- Sample tests running successfully
+- Coverage reporting functional
+- CI/CD integration ready
+- Ready to begin TDD workflow"
+```
+
+## **Test-Driven Development (TDD) Integration**
+
+### **Core TDD Cycle with Jest**
+```bash
+# 1. Start development with watch mode
+npm run test:watch
+
+# 2. Write failing test first
+# Create test file: src/utils/newFeature.test.ts
+# Write test that describes expected behavior
+
+# 3. Implement minimum code to make test pass
+# 4. Refactor while keeping tests green
+# 5. Add edge cases and error scenarios
+```
+
+### **TDD Workflow Per Subtask**
+```bash
+# When starting a new subtask:
+task-master set-status --id=4.1 --status=in-progress
+
+# Begin TDD cycle:
+npm run test:watch  # Keep running during development
+
+# Document TDD progress in subtask:
+task-master update-subtask --id=4.1 --prompt="TDD Progress:
+- Written 3 failing tests for core functionality
+- Implemented basic feature, tests now passing
+- Adding edge case tests for error handling"
+
+# Complete subtask with test summary:
+task-master update-subtask --id=4.1 --prompt="Implementation complete:
+- Feature implemented with 8 unit tests
+- Coverage: 95% statements, 88% branches  
+- All tests passing, TDD cycle complete"
+```
+
+## **Testing Commands & Usage**
+
+### **Development Commands**
+```bash
+# Primary development command - use during coding
+npm run test:watch              # Watch mode with Jest
+npm run test:watch -- --testNamePattern="auth"  # Watch specific tests
+
+# Targeted testing during development
+npm run test:unit               # Run only unit tests
+npm run test:unit -- --coverage # Unit tests with coverage
+
+# Integration testing when APIs are ready
+npm run test:integration        # Run integration tests
+npm run test:integration -- --detectOpenHandles  # Debug hanging tests
+
+# End-to-end testing for workflows
+npm run test:e2e               # Run E2E tests
+npm run test:e2e -- --timeout=30000  # Extended timeout for E2E
+```
+
+### **Quality Assurance Commands**
+```bash
+# Full test suite with coverage (before commits)
+npm run test:coverage          # Complete coverage analysis
+
+# All tests (CI/CD pipeline)
+npm test                       # Run all test projects
+
+# Specific test file execution
+npm test -- auth.test.ts       # Run specific test file
+npm test -- --testNamePattern="should handle errors"  # Run specific tests
+```
+
+## **Test Implementation Patterns**
+
+### **Unit Test Development**
+```typescript
+// ✅ DO: Follow established patterns from auth.test.ts
+describe('FeatureName', () => {
+  beforeEach(() => {
+    jest.clearAllMocks();
+    // Setup mocks with proper typing
+  });
+
+  describe('functionName', () => {
+    it('should handle normal case', () => {
+      // Test implementation with specific assertions
+    });
+    
+    it('should throw error for invalid input', async () => {
+      // Error scenario testing
+      await expect(functionName(invalidInput))
+        .rejects.toThrow('Specific error message');
+    });
+  });
+});
+```
+
+### **Integration Test Development**  
+```typescript
+// ✅ DO: Use supertest for API endpoint testing
+import request from 'supertest';
+import { app } from '../../src/app';
+
+describe('POST /api/auth/register', () => {
+  beforeEach(async () => {
+    await integrationTestUtils.cleanupTestData();
+  });
+  
+  it('should register user successfully', async () => {
+    const userData = createTestUser();
+    
+    const response = await request(app)
+      .post('/api/auth/register')
+      .send(userData)
+      .expect(201);
+      
+    expect(response.body).toMatchObject({
+      id: expect.any(String),
+      email: userData.email
+    });
+    
+    // Verify database state
+    const user = await prisma.user.findUnique({
+      where: { email: userData.email }
+    });
+    expect(user).toBeTruthy();
+  });
+});
+```
+
+### **E2E Test Development**
+```typescript
+// ✅ DO: Test complete user workflows
+describe('User Authentication Flow', () => {
+  it('should complete registration → login → protected access', async () => {
+    // Step 1: Register
+    const userData = createTestUser();
+    await request(app)
+      .post('/api/auth/register')
+      .send(userData)
+      .expect(201);
+    
+    // Step 2: Login
+    const loginResponse = await request(app)
+      .post('/api/auth/login')
+      .send({ email: userData.email, password: userData.password })
+      .expect(200);
+    
+    const { token } = loginResponse.body;
+    
+    // Step 3: Access protected resource
+    await request(app)
+      .get('/api/profile')
+      .set('Authorization', `Bearer ${token}`)
+      .expect(200);
+  }, 30000); // Extended timeout for E2E
+});
+```
+
+## **Mocking & Test Utilities**
+
+### **Established Mocking Patterns**
+```typescript
+// ✅ DO: Use established bcrypt mocking pattern
+jest.mock('bcrypt');
+import bcrypt from 'bcrypt';
+const mockHash = bcrypt.hash as jest.MockedFunction<typeof bcrypt.hash>;
+const mockCompare = bcrypt.compare as jest.MockedFunction<typeof bcrypt.compare>;
+
+// ✅ DO: Use Prisma mocking for unit tests
+jest.mock('@prisma/client', () => ({
+  PrismaClient: jest.fn().mockImplementation(() => ({
+    user: {
+      create: jest.fn(),
+      findUnique: jest.fn(),
+    },
+    $connect: jest.fn(),
+    $disconnect: jest.fn(),
+  })),
+}));
+```
+
+### **Test Fixtures Usage**
+```typescript
+// ✅ DO: Use centralized test fixtures
+import { createTestUser, adminUser, invalidUser } from '../fixtures/users';
+
+describe('User Service', () => {
+  it('should handle admin user creation', async () => {
+    const userData = createTestUser(adminUser);
+    // Test implementation
+  });
+  
+  it('should reject invalid user data', async () => {
+    const userData = createTestUser(invalidUser);
+    // Error testing
+  });
+});
+```
+
+## **Coverage Standards & Monitoring**
+
+### **Coverage Thresholds**
+- **Global Standards**: 80% lines/functions, 70% branches
+- **Critical Code**: 90% utils, 85% middleware
+- **New Features**: Must meet or exceed global thresholds
+- **Legacy Code**: Gradual improvement with each change
+
+### **Coverage Reporting & Analysis**
+```bash
+# Generate coverage reports
+npm run test:coverage
+
+# View detailed HTML report
+open coverage/lcov-report/index.html
+
+# Coverage files generated:
+# - coverage/lcov-report/index.html  # Detailed HTML report
+# - coverage/lcov.info               # LCOV format for IDE integration  
+# - coverage/coverage-final.json     # JSON format for tooling
+```
+
+### **Coverage Quality Checks**
+```typescript
+// ✅ DO: Test all code paths
+describe('validateInput', () => {
+  it('should return true for valid input', () => {
+    expect(validateInput('valid')).toBe(true);
+  });
+  
+  it('should return false for various invalid inputs', () => {
+    expect(validateInput('')).toBe(false);      // Empty string
+    expect(validateInput(null)).toBe(false);    // Null value
+    expect(validateInput(undefined)).toBe(false); // Undefined
+  });
+  
+  it('should throw for unexpected input types', () => {
+    expect(() => validateInput(123)).toThrow('Invalid input type');
+  });
+});
+```
+
+## **Testing During Development Phases**
+
+### **Feature Development Phase**
+```bash
+# 1. Start feature development
+task-master set-status --id=X.Y --status=in-progress
+
+# 2. Begin TDD cycle  
+npm run test:watch
+
+# 3. Document test progress in subtask
+task-master update-subtask --id=X.Y --prompt="Test development:
+- Created test file with 5 failing tests
+- Implemented core functionality
+- Tests passing, adding error scenarios"
+
+# 4. Verify coverage before completion
+npm run test:coverage
+
+# 5. Update subtask with final test status
+task-master update-subtask --id=X.Y --prompt="Testing complete:
+- 12 unit tests with full coverage
+- All edge cases and error scenarios covered
+- Ready for integration testing"
+```
+
+### **Integration Testing Phase**
+```bash
+# After API endpoints are implemented
+npm run test:integration
+
+# Update integration test templates
+# Replace placeholder tests with real endpoint calls
+
+# Document integration test results
+task-master update-subtask --id=X.Y --prompt="Integration tests:
+- Updated auth endpoint tests  
+- Database integration verified
+- All HTTP status codes and responses tested"
+```
+
+### **Pre-Commit Testing Phase**
+```bash
+# Before committing code
+npm run test:coverage         # Verify all tests pass with coverage
+npm run test:unit            # Quick unit test verification
+npm run test:integration     # Integration test verification (if applicable)
+
+# Commit pattern for test updates
+git add tests/ src/**/*.test.ts
+git commit -m "test(task-X): Add comprehensive tests for Feature Y
+
+- Unit tests with 95% coverage (exceeds 90% threshold)
+- Integration tests for API endpoints
+- Test fixtures for data generation
+- Proper mocking patterns established
+
+Task X: Feature Y - Testing complete"
+```
+
+## **Error Handling & Debugging**
+
+### **Test Debugging Techniques**
+```typescript
+// ✅ DO: Use test utilities for debugging
+import { testUtils } from '../setup';
+
+it('should debug complex operation', () => {
+  testUtils.withConsole(() => {
+    // Console output visible only for this test
+    console.log('Debug info:', complexData);
+    service.complexOperation();
+  });
+});
+
+// ✅ DO: Use proper async debugging
+it('should handle async operations', async () => {
+  const promise = service.asyncOperation();
+  
+  // Test intermediate state
+  expect(service.isProcessing()).toBe(true);
+  
+  const result = await promise;
+  expect(result).toBe('expected');
+  expect(service.isProcessing()).toBe(false);
+});
+```
+
+### **Common Test Issues & Solutions**
+```bash
+# Hanging tests (common with database connections)
+npm run test:integration -- --detectOpenHandles
+
+# Memory leaks in tests
+npm run test:unit -- --logHeapUsage
+
+# Slow tests identification
+npm run test:coverage -- --verbose
+
+# Mock not working properly
+# Check: mock is declared before imports
+# Check: jest.clearAllMocks() in beforeEach
+# Check: TypeScript typing is correct
+```
+
+## **Continuous Integration Integration**
+
+### **CI/CD Pipeline Testing**
+```yaml
+# Example GitHub Actions integration
+- name: Run tests
+  run: |
+    npm ci
+    npm run test:coverage
+    
+- name: Upload coverage reports
+  uses: codecov/codecov-action@v3
+  with:
+    file: ./coverage/lcov.info
+```
+
+### **Pre-commit Hooks**
+```bash
+# Setup pre-commit testing (recommended)
+# In package.json scripts:
+"pre-commit": "npm run test:unit && npm run test:integration"
+
+# Husky integration example:
+npx husky add .husky/pre-commit "npm run test:unit"
+```
+
+## **Test Maintenance & Evolution**
+
+### **Adding Tests for New Features**
+1. **Create test file** alongside source code or in `tests/unit/`
+2. **Follow established patterns** from `src/utils/auth.test.ts`
+3. **Use existing fixtures** from `tests/fixtures/`
+4. **Apply proper mocking** patterns for dependencies
+5. **Meet coverage thresholds** for the module
+
+### **Updating Integration/E2E Tests**
+1. **Update templates** in `tests/integration/` when APIs change
+2. **Modify E2E workflows** in `tests/e2e/` for new user journeys  
+3. **Update test fixtures** for new data requirements
+4. **Maintain database cleanup** utilities
+
+### **Test Performance Optimization**
+- **Parallel execution**: Jest runs tests in parallel by default
+- **Test isolation**: Use proper setup/teardown for independence
+- **Mock optimization**: Mock heavy dependencies appropriately  
+- **Database efficiency**: Use transaction rollbacks where possible
+
+---
+
+**Key References:**
+- [Testing Standards](mdc:.cursor/rules/tests.mdc)
+- [Git Workflow](mdc:.cursor/rules/git_workflow.mdc)
+- [Development Workflow](mdc:.cursor/rules/dev_workflow.mdc)
+- [Jest Configuration](mdc:jest.config.js)

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,45 @@
+# What type of PR is this?
+<!-- Check one -->
+
+ - [ ] 🐛 Bug fix
+ - [ ] ✨ Feature
+ - [ ] 🔌 Integration
+ - [ ] 📝 Docs
+ - [ ] 🧹 Refactor
+ - [ ] Other:
+## Description
+<!-- What does this PR do? -->
+
+## Related Issues
+<!-- Link issues: Fixes #123 -->
+
+## How to Test This
+<!-- Quick steps to verify the changes work -->
+```bash
+# Example commands or steps
+```
+
+**Expected result:**
+<!-- What should happen? -->
+
+## Contributor Checklist
+
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check` (or `npm run format` to fix)
+- [ ] Addressed CodeRabbit comments (if any)
+- [ ] Linked related issues (if any)
+- [ ] Manually tested the changes
+
+## Changelog Entry
+<!-- One line describing the change for users -->
+<!-- Example: "Added Kiro IDE integration with automatic task status updates" -->
+
+---
+
+### For Maintainers
+
+- [ ] PR title follows conventional commits
+- [ ] Target branch correct
+- [ ] Labels added
+- [ ] Milestone assigned (if applicable)

.github/PULL_REQUEST_TEMPLATE/bugfix.md

@@ -0,0 +1,39 @@
+## 🐛 Bug Fix
+
+### 🔍 Bug Description
+<!-- Describe the bug -->
+
+### 🔗 Related Issues
+<!-- Fixes #123 -->
+
+### ✨ Solution
+<!-- How does this PR fix the bug? -->
+
+## How to Test
+
+### Steps that caused the bug:
+1. 
+2. 
+
+**Before fix:** 
+**After fix:** 
+
+### Quick verification:
+```bash
+# Commands to verify the fix
+```
+
+## Contributor Checklist
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Added unit tests (if applicable)
+- [ ] Manually verified the fix works
+
+---
+
+### For Maintainers
+- [ ] Root cause identified
+- [ ] Fix doesn't introduce new issues
+- [ ] CI passes

.github/PULL_REQUEST_TEMPLATE/config.yml

@@ -0,0 +1,11 @@
+blank_issues_enabled: false
+contact_links:
+  - name: 🐛 Bug Fix
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=bugfix.md
+    about: Fix a bug in Task Master
+  - name: ✨ New Feature
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=feature.md
+    about: Add a new feature to Task Master
+  - name: 🔌 New Integration
+    url: https://github.com/eyaltoledano/claude-task-master/compare/next...HEAD?template=integration.md
+    about: Add support for a new tool, IDE, or platform

.github/PULL_REQUEST_TEMPLATE/feature.md

@@ -0,0 +1,49 @@
+## ✨ New Feature
+
+### 📋 Feature Description
+<!-- Brief description -->
+
+### 🎯 Problem Statement
+<!-- What problem does this feature solve? Why is it needed? -->
+
+### 💡 Solution
+<!-- How does this feature solve the problem? What's the approach? -->
+
+### 🔗 Related Issues
+<!-- Link related issues: Fixes #123, Part of #456 -->
+
+## How to Use It
+
+### Quick Start
+```bash
+# Basic usage example
+```
+
+### Example
+<!-- Show a real use case -->
+```bash
+# Practical example
+```
+
+**What you should see:**
+<!-- Expected behavior -->
+
+## Contributor Checklist
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Added tests for new functionality
+- [ ] Manually tested in CLI mode
+- [ ] Manually tested in MCP mode (if applicable)
+
+## Changelog Entry
+<!-- One-liner for release notes -->
+
+---
+
+### For Maintainers
+
+- [ ] Feature aligns with project vision
+- [ ] CIs pass
+- [ ] Changeset file exists

.github/PULL_REQUEST_TEMPLATE/integration.md

@@ -0,0 +1,53 @@
+# 🔌 New Integration
+
+## What tool/IDE is being integrated?
+
+<!-- Name and brief description -->
+
+## What can users do with it?
+
+<!-- Key benefits -->
+
+## How to Enable
+
+### Setup
+
+```bash
+task-master rules add [name]
+# Any other setup steps
+```
+
+### Example Usage
+
+<!-- Show it in action -->
+
+```bash
+# Real example
+```
+
+### Natural Language Hooks (if applicable)
+
+```
+"When tests pass, mark task as done"
+# Other examples
+```
+
+## Contributor Checklist
+
+- [ ] Created changeset: `npm run changeset`
+- [ ] Tests pass: `npm test`
+- [ ] Format check passes: `npm run format-check`
+- [ ] Addressed CodeRabbit comments
+- [ ] Integration fully tested with target tool/IDE
+- [ ] Error scenarios tested
+- [ ] Added integration tests
+- [ ] Documentation includes setup guide
+- [ ] Examples are working and clear
+
+---
+
+## For Maintainers
+
+- [ ] Integration stability verified
+- [ ] Documentation comprehensive
+- [ ] Examples working

.github/scripts/auto-close-duplicates.mjs

@@ -0,0 +1,259 @@
+#!/usr/bin/env node
+
+async function githubRequest(endpoint, token, method = 'GET', body) {
+	const response = await fetch(`https://api.github.com${endpoint}`, {
+		method,
+		headers: {
+			Authorization: `Bearer ${token}`,
+			Accept: 'application/vnd.github.v3+json',
+			'User-Agent': 'auto-close-duplicates-script',
+			...(body && { 'Content-Type': 'application/json' })
+		},
+		...(body && { body: JSON.stringify(body) })
+	});
+
+	if (!response.ok) {
+		throw new Error(
+			`GitHub API request failed: ${response.status} ${response.statusText}`
+		);
+	}
+
+	return response.json();
+}
+
+function extractDuplicateIssueNumber(commentBody) {
+	const match = commentBody.match(/#(\d+)/);
+	return match ? parseInt(match[1], 10) : null;
+}
+
+async function closeIssueAsDuplicate(
+	owner,
+	repo,
+	issueNumber,
+	duplicateOfNumber,
+	token
+) {
+	await githubRequest(
+		`/repos/${owner}/${repo}/issues/${issueNumber}`,
+		token,
+		'PATCH',
+		{
+			state: 'closed',
+			state_reason: 'not_planned',
+			labels: ['duplicate']
+		}
+	);
+
+	await githubRequest(
+		`/repos/${owner}/${repo}/issues/${issueNumber}/comments`,
+		token,
+		'POST',
+		{
+			body: `This issue has been automatically closed as a duplicate of #${duplicateOfNumber}.
+
+If this is incorrect, please re-open this issue or create a new one.
+
+🤖 Generated with [Task Master Bot]`
+		}
+	);
+}
+
+async function autoCloseDuplicates() {
+	console.log('[DEBUG] Starting auto-close duplicates script');
+
+	const token = process.env.GITHUB_TOKEN;
+	if (!token) {
+		throw new Error('GITHUB_TOKEN environment variable is required');
+	}
+	console.log('[DEBUG] GitHub token found');
+
+	const owner = process.env.GITHUB_REPOSITORY_OWNER || 'eyaltoledano';
+	const repo = process.env.GITHUB_REPOSITORY_NAME || 'claude-task-master';
+	console.log(`[DEBUG] Repository: ${owner}/${repo}`);
+
+	const threeDaysAgo = new Date();
+	threeDaysAgo.setDate(threeDaysAgo.getDate() - 3);
+	console.log(
+		`[DEBUG] Checking for duplicate comments older than: ${threeDaysAgo.toISOString()}`
+	);
+
+	console.log('[DEBUG] Fetching open issues created more than 3 days ago...');
+	const allIssues = [];
+	let page = 1;
+	const perPage = 100;
+
+	const MAX_PAGES = 50; // Increase limit for larger repos
+	let foundRecentIssue = false;
+
+	while (true) {
+		const pageIssues = await githubRequest(
+			`/repos/${owner}/${repo}/issues?state=open&per_page=${perPage}&page=${page}&sort=created&direction=desc`,
+			token
+		);
+
+		if (pageIssues.length === 0) break;
+
+		// Filter for issues created more than 3 days ago
+		const oldEnoughIssues = pageIssues.filter(
+			(issue) => new Date(issue.created_at) <= threeDaysAgo
+		);
+
+		allIssues.push(...oldEnoughIssues);
+
+		// If all issues on this page are newer than 3 days, we can stop
+		if (oldEnoughIssues.length === 0 && page === 1) {
+			foundRecentIssue = true;
+			break;
+		}
+
+		// If we found some old issues but not all, continue to next page
+		// as there might be more old issues
+		page++;
+
+		// Safety limit to avoid infinite loops
+		if (page > MAX_PAGES) {
+			console.log(`[WARNING] Reached maximum page limit of ${MAX_PAGES}`);
+			break;
+		}
+	}
+
+	const issues = allIssues;
+	console.log(`[DEBUG] Found ${issues.length} open issues`);
+
+	let processedCount = 0;
+	let candidateCount = 0;
+
+	for (const issue of issues) {
+		processedCount++;
+		console.log(
+			`[DEBUG] Processing issue #${issue.number} (${processedCount}/${issues.length}): ${issue.title}`
+		);
+
+		console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
+		const comments = await githubRequest(
+			`/repos/${owner}/${repo}/issues/${issue.number}/comments`,
+			token
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} has ${comments.length} comments`
+		);
+
+		const dupeComments = comments.filter(
+			(comment) =>
+				comment.body.includes('Found') &&
+				comment.body.includes('possible duplicate') &&
+				comment.user.type === 'Bot'
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} has ${dupeComments.length} duplicate detection comments`
+		);
+
+		if (dupeComments.length === 0) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} - no duplicate comments found, skipping`
+			);
+			continue;
+		}
+
+		const lastDupeComment = dupeComments[dupeComments.length - 1];
+		const dupeCommentDate = new Date(lastDupeComment.created_at);
+		console.log(
+			`[DEBUG] Issue #${
+				issue.number
+			} - most recent duplicate comment from: ${dupeCommentDate.toISOString()}`
+		);
+
+		if (dupeCommentDate > threeDaysAgo) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} - duplicate comment is too recent, skipping`
+			);
+			continue;
+		}
+		console.log(
+			`[DEBUG] Issue #${
+				issue.number
+			} - duplicate comment is old enough (${Math.floor(
+				(Date.now() - dupeCommentDate.getTime()) / (1000 * 60 * 60 * 24)
+			)} days)`
+		);
+
+		const commentsAfterDupe = comments.filter(
+			(comment) => new Date(comment.created_at) > dupeCommentDate
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} - ${commentsAfterDupe.length} comments after duplicate detection`
+		);
+
+		if (commentsAfterDupe.length > 0) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} - has activity after duplicate comment, skipping`
+			);
+			continue;
+		}
+
+		console.log(
+			`[DEBUG] Issue #${issue.number} - checking reactions on duplicate comment...`
+		);
+		const reactions = await githubRequest(
+			`/repos/${owner}/${repo}/issues/comments/${lastDupeComment.id}/reactions`,
+			token
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} - duplicate comment has ${reactions.length} reactions`
+		);
+
+		const authorThumbsDown = reactions.some(
+			(reaction) =>
+				reaction.user.id === issue.user.id && reaction.content === '-1'
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} - author thumbs down reaction: ${authorThumbsDown}`
+		);
+
+		if (authorThumbsDown) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} - author disagreed with duplicate detection, skipping`
+			);
+			continue;
+		}
+
+		const duplicateIssueNumber = extractDuplicateIssueNumber(
+			lastDupeComment.body
+		);
+		if (!duplicateIssueNumber) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} - could not extract duplicate issue number from comment, skipping`
+			);
+			continue;
+		}
+
+		candidateCount++;
+		const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
+
+		try {
+			console.log(
+				`[INFO] Auto-closing issue #${issue.number} as duplicate of #${duplicateIssueNumber}: ${issueUrl}`
+			);
+			await closeIssueAsDuplicate(
+				owner,
+				repo,
+				issue.number,
+				duplicateIssueNumber,
+				token
+			);
+			console.log(
+				`[SUCCESS] Successfully closed issue #${issue.number} as duplicate of #${duplicateIssueNumber}`
+			);
+		} catch (error) {
+			console.error(
+				`[ERROR] Failed to close issue #${issue.number} as duplicate: ${error}`
+			);
+		}
+	}
+
+	console.log(
+		`[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates for auto-close`
+	);
+}
+
+autoCloseDuplicates().catch(console.error);

.github/scripts/backfill-duplicate-comments.mjs

@@ -0,0 +1,178 @@
+#!/usr/bin/env node
+
+async function githubRequest(endpoint, token, method = 'GET', body) {
+	const response = await fetch(`https://api.github.com${endpoint}`, {
+		method,
+		headers: {
+			Authorization: `Bearer ${token}`,
+			Accept: 'application/vnd.github.v3+json',
+			'User-Agent': 'backfill-duplicate-comments-script',
+			...(body && { 'Content-Type': 'application/json' })
+		},
+		...(body && { body: JSON.stringify(body) })
+	});
+
+	if (!response.ok) {
+		throw new Error(
+			`GitHub API request failed: ${response.status} ${response.statusText}`
+		);
+	}
+
+	return response.json();
+}
+
+async function triggerDedupeWorkflow(
+	owner,
+	repo,
+	issueNumber,
+	token,
+	dryRun = true
+) {
+	if (dryRun) {
+		console.log(
+			`[DRY RUN] Would trigger dedupe workflow for issue #${issueNumber}`
+		);
+		return;
+	}
+
+	await githubRequest(
+		`/repos/${owner}/${repo}/actions/workflows/claude-dedupe-issues.yml/dispatches`,
+		token,
+		'POST',
+		{
+			ref: 'main',
+			inputs: {
+				issue_number: issueNumber.toString()
+			}
+		}
+	);
+}
+
+async function backfillDuplicateComments() {
+	console.log('[DEBUG] Starting backfill duplicate comments script');
+
+	const token = process.env.GITHUB_TOKEN;
+	if (!token) {
+		throw new Error(`GITHUB_TOKEN environment variable is required
+
+Usage:
+  node .github/scripts/backfill-duplicate-comments.mjs
+
+Environment Variables:
+  GITHUB_TOKEN - GitHub personal access token with repo and actions permissions (required)
+  DRY_RUN - Set to "false" to actually trigger workflows (default: true for safety)
+  DAYS_BACK - How many days back to look for old issues (default: 90)`);
+	}
+	console.log('[DEBUG] GitHub token found');
+
+	const owner = process.env.GITHUB_REPOSITORY_OWNER || 'eyaltoledano';
+	const repo = process.env.GITHUB_REPOSITORY_NAME || 'claude-task-master';
+	const dryRun = process.env.DRY_RUN !== 'false';
+	const daysBack = parseInt(process.env.DAYS_BACK || '90', 10);
+
+	console.log(`[DEBUG] Repository: ${owner}/${repo}`);
+	console.log(`[DEBUG] Dry run mode: ${dryRun}`);
+	console.log(`[DEBUG] Looking back ${daysBack} days`);
+
+	const cutoffDate = new Date();
+	cutoffDate.setDate(cutoffDate.getDate() - daysBack);
+
+	console.log(
+		`[DEBUG] Fetching issues created since ${cutoffDate.toISOString()}...`
+	);
+	const allIssues = [];
+	let page = 1;
+	const perPage = 100;
+
+	while (true) {
+		const pageIssues = await githubRequest(
+			`/repos/${owner}/${repo}/issues?state=all&per_page=${perPage}&page=${page}&since=${cutoffDate.toISOString()}`,
+			token
+		);
+
+		if (pageIssues.length === 0) break;
+
+		allIssues.push(...pageIssues);
+		page++;
+
+		// Safety limit to avoid infinite loops
+		if (page > 100) {
+			console.log('[DEBUG] Reached page limit, stopping pagination');
+			break;
+		}
+	}
+
+	console.log(
+		`[DEBUG] Found ${allIssues.length} issues from the last ${daysBack} days`
+	);
+
+	let processedCount = 0;
+	let candidateCount = 0;
+	let triggeredCount = 0;
+
+	for (const issue of allIssues) {
+		processedCount++;
+		console.log(
+			`[DEBUG] Processing issue #${issue.number} (${processedCount}/${allIssues.length}): ${issue.title}`
+		);
+
+		console.log(`[DEBUG] Fetching comments for issue #${issue.number}...`);
+		const comments = await githubRequest(
+			`/repos/${owner}/${repo}/issues/${issue.number}/comments`,
+			token
+		);
+		console.log(
+			`[DEBUG] Issue #${issue.number} has ${comments.length} comments`
+		);
+
+		// Look for existing duplicate detection comments (from the dedupe bot)
+		const dupeDetectionComments = comments.filter(
+			(comment) =>
+				comment.body.includes('Found') &&
+				comment.body.includes('possible duplicate') &&
+				comment.user.type === 'Bot'
+		);
+
+		console.log(
+			`[DEBUG] Issue #${issue.number} has ${dupeDetectionComments.length} duplicate detection comments`
+		);
+
+		// Skip if there's already a duplicate detection comment
+		if (dupeDetectionComments.length > 0) {
+			console.log(
+				`[DEBUG] Issue #${issue.number} already has duplicate detection comment, skipping`
+			);
+			continue;
+		}
+
+		candidateCount++;
+		const issueUrl = `https://github.com/${owner}/${repo}/issues/${issue.number}`;
+
+		try {
+			console.log(
+				`[INFO] ${dryRun ? '[DRY RUN] ' : ''}Triggering dedupe workflow for issue #${issue.number}: ${issueUrl}`
+			);
+			await triggerDedupeWorkflow(owner, repo, issue.number, token, dryRun);
+
+			if (!dryRun) {
+				console.log(
+					`[SUCCESS] Successfully triggered dedupe workflow for issue #${issue.number}`
+				);
+			}
+			triggeredCount++;
+		} catch (error) {
+			console.error(
+				`[ERROR] Failed to trigger workflow for issue #${issue.number}: ${error}`
+			);
+		}
+
+		// Add a delay between workflow triggers to avoid overwhelming the system
+		await new Promise((resolve) => setTimeout(resolve, 1000));
+	}
+
+	console.log(
+		`[DEBUG] Script completed. Processed ${processedCount} issues, found ${candidateCount} candidates without duplicate comments, ${dryRun ? 'would trigger' : 'triggered'} ${triggeredCount} workflows`
+	);
+}
+
+backfillDuplicateComments().catch(console.error);

.github/scripts/check-pre-release-mode.mjs

@@ -0,0 +1,102 @@
+#!/usr/bin/env node
+import { readFileSync, existsSync } from 'node:fs';
+import { join, dirname, resolve } from 'node:path';
+import { fileURLToPath } from 'node:url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+// Get context from command line argument or environment
+const context = process.argv[2] || process.env.GITHUB_WORKFLOW || 'manual';
+
+function findRootDir(startDir) {
+	let currentDir = resolve(startDir);
+	while (currentDir !== '/') {
+		if (existsSync(join(currentDir, 'package.json'))) {
+			try {
+				const pkg = JSON.parse(
+					readFileSync(join(currentDir, 'package.json'), 'utf8')
+				);
+				if (pkg.name === 'task-master-ai' || pkg.repository) {
+					return currentDir;
+				}
+			} catch {}
+		}
+		currentDir = dirname(currentDir);
+	}
+	throw new Error('Could not find root directory');
+}
+
+function checkPreReleaseMode() {
+	console.log('🔍 Checking if branch is in pre-release mode...');
+
+	const rootDir = findRootDir(__dirname);
+	const preJsonPath = join(rootDir, '.changeset', 'pre.json');
+
+	// Check if pre.json exists
+	if (!existsSync(preJsonPath)) {
+		console.log('✅ Not in active pre-release mode - safe to proceed');
+		process.exit(0);
+	}
+
+	try {
+		// Read and parse pre.json
+		const preJsonContent = readFileSync(preJsonPath, 'utf8');
+		const preJson = JSON.parse(preJsonContent);
+
+		// Check if we're in active pre-release mode
+		if (preJson.mode === 'pre') {
+			console.error('❌ ERROR: This branch is in active pre-release mode!');
+			console.error('');
+
+			// Provide context-specific error messages
+			if (context === 'Release Check' || context === 'pull_request') {
+				console.error(
+					'Pre-release mode must be exited before merging to main.'
+				);
+				console.error('');
+				console.error(
+					'To fix this, run the following commands in your branch:'
+				);
+				console.error('  npx changeset pre exit');
+				console.error('  git add -u');
+				console.error('  git commit -m "chore: exit pre-release mode"');
+				console.error('  git push');
+				console.error('');
+				console.error('Then update this pull request.');
+			} else if (context === 'Release' || context === 'main') {
+				console.error(
+					'Pre-release mode should only be used on feature branches, not main.'
+				);
+				console.error('');
+				console.error('To fix this, run the following commands locally:');
+				console.error('  npx changeset pre exit');
+				console.error('  git add -u');
+				console.error('  git commit -m "chore: exit pre-release mode"');
+				console.error('  git push origin main');
+				console.error('');
+				console.error('Then re-run this workflow.');
+			} else {
+				console.error('Pre-release mode must be exited before proceeding.');
+				console.error('');
+				console.error('To fix this, run the following commands:');
+				console.error('  npx changeset pre exit');
+				console.error('  git add -u');
+				console.error('  git commit -m "chore: exit pre-release mode"');
+				console.error('  git push');
+			}
+
+			process.exit(1);
+		}
+
+		console.log('✅ Not in active pre-release mode - safe to proceed');
+		process.exit(0);
+	} catch (error) {
+		console.error(`❌ ERROR: Unable to parse .changeset/pre.json – aborting.`);
+		console.error(`Error details: ${error.message}`);
+		process.exit(1);
+	}
+}
+
+// Run the check
+checkPreReleaseMode();

.github/scripts/release.mjs

@@ -0,0 +1,30 @@
+#!/usr/bin/env node
+import { existsSync, unlinkSync } from 'node:fs';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { findRootDir, runCommand } from './utils.mjs';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const rootDir = findRootDir(__dirname);
+
+console.log('🚀 Starting release process...');
+
+// Double-check we're not in pre-release mode (safety net)
+const preJsonPath = join(rootDir, '.changeset', 'pre.json');
+if (existsSync(preJsonPath)) {
+	console.log('⚠️  Warning: pre.json still exists. Removing it...');
+	unlinkSync(preJsonPath);
+}
+
+// Check if the extension version has changed and tag it
+// This prevents changeset from trying to publish the private package
+runCommand('node', [join(__dirname, 'tag-extension.mjs')]);
+
+// Run changeset publish for npm packages
+runCommand('npx', ['changeset', 'publish']);
+
+console.log('✅ Release process completed!');
+
+// The extension tag (if created) will trigger the extension-release workflow

.github/scripts/tag-extension.mjs

@@ -0,0 +1,33 @@
+#!/usr/bin/env node
+import assert from 'node:assert/strict';
+import { readFileSync } from 'node:fs';
+import { join, dirname } from 'node:path';
+import { fileURLToPath } from 'node:url';
+import { findRootDir, createAndPushTag } from './utils.mjs';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = dirname(__filename);
+
+const rootDir = findRootDir(__dirname);
+
+// Read the extension's package.json
+const extensionDir = join(rootDir, 'apps', 'extension');
+const pkgPath = join(extensionDir, 'package.json');
+
+let pkg;
+try {
+	const pkgContent = readFileSync(pkgPath, 'utf8');
+	pkg = JSON.parse(pkgContent);
+} catch (error) {
+	console.error('Failed to read package.json:', error.message);
+	process.exit(1);
+}
+
+// Ensure we have required fields
+assert(pkg.name, 'package.json must have a name field');
+assert(pkg.version, 'package.json must have a version field');
+
+const tag = `${pkg.name}@${pkg.version}`;
+
+// Create and push the tag if it doesn't exist
+createAndPushTag(tag);

.github/scripts/utils.mjs

@@ -0,0 +1,88 @@
+#!/usr/bin/env node
+import { spawnSync } from 'node:child_process';
+import { readFileSync } from 'node:fs';
+import { join, dirname, resolve } from 'node:path';
+
+// Find the root directory by looking for package.json with task-master-ai
+export function findRootDir(startDir) {
+	let currentDir = resolve(startDir);
+	while (currentDir !== '/') {
+		const pkgPath = join(currentDir, 'package.json');
+		try {
+			const pkg = JSON.parse(readFileSync(pkgPath, 'utf8'));
+			if (pkg.name === 'task-master-ai' || pkg.repository) {
+				return currentDir;
+			}
+		} catch {}
+		currentDir = dirname(currentDir);
+	}
+	throw new Error('Could not find root directory');
+}
+
+// Run a command with proper error handling
+export function runCommand(command, args = [], options = {}) {
+	console.log(`Running: ${command} ${args.join(' ')}`);
+	const result = spawnSync(command, args, {
+		encoding: 'utf8',
+		stdio: 'inherit',
+		...options
+	});
+
+	if (result.status !== 0) {
+		console.error(`Command failed with exit code ${result.status}`);
+		process.exit(result.status);
+	}
+
+	return result;
+}
+
+// Get package version from a package.json file
+export function getPackageVersion(packagePath) {
+	try {
+		const pkg = JSON.parse(readFileSync(packagePath, 'utf8'));
+		return pkg.version;
+	} catch (error) {
+		console.error(
+			`Failed to read package version from ${packagePath}:`,
+			error.message
+		);
+		process.exit(1);
+	}
+}
+
+// Check if a git tag exists on remote
+export function tagExistsOnRemote(tag, remote = 'origin') {
+	const result = spawnSync('git', ['ls-remote', remote, tag], {
+		encoding: 'utf8'
+	});
+
+	return result.status === 0 && result.stdout.trim() !== '';
+}
+
+// Create and push a git tag if it doesn't exist
+export function createAndPushTag(tag, remote = 'origin') {
+	// Check if tag already exists
+	if (tagExistsOnRemote(tag, remote)) {
+		console.log(`Tag ${tag} already exists on remote, skipping`);
+		return false;
+	}
+
+	console.log(`Creating new tag: ${tag}`);
+
+	// Create the tag locally
+	const tagResult = spawnSync('git', ['tag', tag]);
+	if (tagResult.status !== 0) {
+		console.error('Failed to create tag:', tagResult.error || tagResult.stderr);
+		process.exit(1);
+	}
+
+	// Push the tag to remote
+	const pushResult = spawnSync('git', ['push', remote, tag]);
+	if (pushResult.status !== 0) {
+		console.error('Failed to push tag:', pushResult.error || pushResult.stderr);
+		process.exit(1);
+	}
+
+	console.log(`✅ Successfully created and pushed tag: ${tag}`);
+	return true;
+}

.github/workflows/auto-close-duplicates.yml

@@ -0,0 +1,31 @@
+name: Auto-close duplicate issues
+# description: Auto-closes issues that are duplicates of existing issues
+
+on:
+  schedule:
+    - cron: "0 9 * * *"  # Runs daily at 9 AM UTC
+  workflow_dispatch:
+
+jobs:
+  auto-close-duplicates:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write  # Need write permission to close issues and add comments
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Auto-close duplicate issues
+        run: node .github/scripts/auto-close-duplicates.mjs
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
+          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}

.github/workflows/backfill-duplicate-comments.yml

@@ -0,0 +1,46 @@
+name: Backfill Duplicate Comments
+# description: Triggers duplicate detection for old issues that don't have duplicate comments
+
+on:
+  workflow_dispatch:
+    inputs:
+      days_back:
+        description: "How many days back to look for old issues"
+        required: false
+        default: "90"
+        type: string
+      dry_run:
+        description: "Dry run mode (true to only log what would be done)"
+        required: false
+        default: "true"
+        type: choice
+        options:
+          - "true"
+          - "false"
+
+jobs:
+  backfill-duplicate-comments:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    permissions:
+      contents: read
+      issues: read
+      actions: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Backfill duplicate comments
+        run: node .github/scripts/backfill-duplicate-comments.mjs
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          GITHUB_REPOSITORY_OWNER: ${{ github.repository_owner }}
+          GITHUB_REPOSITORY_NAME: ${{ github.event.repository.name }}
+          DAYS_BACK: ${{ inputs.days_back }}
+          DRY_RUN: ${{ inputs.dry_run }}

.github/workflows/claude-dedupe-issues.yml

@@ -0,0 +1,81 @@
+name: Claude Issue Dedupe
+# description: Automatically dedupe GitHub issues using Claude Code
+
+on:
+  issues:
+    types: [opened]
+  workflow_dispatch:
+    inputs:
+      issue_number:
+        description: "Issue number to process for duplicate detection"
+        required: true
+        type: string
+
+jobs:
+  claude-dedupe-issues:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Run Claude Code slash command
+        uses: anthropics/claude-code-base-action@beta
+        with:
+          prompt: "/dedupe ${{ github.repository }}/issues/${{ github.event.issue.number || inputs.issue_number }}"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          claude_env: |
+            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Log duplicate comment event to Statsig
+        if: always()
+        env:
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
+        run: |
+          ISSUE_NUMBER=${{ github.event.issue.number || inputs.issue_number }}
+          REPO=${{ github.repository }}
+
+          if [ -z "$STATSIG_API_KEY" ]; then
+            echo "STATSIG_API_KEY not found, skipping Statsig logging"
+            exit 0
+          fi
+
+          # Prepare the event payload
+          EVENT_PAYLOAD=$(jq -n \
+            --arg issue_number "$ISSUE_NUMBER" \
+            --arg repo "$REPO" \
+            --arg triggered_by "${{ github.event_name }}" \
+            '{
+              events: [{
+                eventName: "github_duplicate_comment_added",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  triggered_by: $triggered_by,
+                  workflow_run_id: "${{ github.run_id }}"
+                },
+                time: (now | floor | tostring)
+              }]
+            }')
+
+          # Send to Statsig API
+          echo "Logging duplicate comment event to Statsig for issue #${ISSUE_NUMBER}"
+
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
+            -H "Content-Type: application/json" \
+            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
+            -d "$EVENT_PAYLOAD")
+
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+
+          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
+            echo "Successfully logged duplicate comment event for issue #${ISSUE_NUMBER}"
+          else
+            echo "Failed to log duplicate comment event for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi

.github/workflows/claude-docs-trigger.yml

@@ -0,0 +1,57 @@
+name: Trigger Claude Documentation Update
+
+on:
+  push:
+    branches:
+      - next
+    paths-ignore:
+      - "apps/docs/**"
+      - "*.md"
+      - ".github/workflows/**"
+
+jobs:
+  trigger-docs-update:
+    # Only run if changes were merged (not direct pushes from bots)
+    if: github.actor != 'github-actions[bot]' && github.actor != 'dependabot[bot]'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      actions: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 2 # Need previous commit for comparison
+
+      - name: Get changed files
+        id: changed-files
+        run: |
+          echo "Changed files in this push:"
+          git diff --name-only HEAD^ HEAD | tee changed_files.txt
+
+          # Store changed files for Claude to analyze (escaped for JSON)
+          CHANGED_FILES=$(git diff --name-only HEAD^ HEAD | jq -Rs .)
+          echo "changed_files=$CHANGED_FILES" >> $GITHUB_OUTPUT
+
+          # Get the commit message (escaped for JSON)
+          COMMIT_MSG=$(git log -1 --pretty=%B | jq -Rs .)
+          echo "commit_message=$COMMIT_MSG" >> $GITHUB_OUTPUT
+
+          # Get diff for documentation context (escaped for JSON)
+          COMMIT_DIFF=$(git diff HEAD^ HEAD --stat | jq -Rs .)
+          echo "commit_diff=$COMMIT_DIFF" >> $GITHUB_OUTPUT
+
+          # Get commit SHA
+          echo "commit_sha=${{ github.sha }}" >> $GITHUB_OUTPUT
+
+      - name: Trigger Claude workflow
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Trigger the Claude docs updater workflow with the change information
+          gh workflow run claude-docs-updater.yml \
+            --ref next \
+            -f commit_sha="${{ steps.changed-files.outputs.commit_sha }}" \
+            -f commit_message=${{ steps.changed-files.outputs.commit_message }} \
+            -f changed_files=${{ steps.changed-files.outputs.changed_files }} \
+            -f commit_diff=${{ steps.changed-files.outputs.commit_diff }}

.github/workflows/claude-docs-updater.yml

@@ -0,0 +1,145 @@
+name: Claude Documentation Updater
+
+on:
+  workflow_dispatch:
+    inputs:
+      commit_sha:
+        description: 'The commit SHA that triggered this update'
+        required: true
+        type: string
+      commit_message:
+        description: 'The commit message'
+        required: true
+        type: string
+      changed_files:
+        description: 'List of changed files'
+        required: true
+        type: string
+      commit_diff:
+        description: 'Diff summary of changes'
+        required: true
+        type: string
+
+jobs:
+  update-docs:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+      issues: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          ref: next
+          fetch-depth: 0 # Need full history to checkout specific commit
+
+      - name: Create docs update branch
+        id: create-branch
+        run: |
+          BRANCH_NAME="docs/auto-update-$(date +%Y%m%d-%H%M%S)"
+          git checkout -b $BRANCH_NAME
+          echo "branch_name=$BRANCH_NAME" >> $GITHUB_OUTPUT
+
+      - name: Run Claude Code to Update Documentation
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          timeout_minutes: "30"
+          mode: "agent"
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          experimental_allowed_domains: |
+            .anthropic.com
+            .github.com
+            api.github.com
+            .githubusercontent.com
+            registry.npmjs.org
+            .task-master.dev
+          base_branch: "next"
+          direct_prompt: |
+            You are a documentation specialist. Analyze the recent changes pushed to the 'next' branch and update the documentation accordingly.
+
+            Recent changes:
+            - Commit: ${{ inputs.commit_message }}
+            - Changed files:
+            ${{ inputs.changed_files }}
+
+            - Changes summary:
+            ${{ inputs.commit_diff }}
+
+            Your task:
+            1. Analyze the changes to understand what functionality was added, modified, or removed
+            2. Check if these changes require documentation updates in apps/docs/
+            3. If documentation updates are needed:
+               - Update relevant documentation files in apps/docs/
+               - Ensure examples are updated if APIs changed
+               - Update any configuration documentation if config options changed
+               - Add new documentation pages if new features were added
+               - Update the changelog or release notes if applicable
+            4. If no documentation updates are needed, skip creating changes
+
+            Guidelines:
+            - Focus only on user-facing changes that need documentation
+            - Keep documentation clear, concise, and helpful
+            - Include code examples where appropriate
+            - Maintain consistent documentation style with existing docs
+            - Don't document internal implementation details unless they affect users
+            - Update navigation/menu files if new pages are added
+
+            Only make changes if the documentation truly needs updating based on the code changes.
+
+      - name: Check if changes were made
+        id: check-changes
+        run: |
+          if git diff --quiet; then
+            echo "has_changes=false" >> $GITHUB_OUTPUT
+          else
+            echo "has_changes=true" >> $GITHUB_OUTPUT
+            git add -A
+            git config --local user.email "github-actions[bot]@users.noreply.github.com"
+            git config --local user.name "github-actions[bot]"
+            git commit -m "docs: auto-update documentation based on changes in next branch
+
+            This PR was automatically generated to update documentation based on recent changes.
+            
+            Original commit: ${{ inputs.commit_message }}
+            
+            Co-authored-by: Claude <claude-assistant@anthropic.com>"
+          fi
+
+      - name: Push changes and create PR
+        if: steps.check-changes.outputs.has_changes == 'true'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          git push origin ${{ steps.create-branch.outputs.branch_name }}
+
+          # Create PR using GitHub CLI
+          gh pr create \
+            --title "docs: update documentation for recent changes" \
+            --body "## 📚 Documentation Update
+
+            This PR automatically updates documentation based on recent changes merged to the \`next\` branch.
+
+            ### Original Changes
+            **Commit:** ${{ inputs.commit_sha }}
+            **Message:** ${{ inputs.commit_message }}
+            
+            ### Changed Files in Original Commit
+            \`\`\`
+            ${{ inputs.changed_files }}
+            \`\`\`
+
+            ### Documentation Updates
+            This PR includes documentation updates to reflect the changes above. Please review to ensure:
+            - [ ] Documentation accurately reflects the changes
+            - [ ] Examples are correct and working
+            - [ ] No important details are missing
+            - [ ] Style is consistent with existing documentation
+
+            ---
+            *This PR was automatically generated by Claude Code GitHub Action*" \
+            --base next \
+            --head ${{ steps.create-branch.outputs.branch_name }} \
+            --label "documentation" \
+            --label "automated"

.github/workflows/claude-issue-triage.yml

@@ -0,0 +1,107 @@
+name: Claude Issue Triage
+# description: Automatically triage GitHub issues using Claude Code
+
+on:
+  issues:
+    types: [opened]
+
+jobs:
+  triage-issue:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+      issues: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Create triage prompt
+        run: |
+          mkdir -p /tmp/claude-prompts
+          cat > /tmp/claude-prompts/triage-prompt.txt << 'EOF'
+          You're an issue triage assistant for GitHub issues. Your task is to analyze the issue and select appropriate labels from the provided list.
+
+          IMPORTANT: Don't post any comments or messages to the issue. Your only action should be to apply labels.
+
+          Issue Information:
+          - REPO: ${{ github.repository }}
+          - ISSUE_NUMBER: ${{ github.event.issue.number }}
+
+          TASK OVERVIEW:
+
+          1. First, fetch the list of labels available in this repository by running: `gh label list`. Run exactly this command with nothing else.
+
+          2. Next, use the GitHub tools to get context about the issue:
+             - You have access to these tools:
+               - mcp__github__get_issue: Use this to retrieve the current issue's details including title, description, and existing labels
+               - mcp__github__get_issue_comments: Use this to read any discussion or additional context provided in the comments
+               - mcp__github__update_issue: Use this to apply labels to the issue (do not use this for commenting)
+               - mcp__github__search_issues: Use this to find similar issues that might provide context for proper categorization and to identify potential duplicate issues
+               - mcp__github__list_issues: Use this to understand patterns in how other issues are labeled
+             - Start by using mcp__github__get_issue to get the issue details
+
+          3. Analyze the issue content, considering:
+             - The issue title and description
+             - The type of issue (bug report, feature request, question, etc.)
+             - Technical areas mentioned
+             - Severity or priority indicators
+             - User impact
+             - Components affected
+
+          4. Select appropriate labels from the available labels list provided above:
+             - Choose labels that accurately reflect the issue's nature
+             - Be specific but comprehensive
+             - Select priority labels if you can determine urgency (high-priority, med-priority, or low-priority)
+             - Consider platform labels (android, ios) if applicable
+             - If you find similar issues using mcp__github__search_issues, consider using a "duplicate" label if appropriate. Only do so if the issue is a duplicate of another OPEN issue.
+
+          5. Apply the selected labels:
+             - Use mcp__github__update_issue to apply your selected labels
+             - DO NOT post any comments explaining your decision
+             - DO NOT communicate directly with users
+             - If no labels are clearly applicable, do not apply any labels
+
+          IMPORTANT GUIDELINES:
+          - Be thorough in your analysis
+          - Only select labels from the provided list above
+          - DO NOT post any comments to the issue
+          - Your ONLY action should be to apply labels using mcp__github__update_issue
+          - It's okay to not add any labels if none are clearly applicable
+          EOF
+
+      - name: Setup GitHub MCP Server
+        run: |
+          mkdir -p /tmp/mcp-config
+          cat > /tmp/mcp-config/mcp-servers.json << 'EOF'
+          {
+            "mcpServers": {
+              "github": {
+                "command": "docker",
+                "args": [
+                  "run",
+                  "-i",
+                  "--rm",
+                  "-e",
+                  "GITHUB_PERSONAL_ACCESS_TOKEN",
+                  "ghcr.io/github/github-mcp-server:sha-7aced2b"
+                ],
+                "env": {
+                  "GITHUB_PERSONAL_ACCESS_TOKEN": "${{ secrets.GITHUB_TOKEN }}"
+                }
+              }
+            }
+          }
+          EOF
+
+      - name: Run Claude Code for Issue Triage
+        uses: anthropics/claude-code-base-action@beta
+        with:
+          prompt_file: /tmp/claude-prompts/triage-prompt.txt
+          allowed_tools: "Bash(gh label list),mcp__github__get_issue,mcp__github__get_issue_comments,mcp__github__update_issue,mcp__github__search_issues,mcp__github__list_issues"
+          timeout_minutes: "5"
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          mcp_config: /tmp/mcp-config/mcp-servers.json
+          claude_env: |
+            GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/claude.yml

@@ -0,0 +1,36 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
+      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
+      (github.event_name == 'issues' && (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: read
+      issues: read
+      id-token: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4
+        with:
+          fetch-depth: 1
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@beta
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}

.github/workflows/extension-ci.yml

@@ -0,0 +1,143 @@
+name: Extension CI
+
+on:
+  push:
+    branches:
+      - main
+      - next
+    paths:
+      - 'apps/extension/**'
+      - '.github/workflows/extension-ci.yml'
+  pull_request:
+    branches:
+      - main
+      - next
+    paths:
+      - 'apps/extension/**'
+      - '.github/workflows/extension-ci.yml'
+
+permissions:
+  contents: read
+
+jobs:
+  setup:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Cache node_modules
+        uses: actions/cache@v4
+        with:
+          path: |
+            node_modules
+            */*/node_modules
+          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-
+
+      - name: Install Extension Dependencies
+        working-directory: apps/extension
+        run: npm ci
+        timeout-minutes: 5
+
+  typecheck:
+    needs: setup
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+
+      - name: Restore node_modules
+        uses: actions/cache@v4
+        with:
+          path: |
+            node_modules
+            */*/node_modules
+          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-
+
+      - name: Install if cache miss
+        working-directory: apps/extension
+        run: npm ci
+        timeout-minutes: 3
+
+      - name: Type Check Extension
+        working-directory: apps/extension
+        run: npm run check-types
+        env:
+          FORCE_COLOR: 1
+
+  build:
+    needs: setup
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+
+      - name: Restore node_modules
+        uses: actions/cache@v4
+        with:
+          path: |
+            node_modules
+            */*/node_modules
+          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-
+
+      - name: Install if cache miss
+        working-directory: apps/extension
+        run: npm ci
+        timeout-minutes: 3
+
+      - name: Build Extension
+        working-directory: apps/extension
+        run: npm run build
+        env:
+          FORCE_COLOR: 1
+
+      - name: Package Extension
+        working-directory: apps/extension
+        run: npm run package
+        env:
+          FORCE_COLOR: 1
+
+      - name: Verify Package Contents
+        working-directory: apps/extension
+        run: |
+          echo "Checking vsix-build contents..."
+          ls -la vsix-build/
+          echo "Checking dist contents..."
+          ls -la vsix-build/dist/
+          echo "Checking package.json exists..."
+          test -f vsix-build/package.json
+
+      - name: Create VSIX Package (Test)
+        working-directory: apps/extension/vsix-build
+        run: npx vsce package --no-dependencies
+        env:
+          FORCE_COLOR: 1
+
+      - name: Upload Extension Artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: extension-package
+          path: |
+            apps/extension/vsix-build/*.vsix
+            apps/extension/dist/
+          retention-days: 30
+

.github/workflows/extension-release.yml

@@ -0,0 +1,111 @@
+name: Extension Release
+
+on:
+  push:
+    tags:
+      - "extension@*"
+
+permissions:
+  contents: write
+
+concurrency: extension-release-${{ github.ref }}
+
+jobs:
+  publish-extension:
+    runs-on: ubuntu-latest
+    environment: extension-release
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Cache node_modules
+        uses: actions/cache@v4
+        with:
+          path: |
+            node_modules
+            */*/node_modules
+          key: ${{ runner.os }}-node-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-node-
+
+      - name: Install Extension Dependencies
+        working-directory: apps/extension
+        run: npm ci
+        timeout-minutes: 5
+
+      - name: Type Check Extension
+        working-directory: apps/extension
+        run: npm run check-types
+        env:
+          FORCE_COLOR: 1
+
+      - name: Build Extension
+        working-directory: apps/extension
+        run: npm run build
+        env:
+          FORCE_COLOR: 1
+
+      - name: Package Extension
+        working-directory: apps/extension
+        run: npm run package
+        env:
+          FORCE_COLOR: 1
+
+      - name: Create VSIX Package
+        working-directory: apps/extension/vsix-build
+        run: npx vsce package --no-dependencies
+        env:
+          FORCE_COLOR: 1
+
+      - name: Get VSIX filename
+        id: vsix-info
+        working-directory: apps/extension/vsix-build
+        run: |
+          VSIX_FILE=$(find . -maxdepth 1 -name "*.vsix" -type f | head -n1 | xargs basename)
+          if [ -z "$VSIX_FILE" ]; then
+            echo "Error: No VSIX file found"
+            exit 1
+          fi
+          echo "vsix-filename=$VSIX_FILE" >> "$GITHUB_OUTPUT"
+          echo "Found VSIX: $VSIX_FILE"
+
+      - name: Publish to VS Code Marketplace
+        working-directory: apps/extension/vsix-build
+        run: npx vsce publish --packagePath "${{ steps.vsix-info.outputs.vsix-filename }}"
+        env:
+          VSCE_PAT: ${{ secrets.VSCE_PAT }}
+          FORCE_COLOR: 1
+
+      - name: Install Open VSX CLI
+        run: npm install -g ovsx
+
+      - name: Publish to Open VSX Registry
+        working-directory: apps/extension/vsix-build
+        run: ovsx publish "${{ steps.vsix-info.outputs.vsix-filename }}"
+        env:
+          OVSX_PAT: ${{ secrets.OVSX_PAT }}
+          FORCE_COLOR: 1
+
+      - name: Upload Build Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: extension-release-${{ github.ref_name }}
+          path: |
+            apps/extension/vsix-build/*.vsix
+            apps/extension/dist/
+          retention-days: 90
+
+  notify-success:
+    needs: publish-extension
+    if: success()
+    runs-on: ubuntu-latest
+    steps:
+      - name: Success Notification
+        run: |
+          echo "🎉 Extension ${{ github.ref_name }} successfully published!"
+          echo "📦 Available on VS Code Marketplace"
+          echo "🌍 Available on Open VSX Registry"
+          echo "🏷️ GitHub release created: ${{ github.ref_name }}"

.github/workflows/log-issue-events.yml

@@ -0,0 +1,176 @@
+name: Log GitHub Issue Events
+
+on:
+  issues:
+    types: [opened, closed]
+
+jobs:
+  log-issue-created:
+    if: github.event.action == 'opened'
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      contents: read
+      issues: read
+
+    steps:
+      - name: Log issue creation to Statsig
+        env:
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
+        run: |
+          ISSUE_NUMBER=${{ github.event.issue.number }}
+          REPO=${{ github.repository }}
+          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
+          AUTHOR="${{ github.event.issue.user.login }}"
+          CREATED_AT="${{ github.event.issue.created_at }}"
+
+          if [ -z "$STATSIG_API_KEY" ]; then
+            echo "STATSIG_API_KEY not found, skipping Statsig logging"
+            exit 0
+          fi
+
+          # Prepare the event payload
+          EVENT_PAYLOAD=$(jq -n \
+            --arg issue_number "$ISSUE_NUMBER" \
+            --arg repo "$REPO" \
+            --arg title "$ISSUE_TITLE" \
+            --arg author "$AUTHOR" \
+            --arg created_at "$CREATED_AT" \
+            '{
+              events: [{
+                eventName: "github_issue_created",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  issue_title: $title,
+                  issue_author: $author,
+                  created_at: $created_at
+                },
+                time: (now | floor | tostring)
+              }]
+            }')
+
+          # Send to Statsig API
+          echo "Logging issue creation to Statsig for issue #${ISSUE_NUMBER}"
+
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
+            -H "Content-Type: application/json" \
+            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
+            -d "$EVENT_PAYLOAD")
+
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+
+          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
+            echo "Successfully logged issue creation for issue #${ISSUE_NUMBER}"
+          else
+            echo "Failed to log issue creation for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi
+
+  log-issue-closed:
+    if: github.event.action == 'closed'
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      contents: read
+      issues: read
+
+    steps:
+      - name: Log issue closure to Statsig
+        env:
+          STATSIG_API_KEY: ${{ secrets.STATSIG_API_KEY }}
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          ISSUE_NUMBER=${{ github.event.issue.number }}
+          REPO=${{ github.repository }}
+          ISSUE_TITLE=$(echo '${{ github.event.issue.title }}' | sed "s/'/'\\\\''/g")
+          CLOSED_BY="${{ github.event.issue.closed_by.login }}"
+          CLOSED_AT="${{ github.event.issue.closed_at }}"
+          STATE_REASON="${{ github.event.issue.state_reason }}"
+
+          if [ -z "$STATSIG_API_KEY" ]; then
+            echo "STATSIG_API_KEY not found, skipping Statsig logging"
+            exit 0
+          fi
+
+          # Get additional issue data via GitHub API
+          echo "Fetching additional issue data for #${ISSUE_NUMBER}"
+          ISSUE_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}")
+
+          COMMENTS_COUNT=$(echo "$ISSUE_DATA" | jq -r '.comments')
+
+          # Get reactions data
+          REACTIONS_DATA=$(curl -s -H "Authorization: token ${GITHUB_TOKEN}" \
+            -H "Accept: application/vnd.github.v3+json" \
+            "https://api.github.com/repos/${REPO}/issues/${ISSUE_NUMBER}/reactions")
+
+          REACTIONS_COUNT=$(echo "$REACTIONS_DATA" | jq '. | length')
+
+          # Check if issue was closed automatically (by checking if closed_by is a bot)
+          CLOSED_AUTOMATICALLY="false"
+          if [[ "$CLOSED_BY" == *"[bot]"* ]]; then
+            CLOSED_AUTOMATICALLY="true"
+          fi
+
+          # Check if closed as duplicate by state_reason
+          CLOSED_AS_DUPLICATE="false"
+          if [ "$STATE_REASON" = "duplicate" ]; then
+            CLOSED_AS_DUPLICATE="true"
+          fi
+
+          # Prepare the event payload
+          EVENT_PAYLOAD=$(jq -n \
+            --arg issue_number "$ISSUE_NUMBER" \
+            --arg repo "$REPO" \
+            --arg title "$ISSUE_TITLE" \
+            --arg closed_by "$CLOSED_BY" \
+            --arg closed_at "$CLOSED_AT" \
+            --arg state_reason "$STATE_REASON" \
+            --arg comments_count "$COMMENTS_COUNT" \
+            --arg reactions_count "$REACTIONS_COUNT" \
+            --arg closed_automatically "$CLOSED_AUTOMATICALLY" \
+            --arg closed_as_duplicate "$CLOSED_AS_DUPLICATE" \
+            '{
+              events: [{
+                eventName: "github_issue_closed",
+                value: 1,
+                metadata: {
+                  repository: $repo,
+                  issue_number: ($issue_number | tonumber),
+                  issue_title: $title,
+                  closed_by: $closed_by,
+                  closed_at: $closed_at,
+                  state_reason: $state_reason,
+                  comments_count: ($comments_count | tonumber),
+                  reactions_count: ($reactions_count | tonumber),
+                  closed_automatically: ($closed_automatically | test("true")),
+                  closed_as_duplicate: ($closed_as_duplicate | test("true"))
+                },
+                time: (now | floor | tostring)
+              }]
+            }')
+
+          # Send to Statsig API
+          echo "Logging issue closure to Statsig for issue #${ISSUE_NUMBER}"
+
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST https://events.statsigapi.net/v1/log_event \
+            -H "Content-Type: application/json" \
+            -H "STATSIG-API-KEY: ${STATSIG_API_KEY}" \
+            -d "$EVENT_PAYLOAD")
+
+          HTTP_CODE=$(echo "$RESPONSE" | tail -n1)
+          BODY=$(echo "$RESPONSE" | head -n-1)
+
+          if [ "$HTTP_CODE" -eq 200 ] || [ "$HTTP_CODE" -eq 202 ]; then
+            echo "Successfully logged issue closure for issue #${ISSUE_NUMBER}"
+            echo "Closed by: $CLOSED_BY"
+            echo "Comments: $COMMENTS_COUNT"
+            echo "Reactions: $REACTIONS_COUNT"
+            echo "Closed automatically: $CLOSED_AUTOMATICALLY"
+            echo "Closed as duplicate: $CLOSED_AS_DUPLICATE"
+          else
+            echo "Failed to log issue closure for issue #${ISSUE_NUMBER}. HTTP ${HTTP_CODE}: ${BODY}"
+          fi

.github/workflows/pre-release.yml

@@ -3,11 +3,13 @@ name: Pre-Release (RC)
 on:
   workflow_dispatch: # Allows manual triggering from GitHub UI/API
 
-concurrency: pre-release-${{ github.ref }}
-
+concurrency: pre-release-${{ github.ref_name }}
 jobs:
   rc:
     runs-on: ubuntu-latest
+    # Only allow pre-releases on non-main branches
+    if: github.ref != 'refs/heads/main'
+    environment: extension-release
     steps:
       - uses: actions/checkout@v4
         with:
@@ -16,7 +18,7 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 20
-          cache: 'npm'
+          cache: "npm"
 
       - name: Cache node_modules
         uses: actions/cache@v4
@@ -32,10 +34,30 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Enter RC mode
+      - name: Enter RC mode (if not already in RC mode)
         run: |
-          npx changeset pre exit || true
-          npx changeset pre enter rc
+          # Check if we're in pre-release mode with the "rc" tag
+          if [ -f .changeset/pre.json ]; then
+            MODE=$(jq -r '.mode' .changeset/pre.json 2>/dev/null || echo '')
+            TAG=$(jq -r '.tag' .changeset/pre.json 2>/dev/null || echo '')
+            
+            if [ "$MODE" = "exit" ]; then
+              echo "Pre-release mode is in 'exit' state, re-entering RC mode..."
+              npx changeset pre enter rc
+            elif [ "$MODE" = "pre" ] && [ "$TAG" != "rc" ]; then
+              echo "In pre-release mode but with wrong tag ($TAG), switching to RC..."
+              npx changeset pre exit
+              npx changeset pre enter rc
+            elif [ "$MODE" = "pre" ] && [ "$TAG" = "rc" ]; then
+              echo "Already in RC pre-release mode"
+            else
+              echo "Unknown mode state: $MODE, entering RC mode..."
+              npx changeset pre enter rc
+            fi
+          else
+            echo "No pre.json found, entering RC mode..."
+            npx changeset pre enter rc
+          fi
 
       - name: Version RC packages
         run: npx changeset version
@@ -46,17 +68,14 @@ jobs:
       - name: Create Release Candidate Pull Request or Publish Release Candidate to npm
         uses: changesets/action@v1
         with:
-          publish: npm run release
+          publish: npx changeset publish
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}
 
-      - name: Exit RC mode
-        run: npx changeset pre exit
-
       - name: Commit & Push changes
         uses: actions-js/push@master
         with:
           github_token: ${{ secrets.GITHUB_TOKEN }}
           branch: ${{ github.ref }}
-          message: 'chore: rc version bump'
+          message: "chore: rc version bump"

.github/workflows/release-check.yml

@@ -0,0 +1,21 @@
+name: Release Check
+
+on:
+  pull_request:
+    branches:
+      - main
+
+concurrency:
+  group: release-check-${{ github.head_ref }}
+  cancel-in-progress: true
+
+jobs:
+  check-release-mode:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check release mode
+        run: node ./.github/scripts/check-pre-release-mode.mjs "pull_request"

.github/workflows/release.yml

@@ -6,6 +6,11 @@ on:
 
 concurrency: ${{ github.workflow }}-${{ github.ref }}
 
+permissions:
+  contents: write
+  pull-requests: write
+  id-token: write
+
 jobs:
   release:
     runs-on: ubuntu-latest
@@ -33,13 +38,13 @@ jobs:
         run: npm ci
         timeout-minutes: 2
 
-      - name: Exit pre-release mode (safety check)
-        run: npx changeset pre exit || true
+      - name: Check pre-release mode
+        run: node ./.github/scripts/check-pre-release-mode.mjs "main"
 
       - name: Create Release Pull Request or Publish to npm
         uses: changesets/action@v1
         with:
-          publish: npm run release
+          publish: node ./.github/scripts/release.mjs
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           NPM_TOKEN: ${{ secrets.NPM_TOKEN }}

.github/workflows/weekly-metrics-discord.yml

@@ -0,0 +1,96 @@
+name: Weekly Metrics to Discord
+# description: Sends weekly metrics summary to Discord channel
+
+on:
+  schedule:
+    - cron: "0 9 * * 1" # Every Monday at 9 AM
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  issues: write
+  pull-requests: read
+
+jobs:
+  weekly-metrics:
+    runs-on: ubuntu-latest
+    env:
+      DISCORD_WEBHOOK: ${{ secrets.DISCORD_METRICS_WEBHOOK }}
+    steps:
+      - name: Get dates for last week
+        run: |
+          # Last 7 days
+          first_day=$(date -d "7 days ago" +%Y-%m-%d)
+          last_day=$(date +%Y-%m-%d)
+
+          echo "first_day=$first_day" >> $GITHUB_ENV
+          echo "last_day=$last_day" >> $GITHUB_ENV
+          echo "week_of=$(date -d '7 days ago' +'Week of %B %d, %Y')" >> $GITHUB_ENV
+
+      - name: Generate issue metrics
+        uses: github/issue-metrics@v3
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          SEARCH_QUERY: "repo:${{ github.repository }} is:issue created:${{ env.first_day }}..${{ env.last_day }}"
+          HIDE_TIME_TO_ANSWER: true
+          HIDE_LABEL_METRICS: false
+
+      - name: Generate PR metrics
+        uses: github/issue-metrics@v3
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          SEARCH_QUERY: "repo:${{ github.repository }} is:pr created:${{ env.first_day }}..${{ env.last_day }}"
+          OUTPUT_FILE: pr_metrics.md
+
+      - name: Parse metrics
+        id: metrics
+        run: |
+          # Parse the metrics from the generated markdown files
+          if [ -f "issue_metrics.md" ]; then
+            # Extract key metrics using grep/awk
+            AVG_TIME_TO_FIRST_RESPONSE=$(grep -A 1 "Average time to first response" issue_metrics.md | tail -1 | xargs || echo "N/A")
+            AVG_TIME_TO_CLOSE=$(grep -A 1 "Average time to close" issue_metrics.md | tail -1 | xargs || echo "N/A")
+            NUM_ISSUES_CREATED=$(grep -oP '\d+(?= issues created)' issue_metrics.md || echo "0")
+            NUM_ISSUES_CLOSED=$(grep -oP '\d+(?= issues closed)' issue_metrics.md || echo "0")
+          fi
+
+          if [ -f "pr_metrics.md" ]; then
+            PR_AVG_TIME_TO_MERGE=$(grep -A 1 "Average time to close" pr_metrics.md | tail -1 | xargs || echo "N/A")
+            NUM_PRS_CREATED=$(grep -oP '\d+(?= pull requests created)' pr_metrics.md || echo "0")
+            NUM_PRS_MERGED=$(grep -oP '\d+(?= pull requests closed)' pr_metrics.md || echo "0")
+          fi
+
+          # Set outputs for Discord action
+          echo "issues_created=${NUM_ISSUES_CREATED:-0}" >> $GITHUB_OUTPUT
+          echo "issues_closed=${NUM_ISSUES_CLOSED:-0}" >> $GITHUB_OUTPUT
+          echo "prs_created=${NUM_PRS_CREATED:-0}" >> $GITHUB_OUTPUT
+          echo "prs_merged=${NUM_PRS_MERGED:-0}" >> $GITHUB_OUTPUT
+          echo "avg_first_response=${AVG_TIME_TO_FIRST_RESPONSE:-N/A}" >> $GITHUB_OUTPUT
+          echo "avg_time_to_close=${AVG_TIME_TO_CLOSE:-N/A}" >> $GITHUB_OUTPUT
+          echo "pr_avg_merge_time=${PR_AVG_TIME_TO_MERGE:-N/A}" >> $GITHUB_OUTPUT
+
+      - name: Send to Discord
+        uses: sarisia/actions-status-discord@v1
+        if: env.DISCORD_WEBHOOK != ''
+        with:
+          webhook: ${{ env.DISCORD_WEBHOOK }}
+          status: Success
+          title: "📊 Weekly Metrics Report"
+          description: |
+            **${{ env.week_of }}**
+            
+            **🎯 Issues**
+            • Created: ${{ steps.metrics.outputs.issues_created }}
+            • Closed: ${{ steps.metrics.outputs.issues_closed }}
+            
+            **🔀 Pull Requests**
+            • Created: ${{ steps.metrics.outputs.prs_created }}
+            • Merged: ${{ steps.metrics.outputs.prs_merged }}
+            
+            **⏱️ Response Times**
+            • First Response: ${{ steps.metrics.outputs.avg_first_response }}
+            • Time to Close: ${{ steps.metrics.outputs.avg_time_to_close }}
+            • PR Merge Time: ${{ steps.metrics.outputs.pr_avg_merge_time }}
+          color: 0x58AFFF
+          username: Task Master Metrics Bot
+          avatar_url: https://raw.githubusercontent.com/eyaltoledano/claude-task-master/main/images/logo.png

.gitignore

@@ -87,3 +87,10 @@ dev-debug.log
 *.njsproj
 *.sln
 *.sw?
+
+# VS Code extension test files
+.vscode-test/
+apps/extension/.vscode-test/
+
+# apps/extension
+apps/extension/vsix-build/

.kiro/hooks/tm-code-change-task-tracker.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Code Change Task Tracker",
+  "description": "Track implementation progress by monitoring code changes",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*.{js,ts,jsx,tsx,py,go,rs,java,cpp,c,h,hpp,cs,rb,php,swift,kt,scala,clj}",
+      "!**/node_modules/**",
+      "!**/vendor/**",
+      "!**/.git/**",
+      "!**/build/**",
+      "!**/dist/**",
+      "!**/target/**",
+      "!**/__pycache__/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I just saved a source code file. Please:\n\n1. Check what task is currently 'in-progress' using 'tm list --status=in-progress'\n2. Look at the file I saved and summarize what was changed (considering the programming language and context)\n3. Update the task's notes with: 'tm update-subtask --id=<task_id> --prompt=\"Implemented: <summary_of_changes> in <file_path>\"'\n4. If the changes seem to complete the task based on its description, ask if I want to mark it as done"
+  }
+}

.kiro/hooks/tm-complexity-analyzer.kiro.hook

@@ -0,0 +1,16 @@
+{
+  "enabled": false,
+  "name": "[TM] Complexity Analyzer",
+  "description": "Analyze task complexity when new tasks are added",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "New tasks were added to tasks.json. For each new task:\n\n1. Run 'tm analyze-complexity --id=<task_id>'\n2. If complexity score is > 7, automatically expand it: 'tm expand --id=<task_id> --num=5'\n3. Show the complexity analysis results\n4. Suggest task dependencies based on the expanded subtasks"
+  }
+}

.kiro/hooks/tm-daily-standup-assistant.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Daily Standup Assistant",
+  "description": "Morning workflow summary and task selection",
+  "version": "1",
+  "when": {
+    "type": "userTriggered"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Good morning! Please provide my daily standup summary:\n\n1. Run 'tm list --status=done' and show tasks completed in the last 24 hours\n2. Run 'tm list --status=in-progress' to show current work\n3. Run 'tm next' to suggest the highest priority task to start\n4. Show the dependency graph for upcoming work\n5. Ask which task I'd like to focus on today"
+  }
+}

.kiro/hooks/tm-git-commit-task-linker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] Git Commit Task Linker",
+  "description": "Link commits to tasks for traceability",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to commit code. Please:\n\n1. Run 'git diff --staged' to see what's being committed\n2. Analyze the changes and suggest which tasks they relate to\n3. Generate a commit message in format: 'feat(task-<id>): <description>'\n4. Update the relevant tasks with a note about this commit\n5. Show the proposed commit message for approval"
+  }
+}

.kiro/hooks/tm-pr-readiness-checker.kiro.hook

@@ -0,0 +1,13 @@
+{
+  "enabled": true,
+  "name": "[TM] PR Readiness Checker",
+  "description": "Validate tasks before creating a pull request",
+  "version": "1",
+  "when": {
+    "type": "manual"
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "I'm about to create a PR. Please:\n\n1. List all tasks marked as 'done' in this branch\n2. For each done task, verify:\n   - All subtasks are also done\n   - Test files exist for new functionality\n   - No TODO comments remain related to the task\n3. Generate a PR description listing completed tasks\n4. Suggest a PR title based on the main tasks completed"
+  }
+}

.kiro/hooks/tm-task-dependency-auto-progression.kiro.hook

@@ -0,0 +1,17 @@
+{
+  "enabled": true,
+  "name": "[TM] Task Dependency Auto-Progression",
+  "description": "Automatically progress tasks when dependencies are completed",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      ".taskmaster/tasks/tasks.json",
+      ".taskmaster/tasks/*.json"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "Check the tasks.json file for any tasks that just changed status to 'done'. For each completed task:\n\n1. Find all tasks that depend on it\n2. Check if those dependent tasks now have all their dependencies satisfied\n3. If a task has all dependencies met and is still 'pending', use the command 'tm set-status --id=<task_id> --status=in-progress' to start it\n4. Show me which tasks were auto-started and why"
+  }
+}

.kiro/hooks/tm-test-success-task-completer.kiro.hook

@@ -0,0 +1,23 @@
+{
+  "enabled": true,
+  "name": "[TM] Test Success Task Completer",
+  "description": "Mark tasks as done when their tests pass",
+  "version": "1",
+  "when": {
+    "type": "fileEdited",
+    "patterns": [
+      "**/*test*.{js,ts,jsx,tsx,py,go,java,rb,php,rs,cpp,cs}",
+      "**/*spec*.{js,ts,jsx,tsx,rb}",
+      "**/test_*.py",
+      "**/*_test.go",
+      "**/*Test.java",
+      "**/*Tests.cs",
+      "!**/node_modules/**",
+      "!**/vendor/**"
+    ]
+  },
+  "then": {
+    "type": "askAgent",
+    "prompt": "A test file was just saved. Please:\n\n1. Identify the test framework/language and run the appropriate test command for this file (npm test, pytest, go test, cargo test, dotnet test, mvn test, etc.)\n2. If all tests pass, check which tasks mention this functionality\n3. For any matching tasks that are 'in-progress', ask if the passing tests mean the task is complete\n4. If confirmed, mark the task as done with 'tm set-status --id=<task_id> --status=done'"
+  }
+}

.kiro/settings/mcp.json

@@ -0,0 +1,19 @@
+{
+	"mcpServers": {
+		"task-master-ai": {
+			"command": "npx",
+			"args": ["-y", "--package=task-master-ai", "task-master-ai"],
+			"env": {
+				"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+				"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+				"OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+				"GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+				"XAI_API_KEY": "YOUR_XAI_KEY_HERE",
+				"OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+				"MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+				"AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
+				"OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
+			}
+		}
+	}
+}

.kiro/steering/dev_workflow.md

@@ -0,0 +1,422 @@
+---
+inclusion: always
+---
+
+# Taskmaster Development Workflow
+
+This guide outlines the standard process for using Taskmaster to manage software development projects. It is written as a set of instructions for you, the AI agent.
+
+- **Your Default Stance**: For most projects, the user can work directly within the `master` task context. Your initial actions should operate on this default context unless a clear pattern for multi-context work emerges.
+- **Your Goal**: Your role is to elevate the user's workflow by intelligently introducing advanced features like **Tagged Task Lists** when you detect the appropriate context. Do not force tags on the user; suggest them as a helpful solution to a specific need.
+
+## The Basic Loop
+The fundamental development cycle you will facilitate is:
+1.  **`list`**: Show the user what needs to be done.
+2.  **`next`**: Help the user decide what to work on.
+3.  **`show <id>`**: Provide details for a specific task.
+4.  **`expand <id>`**: Break down a complex task into smaller, manageable subtasks.
+5.  **Implement**: The user writes the code and tests.
+6.  **`update-subtask`**: Log progress and findings on behalf of the user.
+7.  **`set-status`**: Mark tasks and subtasks as `done` as work is completed.
+8.  **Repeat**.
+
+All your standard command executions should operate on the user's current task context, which defaults to `master`.
+
+---
+
+## Standard Development Workflow Process
+
+### Simple Workflow (Default Starting Point)
+
+For new projects or when users are getting started, operate within the `master` tag context:
+
+-   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see @`taskmaster.md`) to generate initial tasks.json with tagged structure
+-   Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules kiro,windsurf`) or manage them later with `task-master rules add/remove` commands  
+-   Begin coding sessions with `get_tasks` / `task-master list` (see @`taskmaster.md`) to see current tasks, status, and IDs
+-   Determine the next task to work on using `next_task` / `task-master next` (see @`taskmaster.md`)
+-   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.md`) before breaking down tasks
+-   Review complexity report using `complexity_report` / `task-master complexity-report` (see @`taskmaster.md`)
+-   Select tasks based on dependencies (all marked 'done'), priority level, and ID order
+-   View specific task details using `get_task` / `task-master show <id>` (see @`taskmaster.md`) to understand implementation requirements
+-   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see @`taskmaster.md`) with appropriate flags like `--force` (to replace existing subtasks) and `--research`
+-   Implement code following task details, dependencies, and project standards
+-   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see @`taskmaster.md`)
+-   Update dependent tasks when implementation differs from original plan using `update` / `task-master update --from=<id> --prompt="..."` or `update_task` / `task-master update-task --id=<id> --prompt="..."` (see @`taskmaster.md`)
+
+---
+
+## Leveling Up: Agent-Led Multi-Context Workflows
+
+While the basic workflow is powerful, your primary opportunity to add value is by identifying when to introduce **Tagged Task Lists**. These patterns are your tools for creating a more organized and efficient development environment for the user, especially if you detect agentic or parallel development happening across the same session.
+
+**Critical Principle**: Most users should never see a difference in their experience. Only introduce advanced workflows when you detect clear indicators that the project has evolved beyond simple task management.
+
+### When to Introduce Tags: Your Decision Patterns
+
+Here are the patterns to look for. When you detect one, you should propose the corresponding workflow to the user.
+
+#### Pattern 1: Simple Git Feature Branching
+This is the most common and direct use case for tags.
+
+- **Trigger**: The user creates a new git branch (e.g., `git checkout -b feature/user-auth`).
+- **Your Action**: Propose creating a new tag that mirrors the branch name to isolate the feature's tasks from `master`.
+- **Your Suggested Prompt**: *"I see you've created a new branch named 'feature/user-auth'. To keep all related tasks neatly organized and separate from your main list, I can create a corresponding task tag for you. This helps prevent merge conflicts in your `tasks.json` file later. Shall I create the 'feature-user-auth' tag?"*
+- **Tool to Use**: `task-master add-tag --from-branch`
+
+#### Pattern 2: Team Collaboration
+- **Trigger**: The user mentions working with teammates (e.g., "My teammate Alice is handling the database schema," or "I need to review Bob's work on the API.").
+- **Your Action**: Suggest creating a separate tag for the user's work to prevent conflicts with shared master context.
+- **Your Suggested Prompt**: *"Since you're working with Alice, I can create a separate task context for your work to avoid conflicts. This way, Alice can continue working with the master list while you have your own isolated context. When you're ready to merge your work, we can coordinate the tasks back to master. Shall I create a tag for your current work?"*
+- **Tool to Use**: `task-master add-tag my-work --copy-from-current --description="My tasks while collaborating with Alice"`
+
+#### Pattern 3: Experiments or Risky Refactors
+- **Trigger**: The user wants to try something that might not be kept (e.g., "I want to experiment with switching our state management library," or "Let's refactor the old API module, but I want to keep the current tasks as a reference.").
+- **Your Action**: Propose creating a sandboxed tag for the experimental work.
+- **Your Suggested Prompt**: *"This sounds like a great experiment. To keep these new tasks separate from our main plan, I can create a temporary 'experiment-zustand' tag for this work. If we decide not to proceed, we can simply delete the tag without affecting the main task list. Sound good?"*
+- **Tool to Use**: `task-master add-tag experiment-zustand --description="Exploring Zustand migration"`
+
+#### Pattern 4: Large Feature Initiatives (PRD-Driven)
+This is a more structured approach for significant new features or epics.
+
+- **Trigger**: The user describes a large, multi-step feature that would benefit from a formal plan.
+- **Your Action**: Propose a comprehensive, PRD-driven workflow.
+- **Your Suggested Prompt**: *"This sounds like a significant new feature. To manage this effectively, I suggest we create a dedicated task context for it. Here's the plan: I'll create a new tag called 'feature-xyz', then we can draft a Product Requirements Document (PRD) together to scope the work. Once the PRD is ready, I'll automatically generate all the necessary tasks within that new tag. How does that sound?"*
+- **Your Implementation Flow**:
+    1.  **Create an empty tag**: `task-master add-tag feature-xyz --description "Tasks for the new XYZ feature"`. You can also start by creating a git branch if applicable, and then create the tag from that branch.
+    2.  **Collaborate & Create PRD**: Work with the user to create a detailed PRD file (e.g., `.taskmaster/docs/feature-xyz-prd.txt`).
+    3.  **Parse PRD into the new tag**: `task-master parse-prd .taskmaster/docs/feature-xyz-prd.txt --tag feature-xyz`
+    4.  **Prepare the new task list**: Follow up by suggesting `analyze-complexity` and `expand-all` for the newly created tasks within the `feature-xyz` tag.
+
+#### Pattern 5: Version-Based Development
+Tailor your approach based on the project maturity indicated by tag names.
+
+- **Prototype/MVP Tags** (`prototype`, `mvp`, `poc`, `v0.x`):
+  - **Your Approach**: Focus on speed and functionality over perfection
+  - **Task Generation**: Create tasks that emphasize "get it working" over "get it perfect"
+  - **Complexity Level**: Lower complexity, fewer subtasks, more direct implementation paths
+  - **Research Prompts**: Include context like "This is a prototype - prioritize speed and basic functionality over optimization"
+  - **Example Prompt Addition**: *"Since this is for the MVP, I'll focus on tasks that get core functionality working quickly rather than over-engineering."*
+
+- **Production/Mature Tags** (`v1.0+`, `production`, `stable`):
+  - **Your Approach**: Emphasize robustness, testing, and maintainability
+  - **Task Generation**: Include comprehensive error handling, testing, documentation, and optimization
+  - **Complexity Level**: Higher complexity, more detailed subtasks, thorough implementation paths
+  - **Research Prompts**: Include context like "This is for production - prioritize reliability, performance, and maintainability"
+  - **Example Prompt Addition**: *"Since this is for production, I'll ensure tasks include proper error handling, testing, and documentation."*
+
+### Advanced Workflow (Tag-Based & PRD-Driven)
+
+**When to Transition**: Recognize when the project has evolved (or has initiated a project which existing code) beyond simple task management. Look for these indicators:
+- User mentions teammates or collaboration needs
+- Project has grown to 15+ tasks with mixed priorities
+- User creates feature branches or mentions major initiatives
+- User initializes Taskmaster on an existing, complex codebase
+- User describes large features that would benefit from dedicated planning
+
+**Your Role in Transition**: Guide the user to a more sophisticated workflow that leverages tags for organization and PRDs for comprehensive planning.
+
+#### Master List Strategy (High-Value Focus)
+Once you transition to tag-based workflows, the `master` tag should ideally contain only:
+- **High-level deliverables** that provide significant business value
+- **Major milestones** and epic-level features
+- **Critical infrastructure** work that affects the entire project
+- **Release-blocking** items
+
+**What NOT to put in master**:
+- Detailed implementation subtasks (these go in feature-specific tags' parent tasks)
+- Refactoring work (create dedicated tags like `refactor-auth`)
+- Experimental features (use `experiment-*` tags)
+- Team member-specific tasks (use person-specific tags)
+
+#### PRD-Driven Feature Development
+
+**For New Major Features**:
+1. **Identify the Initiative**: When user describes a significant feature
+2. **Create Dedicated Tag**: `add_tag feature-[name] --description="[Feature description]"`
+3. **Collaborative PRD Creation**: Work with user to create comprehensive PRD in `.taskmaster/docs/feature-[name]-prd.txt`
+4. **Parse & Prepare**: 
+   - `parse_prd .taskmaster/docs/feature-[name]-prd.txt --tag=feature-[name]`
+   - `analyze_project_complexity --tag=feature-[name] --research`
+   - `expand_all --tag=feature-[name] --research`
+5. **Add Master Reference**: Create a high-level task in `master` that references the feature tag
+
+**For Existing Codebase Analysis**:
+When users initialize Taskmaster on existing projects:
+1. **Codebase Discovery**: Use your native tools for producing deep context about the code base. You may use `research` tool with `--tree` and `--files` to collect up to date information using the existing architecture as context.
+2. **Collaborative Assessment**: Work with user to identify improvement areas, technical debt, or new features
+3. **Strategic PRD Creation**: Co-author PRDs that include:
+   - Current state analysis (based on your codebase research)
+   - Proposed improvements or new features
+   - Implementation strategy considering existing code
+4. **Tag-Based Organization**: Parse PRDs into appropriate tags (`refactor-api`, `feature-dashboard`, `tech-debt`, etc.)
+5. **Master List Curation**: Keep only the most valuable initiatives in master
+
+The parse-prd's `--append` flag enables the user to parse multiple PRDs within tags or across tags. PRDs should be focused and the number of tasks they are parsed into should be strategically chosen relative to the PRD's complexity and level of detail.
+
+### Workflow Transition Examples
+
+**Example 1: Simple → Team-Based**
+```
+User: "Alice is going to help with the API work"
+Your Response: "Great! To avoid conflicts, I'll create a separate task context for your work. Alice can continue with the master list while you work in your own context. When you're ready to merge, we can coordinate the tasks back together."
+Action: add_tag my-api-work --copy-from-current --description="My API tasks while collaborating with Alice"
+```
+
+**Example 2: Simple → PRD-Driven**
+```
+User: "I want to add a complete user dashboard with analytics, user management, and reporting"
+Your Response: "This sounds like a major feature that would benefit from detailed planning. Let me create a dedicated context for this work and we can draft a PRD together to ensure we capture all requirements."
+Actions: 
+1. add_tag feature-dashboard --description="User dashboard with analytics and management"
+2. Collaborate on PRD creation
+3. parse_prd dashboard-prd.txt --tag=feature-dashboard
+4. Add high-level "User Dashboard" task to master
+```
+
+**Example 3: Existing Project → Strategic Planning**
+```
+User: "I just initialized Taskmaster on my existing React app. It's getting messy and I want to improve it."
+Your Response: "Let me research your codebase to understand the current architecture, then we can create a strategic plan for improvements."
+Actions:
+1. research "Current React app architecture and improvement opportunities" --tree --files=src/
+2. Collaborate on improvement PRD based on findings
+3. Create tags for different improvement areas (refactor-components, improve-state-management, etc.)
+4. Keep only major improvement initiatives in master
+```
+
+---
+
+## Primary Interaction: MCP Server vs. CLI
+
+Taskmaster offers two primary ways to interact:
+
+1.  **MCP Server (Recommended for Integrated Tools)**:
+    - For AI agents and integrated development environments (like Kiro), interacting via the **MCP server is the preferred method**.
+    - The MCP server exposes Taskmaster functionality through a set of tools (e.g., `get_tasks`, `add_subtask`).
+    - This method offers better performance, structured data exchange, and richer error handling compared to CLI parsing.
+    - Refer to @`mcp.md` for details on the MCP architecture and available tools.
+    - A comprehensive list and description of MCP tools and their corresponding CLI commands can be found in @`taskmaster.md`.
+    - **Restart the MCP server** if core logic in `scripts/modules` or MCP tool/direct function definitions change.
+    - **Note**: MCP tools fully support tagged task lists with complete tag management capabilities.
+
+2.  **`task-master` CLI (For Users & Fallback)**:
+    - The global `task-master` command provides a user-friendly interface for direct terminal interaction.
+    - It can also serve as a fallback if the MCP server is inaccessible or a specific function isn't exposed via MCP.
+    - Install globally with `npm install -g task-master-ai` or use locally via `npx task-master-ai ...`.
+    - The CLI commands often mirror the MCP tools (e.g., `task-master list` corresponds to `get_tasks`).
+    - Refer to @`taskmaster.md` for a detailed command reference.
+    - **Tagged Task Lists**: CLI fully supports the new tagged system with seamless migration.
+
+## How the Tag System Works (For Your Reference)
+
+- **Data Structure**: Tasks are organized into separate contexts (tags) like "master", "feature-branch", or "v2.0".
+- **Silent Migration**: Existing projects automatically migrate to use a "master" tag with zero disruption.
+- **Context Isolation**: Tasks in different tags are completely separate. Changes in one tag do not affect any other tag.
+- **Manual Control**: The user is always in control. There is no automatic switching. You facilitate switching by using `use-tag <name>`.
+- **Full CLI & MCP Support**: All tag management commands are available through both the CLI and MCP tools for you to use. Refer to @`taskmaster.md` for a full command list.
+
+---
+
+## Task Complexity Analysis
+
+-   Run `analyze_project_complexity` / `task-master analyze-complexity --research` (see @`taskmaster.md`) for comprehensive analysis
+-   Review complexity report via `complexity_report` / `task-master complexity-report` (see @`taskmaster.md`) for a formatted, readable version.
+-   Focus on tasks with highest complexity scores (8-10) for detailed breakdown
+-   Use analysis results to determine appropriate subtask allocation
+-   Note that reports are automatically used by the `expand_task` tool/command
+
+## Task Breakdown Process
+
+-   Use `expand_task` / `task-master expand --id=<id>`. It automatically uses the complexity report if found, otherwise generates default number of subtasks.
+-   Use `--num=<number>` to specify an explicit number of subtasks, overriding defaults or complexity report recommendations.
+-   Add `--research` flag to leverage Perplexity AI for research-backed expansion.
+-   Add `--force` flag to clear existing subtasks before generating new ones (default is to append).
+-   Use `--prompt="<context>"` to provide additional context when needed.
+-   Review and adjust generated subtasks as necessary.
+-   Use `expand_all` tool or `task-master expand --all` to expand multiple pending tasks at once, respecting flags like `--force` and `--research`.
+-   If subtasks need complete replacement (regardless of the `--force` flag on `expand`), clear them first with `clear_subtasks` / `task-master clear-subtasks --id=<id>`.
+
+## Implementation Drift Handling
+
+-   When implementation differs significantly from planned approach
+-   When future tasks need modification due to current implementation choices
+-   When new dependencies or requirements emerge
+-   Use `update` / `task-master update --from=<futureTaskId> --prompt='<explanation>\nUpdate context...' --research` to update multiple future tasks.
+-   Use `update_task` / `task-master update-task --id=<taskId> --prompt='<explanation>\nUpdate context...' --research` to update a single specific task.
+
+## Task Status Management
+
+-   Use 'pending' for tasks ready to be worked on
+-   Use 'done' for completed and verified tasks
+-   Use 'deferred' for postponed tasks
+-   Add custom status values as needed for project-specific workflows
+
+## Task Structure Fields
+
+- **id**: Unique identifier for the task (Example: `1`, `1.1`)
+- **title**: Brief, descriptive title (Example: `"Initialize Repo"`)
+- **description**: Concise summary of what the task involves (Example: `"Create a new repository, set up initial structure."`)
+- **status**: Current state of the task (Example: `"pending"`, `"done"`, `"deferred"`)
+- **dependencies**: IDs of prerequisite tasks (Example: `[1, 2.1]`)
+    - Dependencies are displayed with status indicators (✅ for completed, ⏱️ for pending)
+    - This helps quickly identify which prerequisite tasks are blocking work
+- **priority**: Importance level (Example: `"high"`, `"medium"`, `"low"`)
+- **details**: In-depth implementation instructions (Example: `"Use GitHub client ID/secret, handle callback, set session token."`) 
+- **testStrategy**: Verification approach (Example: `"Deploy and call endpoint to confirm 'Hello World' response."`) 
+- **subtasks**: List of smaller, more specific tasks (Example: `[{"id": 1, "title": "Configure OAuth", ...}]`) 
+- Refer to task structure details (previously linked to `tasks.md`).
+
+## Configuration Management (Updated)
+
+Taskmaster configuration is managed through two main mechanisms:
+
+1.  **`.taskmaster/config.json` File (Primary):**
+    *   Located in the project root directory.
+    *   Stores most configuration settings: AI model selections (main, research, fallback), parameters (max tokens, temperature), logging level, default subtasks/priority, project name, etc.
+    *   **Tagged System Settings**: Includes `global.defaultTag` (defaults to "master") and `tags` section for tag management configuration.
+    *   **Managed via `task-master models --setup` command.** Do not edit manually unless you know what you are doing.
+    *   **View/Set specific models via `task-master models` command or `models` MCP tool.**
+    *   Created automatically when you run `task-master models --setup` for the first time or during tagged system migration.
+
+2.  **Environment Variables (`.env` / `mcp.json`):**
+    *   Used **only** for sensitive API keys and specific endpoint URLs.
+    *   Place API keys (one per provider) in a `.env` file in the project root for CLI usage.
+    *   For MCP/Kiro integration, configure these keys in the `env` section of `.kiro/mcp.json`.
+    *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.md`).
+
+3.  **`.taskmaster/state.json` File (Tagged System State):**
+    *   Tracks current tag context and migration status.
+    *   Automatically created during tagged system migration.
+    *   Contains: `currentTag`, `lastSwitched`, `migrationNoticeShown`.
+
+**Important:** Non-API key settings (like model selections, `MAX_TOKENS`, `TASKMASTER_LOG_LEVEL`) are **no longer configured via environment variables**. Use the `task-master models` command (or `--setup` for interactive configuration) or the `models` MCP tool.
+**If AI commands FAIL in MCP** verify that the API key for the selected provider is present in the `env` section of `.kiro/mcp.json`.
+**If AI commands FAIL in CLI** verify that the API key for the selected provider is present in the `.env` file in the root of the project.
+
+## Rules Management
+
+Taskmaster supports multiple AI coding assistant rule sets that can be configured during project initialization or managed afterward:
+
+- **Available Profiles**: Claude Code, Cline, Codex, Kiro, Roo Code, Trae, Windsurf (claude, cline, codex, kiro, roo, trae, windsurf)
+- **During Initialization**: Use `task-master init --rules kiro,windsurf` to specify which rule sets to include
+- **After Initialization**: Use `task-master rules add <profiles>` or `task-master rules remove <profiles>` to manage rule sets
+- **Interactive Setup**: Use `task-master rules setup` to launch an interactive prompt for selecting rule profiles
+- **Default Behavior**: If no `--rules` flag is specified during initialization, all available rule profiles are included
+- **Rule Structure**: Each profile creates its own directory (e.g., `.kiro/steering`, `.roo/rules`) with appropriate configuration files
+
+## Determining the Next Task
+
+- Run `next_task` / `task-master next` to show the next task to work on.
+- The command identifies tasks with all dependencies satisfied
+- Tasks are prioritized by priority level, dependency count, and ID
+- The command shows comprehensive task information including:
+    - Basic task details and description
+    - Implementation details
+    - Subtasks (if they exist)
+    - Contextual suggested actions
+- Recommended before starting any new development work
+- Respects your project's dependency structure
+- Ensures tasks are completed in the appropriate sequence
+- Provides ready-to-use commands for common task actions
+
+## Viewing Specific Task Details
+
+- Run `get_task` / `task-master show <id>` to view a specific task.
+- Use dot notation for subtasks: `task-master show 1.2` (shows subtask 2 of task 1)
+- Displays comprehensive information similar to the next command, but for a specific task
+- For parent tasks, shows all subtasks and their current status
+- For subtasks, shows parent task information and relationship
+- Provides contextual suggested actions appropriate for the specific task
+- Useful for examining task details before implementation or checking status
+
+## Managing Task Dependencies
+
+- Use `add_dependency` / `task-master add-dependency --id=<id> --depends-on=<id>` to add a dependency.
+- Use `remove_dependency` / `task-master remove-dependency --id=<id> --depends-on=<id>` to remove a dependency.
+- The system prevents circular dependencies and duplicate dependency entries
+- Dependencies are checked for existence before being added or removed
+- Task files are automatically regenerated after dependency changes
+- Dependencies are visualized with status indicators in task listings and files
+
+## Task Reorganization
+
+- Use `move_task` / `task-master move --from=<id> --to=<id>` to move tasks or subtasks within the hierarchy
+- This command supports several use cases:
+  - Moving a standalone task to become a subtask (e.g., `--from=5 --to=7`)
+  - Moving a subtask to become a standalone task (e.g., `--from=5.2 --to=7`) 
+  - Moving a subtask to a different parent (e.g., `--from=5.2 --to=7.3`)
+  - Reordering subtasks within the same parent (e.g., `--from=5.2 --to=5.4`)
+  - Moving a task to a new, non-existent ID position (e.g., `--from=5 --to=25`)
+  - Moving multiple tasks at once using comma-separated IDs (e.g., `--from=10,11,12 --to=16,17,18`)
+- The system includes validation to prevent data loss:
+  - Allows moving to non-existent IDs by creating placeholder tasks
+  - Prevents moving to existing task IDs that have content (to avoid overwriting)
+  - Validates source tasks exist before attempting to move them
+- The system maintains proper parent-child relationships and dependency integrity
+- Task files are automatically regenerated after the move operation
+- This provides greater flexibility in organizing and refining your task structure as project understanding evolves
+- This is especially useful when dealing with potential merge conflicts arising from teams creating tasks on separate branches. Solve these conflicts very easily by moving your tasks and keeping theirs.
+
+## Iterative Subtask Implementation
+
+Once a task has been broken down into subtasks using `expand_task` or similar methods, follow this iterative process for implementation:
+
+1.  **Understand the Goal (Preparation):**
+    *   Use `get_task` / `task-master show <subtaskId>` (see @`taskmaster.md`) to thoroughly understand the specific goals and requirements of the subtask.
+
+2.  **Initial Exploration & Planning (Iteration 1):**
+    *   This is the first attempt at creating a concrete implementation plan.
+    *   Explore the codebase to identify the precise files, functions, and even specific lines of code that will need modification.
+    *   Determine the intended code changes (diffs) and their locations.
+    *   Gather *all* relevant details from this exploration phase.
+
+3.  **Log the Plan:**
+    *   Run `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<detailed plan>'`.
+    *   Provide the *complete and detailed* findings from the exploration phase in the prompt. Include file paths, line numbers, proposed diffs, reasoning, and any potential challenges identified. Do not omit details. The goal is to create a rich, timestamped log within the subtask's `details`.
+
+4.  **Verify the Plan:**
+    *   Run `get_task` / `task-master show <subtaskId>` again to confirm that the detailed implementation plan has been successfully appended to the subtask's details.
+
+5.  **Begin Implementation:**
+    *   Set the subtask status using `set_task_status` / `task-master set-status --id=<subtaskId> --status=in-progress`.
+    *   Start coding based on the logged plan.
+
+6.  **Refine and Log Progress (Iteration 2+):**
+    *   As implementation progresses, you will encounter challenges, discover nuances, or confirm successful approaches.
+    *   **Before appending new information**: Briefly review the *existing* details logged in the subtask (using `get_task` or recalling from context) to ensure the update adds fresh insights and avoids redundancy.
+    *   **Regularly** use `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='<update details>\n- What worked...\n- What didn't work...'` to append new findings.
+    *   **Crucially, log:**
+        *   What worked ("fundamental truths" discovered).
+        *   What didn't work and why (to avoid repeating mistakes).
+        *   Specific code snippets or configurations that were successful.
+        *   Decisions made, especially if confirmed with user input.
+        *   Any deviations from the initial plan and the reasoning.
+    *   The objective is to continuously enrich the subtask's details, creating a log of the implementation journey that helps the AI (and human developers) learn, adapt, and avoid repeating errors.
+
+7.  **Review & Update Rules (Post-Implementation):**
+    *   Once the implementation for the subtask is functionally complete, review all code changes and the relevant chat history.
+    *   Identify any new or modified code patterns, conventions, or best practices established during the implementation.
+    *   Create new or update existing rules following internal guidelines (previously linked to `cursor_rules.md` and `self_improve.md`).
+
+8.  **Mark Task Complete:**
+    *   After verifying the implementation and updating any necessary rules, mark the subtask as completed: `set_task_status` / `task-master set-status --id=<subtaskId> --status=done`.
+
+9.  **Commit Changes (If using Git):**
+    *   Stage the relevant code changes and any updated/new rule files (`git add .`).
+    *   Craft a comprehensive Git commit message summarizing the work done for the subtask, including both code implementation and any rule adjustments.
+    *   Execute the commit command directly in the terminal (e.g., `git commit -m 'feat(module): Implement feature X for subtask <subtaskId>\n\n- Details about changes...\n- Updated rule Y for pattern Z'`).
+    *   Consider if a Changeset is needed according to internal versioning guidelines (previously linked to `changeset.md`). If so, run `npm run changeset`, stage the generated file, and amend the commit or create a new one.
+
+10. **Proceed to Next Subtask:**
+    *   Identify the next subtask (e.g., using `next_task` / `task-master next`).
+
+## Code Analysis & Refactoring Techniques
+
+- **Top-Level Function Search**:
+    - Useful for understanding module structure or planning refactors.
+    - Use grep/ripgrep to find exported functions/constants:
+      `rg "export (async function|function|const) \w+"` or similar patterns.
+    - Can help compare functions between files during migrations or identify potential naming conflicts.
+
+---
+*This workflow provides a general guideline. Adapt it based on your specific project needs and team practices.*

.kiro/steering/kiro_rules.md

@@ -0,0 +1,51 @@
+---
+inclusion: always
+---
+
+- **Required Rule Structure:**
+  ```markdown
+  ---
+  description: Clear, one-line description of what the rule enforces
+  globs: path/to/files/*.ext, other/path/**/*
+  alwaysApply: boolean
+  ---
+
+  - **Main Points in Bold**
+    - Sub-points with details
+    - Examples and explanations
+  ```
+
+- **File References:**
+  - Use `[filename](mdc:path/to/file)` ([filename](mdc:filename)) to reference files
+  - Example: [prisma.md](.kiro/steering/prisma.md) for rule references
+  - Example: [schema.prisma](mdc:prisma/schema.prisma) for code references
+
+- **Code Examples:**
+  - Use language-specific code blocks
+  ```typescript
+  // ✅ DO: Show good examples
+  const goodExample = true;
+  
+  // ❌ DON'T: Show anti-patterns
+  const badExample = false;
+  ```
+
+- **Rule Content Guidelines:**
+  - Start with high-level overview
+  - Include specific, actionable requirements
+  - Show examples of correct implementation
+  - Reference existing code when possible
+  - Keep rules DRY by referencing other rules
+
+- **Rule Maintenance:**
+  - Update rules when new patterns emerge
+  - Add examples from actual codebase
+  - Remove outdated patterns
+  - Cross-reference related rules
+
+- **Best Practices:**
+  - Use bullet points for clarity
+  - Keep descriptions concise
+  - Include both DO and DON'T examples
+  - Reference actual code over theoretical examples
+  - Use consistent formatting across rules 

.kiro/steering/self_improve.md

@@ -0,0 +1,70 @@
+---
+inclusion: always
+---
+
+- **Rule Improvement Triggers:**
+  - New code patterns not covered by existing rules
+  - Repeated similar implementations across files
+  - Common error patterns that could be prevented
+  - New libraries or tools being used consistently
+  - Emerging best practices in the codebase
+
+- **Analysis Process:**
+  - Compare new code with existing rules
+  - Identify patterns that should be standardized
+  - Look for references to external documentation
+  - Check for consistent error handling patterns
+  - Monitor test patterns and coverage
+
+- **Rule Updates:**
+  - **Add New Rules When:**
+    - A new technology/pattern is used in 3+ files
+    - Common bugs could be prevented by a rule
+    - Code reviews repeatedly mention the same feedback
+    - New security or performance patterns emerge
+
+  - **Modify Existing Rules When:**
+    - Better examples exist in the codebase
+    - Additional edge cases are discovered
+    - Related rules have been updated
+    - Implementation details have changed
+
+- **Example Pattern Recognition:**
+  ```typescript
+  // If you see repeated patterns like:
+  const data = await prisma.user.findMany({
+    select: { id: true, email: true },
+    where: { status: 'ACTIVE' }
+  });
+  
+  // Consider adding to [prisma.md](.kiro/steering/prisma.md):
+  // - Standard select fields
+  // - Common where conditions
+  // - Performance optimization patterns
+  ```
+
+- **Rule Quality Checks:**
+  - Rules should be actionable and specific
+  - Examples should come from actual code
+  - References should be up to date
+  - Patterns should be consistently enforced
+
+- **Continuous Improvement:**
+  - Monitor code review comments
+  - Track common development questions
+  - Update rules after major refactors
+  - Add links to relevant documentation
+  - Cross-reference related rules
+
+- **Rule Deprecation:**
+  - Mark outdated patterns as deprecated
+  - Remove rules that no longer apply
+  - Update references to deprecated rules
+  - Document migration paths for old patterns
+
+- **Documentation Updates:**
+  - Keep examples synchronized with code
+  - Update references to external docs
+  - Maintain links between related rules
+  - Document breaking changes
+Follow [kiro_rules.md](.kiro/steering/kiro_rules.md) for proper rule formatting and structure.

.kiro/steering/taskmaster.md

@@ -0,0 +1,556 @@
+---
+inclusion: always
+---
+
+# Taskmaster Tool & Command Reference
+
+This document provides a detailed reference for interacting with Taskmaster, covering both the recommended MCP tools, suitable for integrations like Kiro, and the corresponding `task-master` CLI commands, designed for direct user interaction or fallback.
+
+**Note:** For interacting with Taskmaster programmatically or via integrated tools, using the **MCP tools is strongly recommended** due to better performance, structured data, and error handling. The CLI commands serve as a user-friendly alternative and fallback. 
+
+**Important:** Several MCP tools involve AI processing... The AI-powered tools include `parse_prd`, `analyze_project_complexity`, `update_subtask`, `update_task`, `update`, `expand_all`, `expand_task`, and `add_task`.
+
+**🏷️ Tagged Task Lists System:** Task Master now supports **tagged task lists** for multi-context task management. This allows you to maintain separate, isolated lists of tasks for different features, branches, or experiments. Existing projects are seamlessly migrated to use a default "master" tag. Most commands now support a `--tag <name>` flag to specify which context to operate on. If omitted, commands use the currently active tag.
+
+---
+
+## Initialization & Setup
+
+### 1. Initialize Project (`init`)
+
+*   **MCP Tool:** `initialize_project`
+*   **CLI Command:** `task-master init [options]`
+*   **Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project.`
+*   **Key CLI Options:**
+    *   `--name <name>`: `Set the name for your project in Taskmaster's configuration.`
+    *   `--description <text>`: `Provide a brief description for your project.`
+    *   `--version <version>`: `Set the initial version for your project, e.g., '0.1.0'.`
+    *   `-y, --yes`: `Initialize Taskmaster quickly using default settings without interactive prompts.`
+*   **Usage:** Run this once at the beginning of a new project.
+*   **MCP Variant Description:** `Set up the basic Taskmaster file structure and configuration in the current directory for a new project by running the 'task-master init' command.`
+*   **Key MCP Parameters/Options:**
+    *   `projectName`: `Set the name for your project.` (CLI: `--name <name>`)
+    *   `projectDescription`: `Provide a brief description for your project.` (CLI: `--description <text>`)
+    *   `projectVersion`: `Set the initial version for your project, e.g., '0.1.0'.` (CLI: `--version <version>`)
+    *   `authorName`: `Author name.` (CLI: `--author <author>`)
+    *   `skipInstall`: `Skip installing dependencies. Default is false.` (CLI: `--skip-install`)
+    *   `addAliases`: `Add shell aliases tm and taskmaster. Default is false.` (CLI: `--aliases`)
+    *   `yes`: `Skip prompts and use defaults/provided arguments. Default is false.` (CLI: `-y, --yes`)
+*   **Usage:** Run this once at the beginning of a new project, typically via an integrated tool like Kiro. Operates on the current working directory of the MCP server. 
+*   **Important:** Once complete, you *MUST* parse a prd in order to generate tasks. There will be no tasks files until then. The next step after initializing should be to create a PRD using the example PRD in .taskmaster/templates/example_prd.txt. 
+*   **Tagging:** Use the `--tag` option to parse the PRD into a specific, non-default tag context. If the tag doesn't exist, it will be created automatically. Example: `task-master parse-prd spec.txt --tag=new-feature`.
+
+### 2. Parse PRD (`parse_prd`)
+
+*   **MCP Tool:** `parse_prd`
+*   **CLI Command:** `task-master parse-prd [file] [options]`
+*   **Description:** `Parse a Product Requirements Document, PRD, or text file with Taskmaster to automatically generate an initial set of tasks in tasks.json.`
+*   **Key Parameters/Options:**
+    *   `input`: `Path to your PRD or requirements text file that Taskmaster should parse for tasks.` (CLI: `[file]` positional or `-i, --input <file>`)
+    *   `output`: `Specify where Taskmaster should save the generated 'tasks.json' file. Defaults to '.taskmaster/tasks/tasks.json'.` (CLI: `-o, --output <file>`)
+    *   `numTasks`: `Approximate number of top-level tasks Taskmaster should aim to generate from the document.` (CLI: `-n, --num-tasks <number>`)
+    *   `force`: `Use this to allow Taskmaster to overwrite an existing 'tasks.json' without asking for confirmation.` (CLI: `-f, --force`)
+*   **Usage:** Useful for bootstrapping a project from an existing requirements document.
+*   **Notes:** Task Master will strictly adhere to any specific requirements mentioned in the PRD, such as libraries, database schemas, frameworks, tech stacks, etc., while filling in any gaps where the PRD isn't fully specified. Tasks are designed to provide the most direct implementation path while avoiding over-engineering.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress. If the user does not have a PRD, suggest discussing their idea and then use the example PRD in `.taskmaster/templates/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
+
+---
+
+## AI Model Configuration
+
+### 2. Manage Models (`models`)
+*   **MCP Tool:** `models`
+*   **CLI Command:** `task-master models [options]`
+*   **Description:** `View the current AI model configuration or set specific models for different roles (main, research, fallback). Allows setting custom model IDs for Ollama and OpenRouter.`
+*   **Key MCP Parameters/Options:**
+    *   `setMain <model_id>`: `Set the primary model ID for task generation/updates.` (CLI: `--set-main <model_id>`)
+    *   `setResearch <model_id>`: `Set the model ID for research-backed operations.` (CLI: `--set-research <model_id>`)
+    *   `setFallback <model_id>`: `Set the model ID to use if the primary fails.` (CLI: `--set-fallback <model_id>`)
+    *   `ollama <boolean>`: `Indicates the set model ID is a custom Ollama model.` (CLI: `--ollama`)
+    *   `openrouter <boolean>`: `Indicates the set model ID is a custom OpenRouter model.` (CLI: `--openrouter`)
+    *   `listAvailableModels <boolean>`: `If true, lists available models not currently assigned to a role.` (CLI: No direct equivalent; CLI lists available automatically)
+    *   `projectRoot <string>`: `Optional. Absolute path to the project root directory.` (CLI: Determined automatically)
+*   **Key CLI Options:**
+    *   `--set-main <model_id>`: `Set the primary model.`
+    *   `--set-research <model_id>`: `Set the research model.`
+    *   `--set-fallback <model_id>`: `Set the fallback model.`
+    *   `--ollama`: `Specify that the provided model ID is for Ollama (use with --set-*).`
+    *   `--openrouter`: `Specify that the provided model ID is for OpenRouter (use with --set-*). Validates against OpenRouter API.`
+    *   `--bedrock`: `Specify that the provided model ID is for AWS Bedrock (use with --set-*).`
+    *   `--setup`: `Run interactive setup to configure models, including custom Ollama/OpenRouter IDs.`
+*   **Usage (MCP):** Call without set flags to get current config. Use `setMain`, `setResearch`, or `setFallback` with a valid model ID to update the configuration. Use `listAvailableModels: true` to get a list of unassigned models. To set a custom model, provide the model ID and set `ollama: true` or `openrouter: true`.
+*   **Usage (CLI):** Run without flags to view current configuration and available models. Use set flags to update specific roles. Use `--setup` for guided configuration, including custom models. To set a custom model via flags, use `--set-<role>=<model_id>` along with either `--ollama` or `--openrouter`.
+*   **Notes:** Configuration is stored in `.taskmaster/config.json` in the project root. This command/tool modifies that file. Use `listAvailableModels` or `task-master models` to see internally supported models. OpenRouter custom models are validated against their live API. Ollama custom models are not validated live.
+*   **API note:** API keys for selected AI providers (based on their model) need to exist in the mcp.json file to be accessible in MCP context. The API keys must be present in the local .env file for the CLI to be able to read them.
+*   **Model costs:** The costs in supported models are expressed in dollars. An input/output value of 3 is $3.00. A value of 0.8 is $0.80. 
+*   **Warning:** DO NOT MANUALLY EDIT THE .taskmaster/config.json FILE. Use the included commands either in the MCP or CLI format as needed. Always prioritize MCP tools when available and use the CLI as a fallback.
+
+---
+
+## Task Listing & Viewing
+
+### 3. Get Tasks (`get_tasks`)
+
+*   **MCP Tool:** `get_tasks`
+*   **CLI Command:** `task-master list [options]`
+*   **Description:** `List your Taskmaster tasks, optionally filtering by status and showing subtasks.`
+*   **Key Parameters/Options:**
+    *   `status`: `Show only Taskmaster tasks matching this status (or multiple statuses, comma-separated), e.g., 'pending' or 'done,in-progress'.` (CLI: `-s, --status <status>`)
+    *   `withSubtasks`: `Include subtasks indented under their parent tasks in the list.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to list tasks from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Get an overview of the project status, often used at the start of a work session.
+
+### 4. Get Next Task (`next_task`)
+
+*   **MCP Tool:** `next_task`
+*   **CLI Command:** `task-master next [options]`
+*   **Description:** `Ask Taskmaster to show the next available task you can work on, based on status and completed dependencies.`
+*   **Key Parameters/Options:**
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `tag`: `Specify which tag context to use. Defaults to the current active tag.` (CLI: `--tag <name>`)
+*   **Usage:** Identify what to work on next according to the plan.
+
+### 5. Get Task Details (`get_task`)
+
+*   **MCP Tool:** `get_task`
+*   **CLI Command:** `task-master show [id] [options]`
+*   **Description:** `Display detailed information for one or more specific Taskmaster tasks or subtasks by ID.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task (e.g., '15'), subtask (e.g., '15.2'), or a comma-separated list of IDs ('1,5,10.2') you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
+    *   `tag`: `Specify which tag context to get the task(s) from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Understand the full details for a specific task. When multiple IDs are provided, a summary table is shown.
+*   **CRITICAL INFORMATION** If you need to collect information from multiple tasks, use comma-separated IDs (i.e. 1,2,3) to receive an array of tasks. Do not needlessly get tasks one at a time if you need to get many as that is wasteful.
+
+---
+
+## Task Creation & Modification
+
+### 6. Add Task (`add_task`)
+
+*   **MCP Tool:** `add_task`
+*   **CLI Command:** `task-master add-task [options]`
+*   **Description:** `Add a new task to Taskmaster by describing it; AI will structure it.`
+*   **Key Parameters/Options:**
+    *   `prompt`: `Required. Describe the new task you want Taskmaster to create, e.g., "Implement user authentication using JWT".` (CLI: `-p, --prompt <text>`)
+    *   `dependencies`: `Specify the IDs of any Taskmaster tasks that must be completed before this new one can start, e.g., '12,14'.` (CLI: `-d, --dependencies <ids>`)
+    *   `priority`: `Set the priority for the new task: 'high', 'medium', or 'low'. Default is 'medium'.` (CLI: `--priority <priority>`)
+    *   `research`: `Enable Taskmaster to use the research role for potentially more informed task creation.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to add the task to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Quickly add newly identified tasks during development.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 7. Add Subtask (`add_subtask`)
+
+*   **MCP Tool:** `add_subtask`
+*   **CLI Command:** `task-master add-subtask [options]`
+*   **Description:** `Add a new subtask to a Taskmaster parent task, or convert an existing task into a subtask.`
+*   **Key Parameters/Options:**
+    *   `id` / `parent`: `Required. The ID of the Taskmaster task that will be the parent.` (MCP: `id`, CLI: `-p, --parent <id>`)
+    *   `taskId`: `Use this if you want to convert an existing top-level Taskmaster task into a subtask of the specified parent.` (CLI: `-i, --task-id <id>`)
+    *   `title`: `Required if not using taskId. The title for the new subtask Taskmaster should create.` (CLI: `-t, --title <title>`)
+    *   `description`: `A brief description for the new subtask.` (CLI: `-d, --description <text>`)
+    *   `details`: `Provide implementation notes or details for the new subtask.` (CLI: `--details <text>`)
+    *   `dependencies`: `Specify IDs of other tasks or subtasks, e.g., '15' or '16.1', that must be done before this new subtask.` (CLI: `--dependencies <ids>`)
+    *   `status`: `Set the initial status for the new subtask. Default is 'pending'.` (CLI: `-s, --status <status>`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after adding the subtask.` (CLI: `--generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Break down tasks manually or reorganize existing tasks.
+
+### 8. Update Tasks (`update`)
+
+*   **MCP Tool:** `update`
+*   **CLI Command:** `task-master update [options]`
+*   **Description:** `Update multiple upcoming tasks in Taskmaster based on new context or changes, starting from a specific task ID.`
+*   **Key Parameters/Options:**
+    *   `from`: `Required. The ID of the first task Taskmaster should update. All tasks with this ID or higher that are not 'done' will be considered.` (CLI: `--from <id>`)
+    *   `prompt`: `Required. Explain the change or new context for Taskmaster to apply to the tasks, e.g., "We are now using React Query instead of Redux Toolkit for data fetching".` (CLI: `-p, --prompt <text>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Handle significant implementation changes or pivots that affect multiple future tasks. Example CLI: `task-master update --from='18' --prompt='Switching to React Query.\nNeed to refactor data fetching...'`
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 9. Update Task (`update_task`)
+
+*   **MCP Tool:** `update_task`
+*   **CLI Command:** `task-master update-task [options]`
+*   **Description:** `Modify a specific Taskmaster task by ID, incorporating new information or changes. By default, this replaces the existing task details.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The specific ID of the Taskmaster task, e.g., '15', you want to update.` (CLI: `-i, --id <id>`)
+    *   `prompt`: `Required. Explain the specific changes or provide the new information Taskmaster should incorporate into this task.` (CLI: `-p, --prompt <text>`)
+    *   `append`: `If true, appends the prompt content to the task's details with a timestamp, rather than replacing them. Behaves like update-subtask.` (CLI: `--append`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Refine a specific task based on new understanding. Use `--append` to log progress without creating subtasks.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 10. Update Subtask (`update_subtask`)
+
+*   **MCP Tool:** `update_subtask`
+*   **CLI Command:** `task-master update-subtask [options]`
+*   **Description:** `Append timestamped notes or details to a specific Taskmaster subtask without overwriting existing content. Intended for iterative implementation logging.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster subtask, e.g., '5.2', to update with new information.` (CLI: `-i, --id <id>`)
+    *   `prompt`: `Required. The information, findings, or progress notes to append to the subtask's details with a timestamp.` (CLI: `-p, --prompt <text>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed updates. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context the subtask belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Log implementation progress, findings, and discoveries during subtask development. Each update is timestamped and appended to preserve the implementation journey.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 11. Set Task Status (`set_task_status`)
+
+*   **MCP Tool:** `set_task_status`
+*   **CLI Command:** `task-master set-status [options]`
+*   **Description:** `Update the status of one or more Taskmaster tasks or subtasks, e.g., 'pending', 'in-progress', 'done'.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID(s) of the Taskmaster task(s) or subtask(s), e.g., '15', '15.2', or '16,17.1', to update.` (CLI: `-i, --id <id>`)
+    *   `status`: `Required. The new status to set, e.g., 'done', 'pending', 'in-progress', 'review', 'cancelled'.` (CLI: `-s, --status <status>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Mark progress as tasks move through the development cycle.
+
+### 12. Remove Task (`remove_task`)
+
+*   **MCP Tool:** `remove_task`
+*   **CLI Command:** `task-master remove-task [options]`
+*   **Description:** `Permanently remove a task or subtask from the Taskmaster tasks list.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task, e.g., '5', or subtask, e.g., '5.2', to permanently remove.` (CLI: `-i, --id <id>`)
+    *   `yes`: `Skip the confirmation prompt and immediately delete the task.` (CLI: `-y, --yes`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Permanently delete tasks or subtasks that are no longer needed in the project.
+*   **Notes:** Use with caution as this operation cannot be undone. Consider using 'blocked', 'cancelled', or 'deferred' status instead if you just want to exclude a task from active planning but keep it for reference. The command automatically cleans up dependency references in other tasks.
+
+---
+
+## Task Structure & Breakdown
+
+### 13. Expand Task (`expand_task`)
+
+*   **MCP Tool:** `expand_task`
+*   **CLI Command:** `task-master expand [options]`
+*   **Description:** `Use Taskmaster's AI to break down a complex task into smaller, manageable subtasks. Appends subtasks by default.`
+*   **Key Parameters/Options:**
+    *   `id`: `The ID of the specific Taskmaster task you want to break down into subtasks.` (CLI: `-i, --id <id>`)
+    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create. Uses complexity analysis/defaults otherwise.` (CLI: `-n, --num <number>`)
+    *   `research`: `Enable Taskmaster to use the research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `prompt`: `Optional: Provide extra context or specific instructions to Taskmaster for generating the subtasks.` (CLI: `-p, --prompt <text>`)
+    *   `force`: `Optional: If true, clear existing subtasks before generating new ones. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context the task belongs to. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Generate a detailed implementation plan for a complex task before starting coding. Automatically uses complexity report recommendations if available and `num` is not specified.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 14. Expand All Tasks (`expand_all`)
+
+*   **MCP Tool:** `expand_all`
+*   **CLI Command:** `task-master expand --all [options]` (Note: CLI uses the `expand` command with the `--all` flag)
+*   **Description:** `Tell Taskmaster to automatically expand all eligible pending/in-progress tasks based on complexity analysis or defaults. Appends subtasks by default.`
+*   **Key Parameters/Options:**
+    *   `num`: `Optional: Suggests how many subtasks Taskmaster should aim to create per task.` (CLI: `-n, --num <number>`)
+    *   `research`: `Enable research role for more informed subtask generation. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `prompt`: `Optional: Provide extra context for Taskmaster to apply generally during expansion.` (CLI: `-p, --prompt <text>`)
+    *   `force`: `Optional: If true, clear existing subtasks before generating new ones for each eligible task. Default is false (append).` (CLI: `--force`)
+    *   `tag`: `Specify which tag context to expand. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Useful after initial task generation or complexity analysis to break down multiple tasks at once.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 15. Clear Subtasks (`clear_subtasks`)
+
+*   **MCP Tool:** `clear_subtasks`
+*   **CLI Command:** `task-master clear-subtasks [options]`
+*   **Description:** `Remove all subtasks from one or more specified Taskmaster parent tasks.`
+*   **Key Parameters/Options:**
+    *   `id`: `The ID(s) of the Taskmaster parent task(s) whose subtasks you want to remove, e.g., '15' or '16,18'. Required unless using 'all'.` (CLI: `-i, --id <ids>`)
+    *   `all`: `Tell Taskmaster to remove subtasks from all parent tasks.` (CLI: `--all`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Used before regenerating subtasks with `expand_task` if the previous breakdown needs replacement.
+
+### 16. Remove Subtask (`remove_subtask`)
+
+*   **MCP Tool:** `remove_subtask`
+*   **CLI Command:** `task-master remove-subtask [options]`
+*   **Description:** `Remove a subtask from its Taskmaster parent, optionally converting it into a standalone task.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID(s) of the Taskmaster subtask(s) to remove, e.g., '15.2' or '16.1,16.3'.` (CLI: `-i, --id <id>`)
+    *   `convert`: `If used, Taskmaster will turn the subtask into a regular top-level task instead of deleting it.` (CLI: `-c, --convert`)
+    *   `generate`: `Enable Taskmaster to regenerate markdown task files after removing the subtask.` (CLI: `--generate`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Delete unnecessary subtasks or promote a subtask to a top-level task.
+
+### 17. Move Task (`move_task`)
+
+*   **MCP Tool:** `move_task`
+*   **CLI Command:** `task-master move [options]`
+*   **Description:** `Move a task or subtask to a new position within the task hierarchy.`
+*   **Key Parameters/Options:**
+    *   `from`: `Required. ID of the task/subtask to move (e.g., "5" or "5.2"). Can be comma-separated for multiple tasks.` (CLI: `--from <id>`)
+    *   `to`: `Required. ID of the destination (e.g., "7" or "7.3"). Must match the number of source IDs if comma-separated.` (CLI: `--to <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Reorganize tasks by moving them within the hierarchy. Supports various scenarios like:
+    *   Moving a task to become a subtask
+    *   Moving a subtask to become a standalone task
+    *   Moving a subtask to a different parent
+    *   Reordering subtasks within the same parent
+    *   Moving a task to a new, non-existent ID (automatically creates placeholders)
+    *   Moving multiple tasks at once with comma-separated IDs
+*   **Validation Features:**
+    *   Allows moving tasks to non-existent destination IDs (creates placeholder tasks)
+    *   Prevents moving to existing task IDs that already have content (to avoid overwriting)
+    *   Validates that source tasks exist before attempting to move them
+    *   Maintains proper parent-child relationships
+*   **Example CLI:** `task-master move --from=5.2 --to=7.3` to move subtask 5.2 to become subtask 7.3.
+*   **Example Multi-Move:** `task-master move --from=10,11,12 --to=16,17,18` to move multiple tasks to new positions.
+*   **Common Use:** Resolving merge conflicts in tasks.json when multiple team members create tasks on different branches.
+
+---
+
+## Dependency Management
+
+### 18. Add Dependency (`add_dependency`)
+
+*   **MCP Tool:** `add_dependency`
+*   **CLI Command:** `task-master add-dependency [options]`
+*   **Description:** `Define a dependency in Taskmaster, making one task a prerequisite for another.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task that will depend on another.` (CLI: `-i, --id <id>`)
+    *   `dependsOn`: `Required. The ID of the Taskmaster task that must be completed first, the prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <path>`)
+*   **Usage:** Establish the correct order of execution between tasks.
+
+### 19. Remove Dependency (`remove_dependency`)
+
+*   **MCP Tool:** `remove_dependency`
+*   **CLI Command:** `task-master remove-dependency [options]`
+*   **Description:** `Remove a dependency relationship between two Taskmaster tasks.`
+*   **Key Parameters/Options:**
+    *   `id`: `Required. The ID of the Taskmaster task you want to remove a prerequisite from.` (CLI: `-i, --id <id>`)
+    *   `dependsOn`: `Required. The ID of the Taskmaster task that should no longer be a prerequisite.` (CLI: `-d, --depends-on <id>`)
+    *   `tag`: `Specify which tag context to operate on. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Update task relationships when the order of execution changes.
+
+### 20. Validate Dependencies (`validate_dependencies`)
+
+*   **MCP Tool:** `validate_dependencies`
+*   **CLI Command:** `task-master validate-dependencies [options]`
+*   **Description:** `Check your Taskmaster tasks for dependency issues (like circular references or links to non-existent tasks) without making changes.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to validate. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Audit the integrity of your task dependencies.
+
+### 21. Fix Dependencies (`fix_dependencies`)
+
+*   **MCP Tool:** `fix_dependencies`
+*   **CLI Command:** `task-master fix-dependencies [options]`
+*   **Description:** `Automatically fix dependency issues (like circular references or links to non-existent tasks) in your Taskmaster tasks.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to fix dependencies in. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Clean up dependency errors automatically.
+
+---
+
+## Analysis & Reporting
+
+### 22. Analyze Project Complexity (`analyze_project_complexity`)
+
+*   **MCP Tool:** `analyze_project_complexity`
+*   **CLI Command:** `task-master analyze-complexity [options]`
+*   **Description:** `Have Taskmaster analyze your tasks to determine their complexity and suggest which ones need to be broken down further.`
+*   **Key Parameters/Options:**
+    *   `output`: `Where to save the complexity analysis report. Default is '.taskmaster/reports/task-complexity-report.json' (or '..._tagname.json' if a tag is used).` (CLI: `-o, --output <file>`)
+    *   `threshold`: `The minimum complexity score (1-10) that should trigger a recommendation to expand a task.` (CLI: `-t, --threshold <number>`)
+    *   `research`: `Enable research role for more accurate complexity analysis. Requires appropriate API key.` (CLI: `-r, --research`)
+    *   `tag`: `Specify which tag context to analyze. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Used before breaking down tasks to identify which ones need the most attention.
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. Please inform users to hang tight while the operation is in progress.
+
+### 23. View Complexity Report (`complexity_report`)
+
+*   **MCP Tool:** `complexity_report`
+*   **CLI Command:** `task-master complexity-report [options]`
+*   **Description:** `Display the task complexity analysis report in a readable format.`
+*   **Key Parameters/Options:**
+    *   `tag`: `Specify which tag context to show the report for. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to the complexity report (default: '.taskmaster/reports/task-complexity-report.json').` (CLI: `-f, --file <file>`)
+*   **Usage:** Review and understand the complexity analysis results after running analyze-complexity.
+
+---
+
+## File Management
+
+### 24. Generate Task Files (`generate`)
+
+*   **MCP Tool:** `generate`
+*   **CLI Command:** `task-master generate [options]`
+*   **Description:** `Create or update individual Markdown files for each task based on your tasks.json.`
+*   **Key Parameters/Options:**
+    *   `output`: `The directory where Taskmaster should save the task files (default: in a 'tasks' directory).` (CLI: `-o, --output <directory>`)
+    *   `tag`: `Specify which tag context to generate files for. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+*   **Usage:** Run this after making changes to tasks.json to keep individual task files up to date. This command is now manual and no longer runs automatically.
+
+---
+
+## AI-Powered Research
+
+### 25. Research (`research`)
+
+*   **MCP Tool:** `research`
+*   **CLI Command:** `task-master research [options]`
+*   **Description:** `Perform AI-powered research queries with project context to get fresh, up-to-date information beyond the AI's knowledge cutoff.`
+*   **Key Parameters/Options:**
+    *   `query`: `Required. Research query/prompt (e.g., "What are the latest best practices for React Query v5?").` (CLI: `[query]` positional or `-q, --query <text>`)
+    *   `taskIds`: `Comma-separated list of task/subtask IDs from the current tag context (e.g., "15,16.2,17").` (CLI: `-i, --id <ids>`)
+    *   `filePaths`: `Comma-separated list of file paths for context (e.g., "src/api.js,docs/readme.md").` (CLI: `-f, --files <paths>`)
+    *   `customContext`: `Additional custom context text to include in the research.` (CLI: `-c, --context <text>`)
+    *   `includeProjectTree`: `Include project file tree structure in context (default: false).` (CLI: `--tree`)
+    *   `detailLevel`: `Detail level for the research response: 'low', 'medium', 'high' (default: medium).` (CLI: `--detail <level>`)
+    *   `saveTo`: `Task or subtask ID (e.g., "15", "15.2") to automatically save the research conversation to.` (CLI: `--save-to <id>`)
+    *   `saveFile`: `If true, saves the research conversation to a markdown file in '.taskmaster/docs/research/'.` (CLI: `--save-file`)
+    *   `noFollowup`: `Disables the interactive follow-up question menu in the CLI.` (CLI: `--no-followup`)
+    *   `tag`: `Specify which tag context to use for task-based context gathering. Defaults to the current active tag.` (CLI: `--tag <name>`)
+    *   `projectRoot`: `The directory of the project. Must be an absolute path.` (CLI: Determined automatically)
+*   **Usage:** **This is a POWERFUL tool that agents should use FREQUENTLY** to:
+    *   Get fresh information beyond knowledge cutoff dates
+    *   Research latest best practices, library updates, security patches
+    *   Find implementation examples for specific technologies
+    *   Validate approaches against current industry standards
+    *   Get contextual advice based on project files and tasks
+*   **When to Consider Using Research:**
+    *   **Before implementing any task** - Research current best practices
+    *   **When encountering new technologies** - Get up-to-date implementation guidance (libraries, apis, etc)
+    *   **For security-related tasks** - Find latest security recommendations
+    *   **When updating dependencies** - Research breaking changes and migration guides
+    *   **For performance optimization** - Get current performance best practices
+    *   **When debugging complex issues** - Research known solutions and workarounds
+*   **Research + Action Pattern:**
+    *   Use `research` to gather fresh information
+    *   Use `update_subtask` to commit findings with timestamps
+    *   Use `update_task` to incorporate research into task details
+    *   Use `add_task` with research flag for informed task creation
+*   **Important:** This MCP tool makes AI calls and can take up to a minute to complete. The research provides FRESH data beyond the AI's training cutoff, making it invaluable for current best practices and recent developments.
+
+---
+
+## Tag Management
+
+This new suite of commands allows you to manage different task contexts (tags).
+
+### 26. List Tags (`tags`)
+
+*   **MCP Tool:** `list_tags`
+*   **CLI Command:** `task-master tags [options]`
+*   **Description:** `List all available tags with task counts, completion status, and other metadata.`
+*   **Key Parameters/Options:**
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+    *   `--show-metadata`: `Include detailed metadata in the output (e.g., creation date, description).` (CLI: `--show-metadata`)
+
+### 27. Add Tag (`add_tag`)
+
+*   **MCP Tool:** `add_tag`
+*   **CLI Command:** `task-master add-tag <tagName> [options]`
+*   **Description:** `Create a new, empty tag context, or copy tasks from another tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the new tag to create (alphanumeric, hyphens, underscores).` (CLI: `<tagName>` positional)
+    *   `--from-branch`: `Creates a tag with a name derived from the current git branch, ignoring the <tagName> argument.` (CLI: `--from-branch`)
+    *   `--copy-from-current`: `Copy tasks from the currently active tag to the new tag.` (CLI: `--copy-from-current`)
+    *   `--copy-from <tag>`: `Copy tasks from a specific source tag to the new tag.` (CLI: `--copy-from <tag>`)
+    *   `--description <text>`: `Provide an optional description for the new tag.` (CLI: `-d, --description <text>`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 28. Delete Tag (`delete_tag`)
+
+*   **MCP Tool:** `delete_tag`
+*   **CLI Command:** `task-master delete-tag <tagName> [options]`
+*   **Description:** `Permanently delete a tag and all of its associated tasks.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to delete.` (CLI: `<tagName>` positional)
+    *   `--yes`: `Skip the confirmation prompt.` (CLI: `-y, --yes`)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 29. Use Tag (`use_tag`)
+
+*   **MCP Tool:** `use_tag`
+*   **CLI Command:** `task-master use-tag <tagName>`
+*   **Description:** `Switch your active task context to a different tag.`
+*   **Key Parameters/Options:**
+    *   `tagName`: `Name of the tag to switch to.` (CLI: `<tagName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 30. Rename Tag (`rename_tag`)
+
+*   **MCP Tool:** `rename_tag`
+*   **CLI Command:** `task-master rename-tag <oldName> <newName>`
+*   **Description:** `Rename an existing tag.`
+*   **Key Parameters/Options:**
+    *   `oldName`: `The current name of the tag.` (CLI: `<oldName>` positional)
+    *   `newName`: `The new name for the tag.` (CLI: `<newName>` positional)
+    *   `file`: `Path to your Taskmaster 'tasks.json' file. Default relies on auto-detection.` (CLI: `-f, --file <file>`)
+
+### 31. Copy Tag (`copy_tag`)
+
+*   **MCP Tool:** `copy_tag`
+*   **CLI Command:** `task-master copy-tag <sourceName> <targetName> [options]`
+*   **Description:** `Copy an entire tag context, including all its tasks and metadata, to a new tag.`
+*   **Key Parameters/Options:**
+    *   `sourceName`: `Name of the tag to copy from.` (CLI: `<sourceName>` positional)
+    *   `targetName`: `Name of the new tag to create.` (CLI: `<targetName>` positional)
+    *   `--description <text>`: `Optional description for the new tag.` (CLI: `-d, --description <text>`)
+
+---
+
+## Miscellaneous
+
+### 32. Sync Readme (`sync-readme`) -- experimental
+
+*   **MCP Tool:** N/A
+*   **CLI Command:** `task-master sync-readme [options]`
+*   **Description:** `Exports your task list to your project's README.md file, useful for showcasing progress.`
+*   **Key Parameters/Options:**
+    *   `status`: `Filter tasks by status (e.g., 'pending', 'done').` (CLI: `-s, --status <status>`)
+    *   `withSubtasks`: `Include subtasks in the export.` (CLI: `--with-subtasks`)
+    *   `tag`: `Specify which tag context to export from. Defaults to the current active tag.` (CLI: `--tag <name>`)
+
+---
+
+## Environment Variables Configuration (Updated)
+
+Taskmaster primarily uses the **`.taskmaster/config.json`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
+
+Environment variables are used **only** for sensitive API keys related to AI providers and specific overrides like the Ollama base URL:
+
+*   **API Keys (Required for corresponding provider):**
+    *   `ANTHROPIC_API_KEY`
+    *   `PERPLEXITY_API_KEY`
+    *   `OPENAI_API_KEY`
+    *   `GOOGLE_API_KEY`
+    *   `MISTRAL_API_KEY`
+    *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
+    *   `OPENROUTER_API_KEY`
+    *   `XAI_API_KEY`
+    *   `OLLAMA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
+*   **Endpoints (Optional/Provider Specific inside .taskmaster/config.json):**
+    *   `AZURE_OPENAI_ENDPOINT`
+    *   `OLLAMA_BASE_URL` (Default: `http://localhost:11434/api`)
+
+**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.kiro/mcp.json`** file (for MCP/Kiro integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmaster/config.json` via `task-master models` command or `models` MCP tool.
+
+---
+
+For details on how these commands fit into the development process, see the [dev_workflow.md](.kiro/steering/dev_workflow.md).

.kiro/steering/taskmaster_hooks_workflow.md

@@ -0,0 +1,59 @@
+---
+inclusion: always
+---
+
+# Taskmaster Hook-Driven Workflow
+
+## Core Principle: Hooks Automate Task Management
+
+When working with Taskmaster in Kiro, **avoid manually marking tasks as done**. The hook system automatically handles task completion based on:
+
+- **Test Success**: `[TM] Test Success Task Completer` detects passing tests and prompts for task completion
+- **Code Changes**: `[TM] Code Change Task Tracker` monitors implementation progress
+- **Dependency Chains**: `[TM] Task Dependency Auto-Progression` auto-starts dependent tasks
+
+## AI Assistant Workflow
+
+Follow this pattern when implementing features:
+
+1. **Implement First**: Write code, create tests, make changes
+2. **Save Frequently**: Hooks trigger on file saves to track progress automatically
+3. **Let Hooks Decide**: Allow hooks to detect completion rather than manually setting status
+4. **Respond to Prompts**: Confirm when hooks suggest task completion
+
+## Key Rules for AI Assistants
+
+- **Never use `tm set-status --status=done`** unless hooks fail to detect completion
+- **Always write tests** - they provide the most reliable completion signal
+- **Save files after implementation** - this triggers progress tracking
+- **Trust hook suggestions** - if no completion prompt appears, more work may be needed
+
+## Automatic Behaviors
+
+The hook system provides:
+
+- **Progress Logging**: Implementation details automatically added to task notes
+- **Evidence-Based Completion**: Tasks marked done only when criteria are met
+- **Dependency Management**: Next tasks auto-started when dependencies complete
+- **Natural Flow**: Focus on coding, not task management overhead
+
+## Manual Override Cases
+
+Only manually set task status for:
+
+- Documentation-only tasks
+- Tasks without testable outcomes
+- Emergency fixes without proper test coverage
+
+Use `tm set-status` sparingly - prefer hook-driven completion.
+
+## Implementation Pattern
+
+```
+1. Implement feature → Save file
+2. Write tests → Save test file
+3. Tests pass → Hook prompts completion
+4. Confirm completion → Next task auto-starts
+```
+
+This workflow ensures proper task tracking while maintaining development flow.

.mcp.json

@@ -0,0 +1,9 @@
+{
+	"mcpServers": {
+		"task-master-ai": {
+			"type": "stdio",
+			"command": "npx",
+			"args": ["-y", "task-master-ai"]
+		}
+	}
+}

.taskmaster/CLAUDE.md

@@ -0,0 +1,417 @@
+# Task Master AI - Agent Integration Guide
+
+## Essential Commands
+
+### Core Workflow Commands
+
+```bash
+# Project Setup
+task-master init                                    # Initialize Task Master in current project
+task-master parse-prd .taskmaster/docs/prd.txt      # Generate tasks from PRD document
+task-master models --setup                        # Configure AI models interactively
+
+# Daily Development Workflow
+task-master list                                   # Show all tasks with status
+task-master next                                   # Get next available task to work on
+task-master show <id>                             # View detailed task information (e.g., task-master show 1.2)
+task-master set-status --id=<id> --status=done    # Mark task complete
+
+# Task Management
+task-master add-task --prompt="description" --research        # Add new task with AI assistance
+task-master expand --id=<id> --research --force              # Break task into subtasks
+task-master update-task --id=<id> --prompt="changes"         # Update specific task
+task-master update --from=<id> --prompt="changes"            # Update multiple tasks from ID onwards
+task-master update-subtask --id=<id> --prompt="notes"        # Add implementation notes to subtask
+
+# Analysis & Planning
+task-master analyze-complexity --research          # Analyze task complexity
+task-master complexity-report                      # View complexity analysis
+task-master expand --all --research               # Expand all eligible tasks
+
+# Dependencies & Organization
+task-master add-dependency --id=<id> --depends-on=<id>       # Add task dependency
+task-master move --from=<id> --to=<id>                       # Reorganize task hierarchy
+task-master validate-dependencies                            # Check for dependency issues
+task-master generate                                         # Update task markdown files (usually auto-called)
+```
+
+## Key Files & Project Structure
+
+### Core Files
+
+- `.taskmaster/tasks/tasks.json` - Main task data file (auto-managed)
+- `.taskmaster/config.json` - AI model configuration (use `task-master models` to modify)
+- `.taskmaster/docs/prd.txt` - Product Requirements Document for parsing
+- `.taskmaster/tasks/*.txt` - Individual task files (auto-generated from tasks.json)
+- `.env` - API keys for CLI usage
+
+### Claude Code Integration Files
+
+- `CLAUDE.md` - Auto-loaded context for Claude Code (this file)
+- `.claude/settings.json` - Claude Code tool allowlist and preferences
+- `.claude/commands/` - Custom slash commands for repeated workflows
+- `.mcp.json` - MCP server configuration (project-specific)
+
+### Directory Structure
+
+```
+project/
+├── .taskmaster/
+│   ├── tasks/              # Task files directory
+│   │   ├── tasks.json      # Main task database
+│   │   ├── task-1.md      # Individual task files
+│   │   └── task-2.md
+│   ├── docs/              # Documentation directory
+│   │   ├── prd.txt        # Product requirements
+│   ├── reports/           # Analysis reports directory
+│   │   └── task-complexity-report.json
+│   ├── templates/         # Template files
+│   │   └── example_prd.txt  # Example PRD template
+│   └── config.json        # AI models & settings
+├── .claude/
+│   ├── settings.json      # Claude Code configuration
+│   └── commands/         # Custom slash commands
+├── .env                  # API keys
+├── .mcp.json            # MCP configuration
+└── CLAUDE.md            # This file - auto-loaded by Claude Code
+```
+
+## MCP Integration
+
+Task Master provides an MCP server that Claude Code can connect to. Configure in `.mcp.json`:
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "ANTHROPIC_API_KEY": "your_key_here",
+        "PERPLEXITY_API_KEY": "your_key_here",
+        "OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
+        "GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
+        "XAI_API_KEY": "XAI_API_KEY_HERE",
+        "OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
+        "MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
+        "AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
+        "OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE"
+      }
+    }
+  }
+}
+```
+
+### Essential MCP Tools
+
+```javascript
+help; // = shows available taskmaster commands
+// Project setup
+initialize_project; // = task-master init
+parse_prd; // = task-master parse-prd
+
+// Daily workflow
+get_tasks; // = task-master list
+next_task; // = task-master next
+get_task; // = task-master show <id>
+set_task_status; // = task-master set-status
+
+// Task management
+add_task; // = task-master add-task
+expand_task; // = task-master expand
+update_task; // = task-master update-task
+update_subtask; // = task-master update-subtask
+update; // = task-master update
+
+// Analysis
+analyze_project_complexity; // = task-master analyze-complexity
+complexity_report; // = task-master complexity-report
+```
+
+## Claude Code Workflow Integration
+
+### Standard Development Workflow
+
+#### 1. Project Initialization
+
+```bash
+# Initialize Task Master
+task-master init
+
+# Create or obtain PRD, then parse it
+task-master parse-prd .taskmaster/docs/prd.txt
+
+# Analyze complexity and expand tasks
+task-master analyze-complexity --research
+task-master expand --all --research
+```
+
+If tasks already exist, another PRD can be parsed (with new information only!) using parse-prd with --append flag. This will add the generated tasks to the existing list of tasks..
+
+#### 2. Daily Development Loop
+
+```bash
+# Start each session
+task-master next                           # Find next available task
+task-master show <id>                     # Review task details
+
+# During implementation, check in code context into the tasks and subtasks
+task-master update-subtask --id=<id> --prompt="implementation notes..."
+
+# Complete tasks
+task-master set-status --id=<id> --status=done
+```
+
+#### 3. Multi-Claude Workflows
+
+For complex projects, use multiple Claude Code sessions:
+
+```bash
+# Terminal 1: Main implementation
+cd project && claude
+
+# Terminal 2: Testing and validation
+cd project-test-worktree && claude
+
+# Terminal 3: Documentation updates
+cd project-docs-worktree && claude
+```
+
+### Custom Slash Commands
+
+Create `.claude/commands/taskmaster-next.md`:
+
+```markdown
+Find the next available Task Master task and show its details.
+
+Steps:
+
+1. Run `task-master next` to get the next task
+2. If a task is available, run `task-master show <id>` for full details
+3. Provide a summary of what needs to be implemented
+4. Suggest the first implementation step
+```
+
+Create `.claude/commands/taskmaster-complete.md`:
+
+```markdown
+Complete a Task Master task: $ARGUMENTS
+
+Steps:
+
+1. Review the current task with `task-master show $ARGUMENTS`
+2. Verify all implementation is complete
+3. Run any tests related to this task
+4. Mark as complete: `task-master set-status --id=$ARGUMENTS --status=done`
+5. Show the next available task with `task-master next`
+```
+
+## Tool Allowlist Recommendations
+
+Add to `.claude/settings.json`:
+
+```json
+{
+  "allowedTools": [
+    "Edit",
+    "Bash(task-master *)",
+    "Bash(git commit:*)",
+    "Bash(git add:*)",
+    "Bash(npm run *)",
+    "mcp__task_master_ai__*"
+  ]
+}
+```
+
+## Configuration & Setup
+
+### API Keys Required
+
+At least **one** of these API keys must be configured:
+
+- `ANTHROPIC_API_KEY` (Claude models) - **Recommended**
+- `PERPLEXITY_API_KEY` (Research features) - **Highly recommended**
+- `OPENAI_API_KEY` (GPT models)
+- `GOOGLE_API_KEY` (Gemini models)
+- `MISTRAL_API_KEY` (Mistral models)
+- `OPENROUTER_API_KEY` (Multiple models)
+- `XAI_API_KEY` (Grok models)
+
+An API key is required for any provider used across any of the 3 roles defined in the `models` command.
+
+### Model Configuration
+
+```bash
+# Interactive setup (recommended)
+task-master models --setup
+
+# Set specific models
+task-master models --set-main claude-3-5-sonnet-20241022
+task-master models --set-research perplexity-llama-3.1-sonar-large-128k-online
+task-master models --set-fallback gpt-4o-mini
+```
+
+## Task Structure & IDs
+
+### Task ID Format
+
+- Main tasks: `1`, `2`, `3`, etc.
+- Subtasks: `1.1`, `1.2`, `2.1`, etc.
+- Sub-subtasks: `1.1.1`, `1.1.2`, etc.
+
+### Task Status Values
+
+- `pending` - Ready to work on
+- `in-progress` - Currently being worked on
+- `done` - Completed and verified
+- `deferred` - Postponed
+- `cancelled` - No longer needed
+- `blocked` - Waiting on external factors
+
+### Task Fields
+
+```json
+{
+  "id": "1.2",
+  "title": "Implement user authentication",
+  "description": "Set up JWT-based auth system",
+  "status": "pending",
+  "priority": "high",
+  "dependencies": ["1.1"],
+  "details": "Use bcrypt for hashing, JWT for tokens...",
+  "testStrategy": "Unit tests for auth functions, integration tests for login flow",
+  "subtasks": []
+}
+```
+
+## Claude Code Best Practices with Task Master
+
+### Context Management
+
+- Use `/clear` between different tasks to maintain focus
+- This CLAUDE.md file is automatically loaded for context
+- Use `task-master show <id>` to pull specific task context when needed
+
+### Iterative Implementation
+
+1. `task-master show <subtask-id>` - Understand requirements
+2. Explore codebase and plan implementation
+3. `task-master update-subtask --id=<id> --prompt="detailed plan"` - Log plan
+4. `task-master set-status --id=<id> --status=in-progress` - Start work
+5. Implement code following logged plan
+6. `task-master update-subtask --id=<id> --prompt="what worked/didn't work"` - Log progress
+7. `task-master set-status --id=<id> --status=done` - Complete task
+
+### Complex Workflows with Checklists
+
+For large migrations or multi-step processes:
+
+1. Create a markdown PRD file describing the new changes: `touch task-migration-checklist.md` (prds can be .txt or .md)
+2. Use Taskmaster to parse the new prd with `task-master parse-prd --append` (also available in MCP)
+3. Use Taskmaster to expand the newly generated tasks into subtasks. Consdier using `analyze-complexity` with the correct --to and --from IDs (the new ids) to identify the ideal subtask amounts for each task. Then expand them.
+4. Work through items systematically, checking them off as completed
+5. Use `task-master update-subtask` to log progress on each task/subtask and/or updating/researching them before/during implementation if getting stuck
+
+### Git Integration
+
+Task Master works well with `gh` CLI:
+
+```bash
+# Create PR for completed task
+gh pr create --title "Complete task 1.2: User authentication" --body "Implements JWT auth system as specified in task 1.2"
+
+# Reference task in commits
+git commit -m "feat: implement JWT auth (task 1.2)"
+```
+
+### Parallel Development with Git Worktrees
+
+```bash
+# Create worktrees for parallel task development
+git worktree add ../project-auth feature/auth-system
+git worktree add ../project-api feature/api-refactor
+
+# Run Claude Code in each worktree
+cd ../project-auth && claude    # Terminal 1: Auth work
+cd ../project-api && claude     # Terminal 2: API work
+```
+
+## Troubleshooting
+
+### AI Commands Failing
+
+```bash
+# Check API keys are configured
+cat .env                           # For CLI usage
+
+# Verify model configuration
+task-master models
+
+# Test with different model
+task-master models --set-fallback gpt-4o-mini
+```
+
+### MCP Connection Issues
+
+- Check `.mcp.json` configuration
+- Verify Node.js installation
+- Use `--mcp-debug` flag when starting Claude Code
+- Use CLI as fallback if MCP unavailable
+
+### Task File Sync Issues
+
+```bash
+# Regenerate task files from tasks.json
+task-master generate
+
+# Fix dependency issues
+task-master fix-dependencies
+```
+
+DO NOT RE-INITIALIZE. That will not do anything beyond re-adding the same Taskmaster core files.
+
+## Important Notes
+
+### AI-Powered Operations
+
+These commands make AI calls and may take up to a minute:
+
+- `parse_prd` / `task-master parse-prd`
+- `analyze_project_complexity` / `task-master analyze-complexity`
+- `expand_task` / `task-master expand`
+- `expand_all` / `task-master expand --all`
+- `add_task` / `task-master add-task`
+- `update` / `task-master update`
+- `update_task` / `task-master update-task`
+- `update_subtask` / `task-master update-subtask`
+
+### File Management
+
+- Never manually edit `tasks.json` - use commands instead
+- Never manually edit `.taskmaster/config.json` - use `task-master models`
+- Task markdown files in `tasks/` are auto-generated
+- Run `task-master generate` after manual changes to tasks.json
+
+### Claude Code Session Management
+
+- Use `/clear` frequently to maintain focused context
+- Create custom slash commands for repeated Task Master workflows
+- Configure tool allowlist to streamline permissions
+- Use headless mode for automation: `claude -p "task-master next"`
+
+### Multi-Task Updates
+
+- Use `update --from=<id>` to update multiple future tasks
+- Use `update-task --id=<id>` for single task updates
+- Use `update-subtask --id=<id>` for implementation logging
+
+### Research Mode
+
+- Add `--research` flag for research-based AI enhancement
+- Requires a research model API key like Perplexity (`PERPLEXITY_API_KEY`) in environment
+- Provides more informed task creation and updates
+- Recommended for complex technical tasks
+
+---
+
+_This guide ensures Claude Code has immediate access to Task Master's essential functionality for agentic development workflows._

.taskmaster/docs/research/2025-08-01_do-we-need-to-add-new-commands-or-can-we-just-weap.md

@@ -0,0 +1,153 @@
+---
+title: Research Session
+query: "do we need to add new commands or can we just weaponize the gh cli tool"
+date: 2025-08-01
+time: 2:27:52 p.m.
+timestamp: 2025-08-01T11:27:52.249Z
+exchanges: 3
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** do we need to add new commands or can we just weaponize the gh cli tool
+
+**Response:**
+
+For the implementation of the `task-master git` command suite to automate git workflows (Task 97), it is possible to leverage the existing **GitHub CLI (`gh`) tool** rather than creating entirely new git commands from scratch. The GitHub CLI provides a rich set of commands that cover many GitHub-related operations such as branch management, pull request handling, workflow triggering, and release management, which can be scripted and integrated into your CLI tool[1][2][3][4].
+
+### Key Points Supporting Weaponizing GitHub CLI:
+
+- **Comprehensive GitHub Operations**: The `gh` CLI supports creating branches, managing pull requests, releases, tags, and even triggering and monitoring GitHub Actions workflows. This aligns well with the requirements of automated branch management, commit generation, and PR description generation in Task 97[1][3].
+
+- **Scripting and Automation Friendly**: GitHub CLI commands can be scripted and integrated into custom workflows or CLI tools. You can create aliases or wrap `gh` commands inside your own CLI commands to provide a seamless user experience while relying on the battle-tested GitHub CLI for underlying operations[1][3].
+
+- **Authentication and Permissions**: `gh` uses environment variables like `GH_TOKEN` or `GITHUB_TOKEN` for authentication, which can be securely managed in CI/CD pipelines or local environments. This simplifies integration without needing to implement custom authentication logic[3][4].
+
+- **Extensibility**: If some specific git workflow features are not directly supported by `gh`, you can extend it with custom scripts or combine it with native git commands. This hybrid approach reduces the need to reinvent core git operations while allowing customization[1].
+
+### Considerations for Your Project:
+
+- Since Task 97 requires **automated branch management** (branch creation, validation, switching, cleanup), **intelligent commit generation**, and **PR description generation**, you can implement these by invoking `gh` commands programmatically within your `task-master git` commands.
+
+- For example, branch creation and switching can be done with native git commands wrapped in your CLI, while PR creation and management can be handled via `gh pr create`, `gh pr merge`, etc.
+
+- You may still need to implement some **custom logic** for commit type detection, branch name validation, and PR description generation based on your task metadata, but the underlying git and GitHub operations can be delegated to `gh`.
+
+- This approach aligns with your existing CLI foundation (Task 2) and leverages a well-supported tool, reducing development effort and increasing reliability.
+
+### Summary
+
+You **do not necessarily need to add entirely new git commands** for Task 97. Instead, you can **weaponize the GitHub CLI (`gh`) tool** by wrapping and scripting its commands within your `task-master git` command suite. This will allow you to automate git workflows efficiently, maintain consistency, and leverage GitHub’s API capabilities without reinventing the wheel[1][2][3][4].
+
+If there are gaps in `gh` functionality for your specific workflow needs, you can supplement with native git commands or custom scripts, but the core git and GitHub operations should be handled by `gh` for best results.
+
+---
+
+## Follow-up 1
+
+**Question:** how does this relate to git worktrees? i hear that they get super complicated when trying to implement them.
+
+**Response:**
+
+Git worktrees allow you to have multiple working directories attached to the same Git repository, each checked out to different branches simultaneously. This enables parallel development workflows without the overhead of cloning the repository multiple times or constantly switching branches in a single working directory[2][3].
+
+However, **implementing or managing git worktrees can get complicated** for several reasons:
+
+- **Complexity for users and tooling:** Managing multiple active worktrees requires careful tracking of which directory corresponds to which branch. This can be confusing and error-prone, especially for novices or when many worktrees are in use simultaneously. Mistakes like committing to the wrong branch or working in the wrong directory are common risks[1].
+
+- **Maintenance overhead:** Worktrees accumulate over time and need to be pruned or cleaned up regularly (`git worktree prune`) to avoid clutter and potential confusion. This adds an extra maintenance step to the workflow[1].
+
+- **Syncing and update challenges:** Each worktree is a separate checkout and can become outdated if not regularly updated from the main repository. This can lead to merge conflicts or redundant work if branches diverge significantly[1].
+
+- **Tooling and integration limitations:** Not all Git tools, scripts, or GUIs fully support worktrees or are optimized for them. This can cause inconsistencies or require additional custom tooling to manage worktrees effectively[1].
+
+- **Performance considerations:** Managing multiple worktrees simultaneously can have performance implications, especially in very large repositories, due to the overhead of maintaining multiple checkouts and metadata[1].
+
+In the context of your project, which involves automating git workflows and possibly wrapping or extending git/GitHub CLI commands, these complexities imply:
+
+- If you consider supporting git worktrees in your `task-master git` command suite, you will need to handle the complexity of managing multiple directories and branches carefully.
+
+- You might need to implement additional logic or tooling to track and manage worktrees, avoid user confusion, and ensure synchronization between them.
+
+- Since your project already plans to leverage the GitHub CLI (`gh`) and native git commands, you could integrate worktree commands (`git worktree add`, `git worktree remove`, `git worktree list`) but should be prepared for the added complexity in workflow management and user documentation.
+
+- Custom wrappers or managers (like the one described in [3]) can help reduce friction by automating worktree creation, switching, and cleanup, which might be a useful approach to consider.
+
+Overall, **git worktrees provide powerful parallel branch management but introduce complexity in implementation and user experience** that must be carefully managed through tooling, automation, and clear documentation[1][3][4].
+
+---
+
+**Summary Table of Git Worktree Challenges and Considerations**
+
+| Aspect                  | Description                                                                                   | Implication for Project                                  |
+|-------------------------|-----------------------------------------------------------------------------------------------|----------------------------------------------------------|
+| User Complexity         | Confusing multiple directories and branches                                                  | Need clear UI/UX and safeguards                          |
+| Maintenance Overhead    | Requires pruning and cleanup of stale worktrees                                              | Automate cleanup or provide commands                     |
+| Syncing Issues         | Worktrees can become outdated or diverge                                                     | Implement update checks and sync workflows               |
+| Tooling Support        | Limited support in some Git tools and GUIs                                                  | May require custom tooling or wrappers                   |
+| Performance            | Overhead in large repos with many worktrees                                                 | Monitor and optimize performance                          |
+| Workflow Automation    | Manual worktree management is tedious                                                       | Build custom managers or wrappers to simplify usage     |
+
+---
+
+Given your project’s focus on automating git workflows and leveraging existing CLI tools, **implementing git worktree support is feasible but will require careful design to handle these complexities effectively**. You may want to start with basic worktree commands and incrementally add automation and safeguards as needed.
+
+---
+
+## Follow-up 2
+
+**Question:** since we already have a way to have separated task lists per branch, couldn't we do the same thing for worktrees? each taskmaster list (tag) would have its own worktree based on the name of the tag?
+
+**Response:**
+
+Yes, you can apply a similar approach used for separated task lists per branch to git worktrees by associating each taskmaster list (tag) with its own git worktree named after the tag. This means each tag would correspond to a dedicated worktree directory checked out to a branch or commit related to that tag, enabling isolated parallel work environments for each task list.
+
+### How This Maps to Git Worktrees
+
+- **Git worktrees** allow multiple working directories linked to the same repository, each checked out to a different branch or commit[1][2]. This lets you work on multiple branches simultaneously without switching contexts in a single directory.
+
+- When you create a worktree with `git worktree add <path> [<branch>]`, Git creates a new linked working tree at `<path>`, optionally checking out a specified branch or creating a new one[1][2]. Naming the worktree directory after the tag (taskmaster list) is straightforward and semantically clear.
+
+- This setup mirrors your existing branch-based task list separation but extends it to physical directories, which can improve workflow isolation and reduce context switching.
+
+### Benefits for Your Project
+
+- **Isolated environments per task list/tag:** Each tag’s worktree can have its own checked-out branch, allowing independent development, testing, or review without interference.
+
+- **Parallel workflows:** Developers can switch between worktrees (directories) instead of switching branches in one directory, reducing errors and improving productivity.
+
+- **Automation potential:** Your `task-master git` commands can automate creating, switching, and cleaning up these worktrees based on tags, similar to how you manage branches and task lists.
+
+### Challenges and Considerations
+
+- **Complexity in management:** Git worktrees add complexity in tracking multiple directories and ensuring users operate in the correct one[1]. Your CLI should provide clear commands and feedback to avoid confusion.
+
+- **Maintenance overhead:** Worktrees need pruning and cleanup (`git worktree prune` or `git worktree remove`) to avoid clutter[1]. Automating cleanup in your tool would be beneficial.
+
+- **Syncing and updates:** Each worktree is a separate checkout and can become outdated. Your automation should include commands to update or rebase worktrees as needed.
+
+- **Tooling support:** Not all Git tools or scripts fully support worktrees, so your CLI wrappers should handle edge cases and provide a consistent experience[1][3].
+
+### Practical Implementation Ideas
+
+- When a new tag (taskmaster list) is created, run `git worktree add` to create a new worktree directory named after the tag.
+
+- Store metadata linking tags to worktree paths in your taskmaster configuration to track and manage them.
+
+- Provide commands like `task-master worktree list`, `task-master worktree add <tag>`, and `task-master worktree remove <tag>` to manage these worktrees.
+
+- Integrate with GitHub CLI (`gh`) and native git commands to automate branch creation, PR handling, and syncing within each worktree.
+
+- Consider inspiration from existing tools like [wt](https://github.com/taecontrol/wt) that automate worktree environment setup and teardown[3].
+
+### Summary
+
+Using git worktrees per taskmaster tag is a feasible and potentially powerful extension of your current branch-based task list separation. It offers isolated, parallel working directories aligned with your tags, improving workflow clarity and reducing branch-switching overhead. However, it requires careful tooling and automation to manage complexity, maintenance, and synchronization effectively. Given your project’s focus on automating git workflows and leveraging CLI tools, implementing this feature incrementally with robust user feedback and cleanup commands would be a practical approach.
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-08-01T11:27:52.249Z*

.taskmaster/docs/test-prd.txt

@@ -0,0 +1,8 @@
+Simple Todo App PRD
+
+Create a basic todo list application with the following features:
+1. Add new todos
+2. Mark todos as complete
+3. Delete todos
+
+That's it. Keep it simple.

.taskmaster/docs/tm-core-phase-1.txt

@@ -0,0 +1,343 @@
+# Product Requirements Document: tm-core Package - Parse PRD Feature
+
+## Project Overview
+Create a TypeScript package named `tm-core` at `packages/tm-core` that implements parse-prd functionality using class-based architecture similar to the existing AI providers pattern.
+
+## Design Patterns & Architecture
+
+### Patterns to Apply
+1. **Factory Pattern**: Use for `ProviderFactory` to create AI provider instances
+2. **Strategy Pattern**: Use for `IAIProvider` implementations and `IStorage` implementations
+3. **Facade Pattern**: Use for `TaskMasterCore` as the main API entry point
+4. **Template Method Pattern**: Use for `BaseProvider` abstract class
+5. **Dependency Injection**: Use throughout for testability (pass dependencies via constructor)
+6. **Repository Pattern**: Use for `FileStorage` to abstract data persistence
+
+### Naming Conventions
+- **Files**: kebab-case (e.g., `task-parser.ts`, `file-storage.ts`)
+- **Classes**: PascalCase (e.g., `TaskParser`, `FileStorage`)
+- **Interfaces**: PascalCase with 'I' prefix (e.g., `IStorage`, `IAIProvider`)
+- **Methods**: camelCase (e.g., `parsePRD`, `loadTasks`)
+- **Constants**: UPPER_SNAKE_CASE (e.g., `DEFAULT_MODEL`)
+- **Type aliases**: PascalCase (e.g., `TaskStatus`, `ParseOptions`)
+
+## Exact Folder Structure Required
+```
+packages/tm-core/
+├── src/
+│   ├── index.ts
+│   ├── types/
+│   │   └── index.ts
+│   ├── interfaces/
+│   │   ├── index.ts              # Barrel export
+│   │   ├── storage.interface.ts
+│   │   ├── ai-provider.interface.ts
+│   │   └── configuration.interface.ts
+│   ├── tasks/
+│   │   ├── index.ts              # Barrel export
+│   │   └── task-parser.ts
+│   ├── ai/
+│   │   ├── index.ts              # Barrel export
+│   │   ├── base-provider.ts
+│   │   ├── provider-factory.ts
+│   │   ├── prompt-builder.ts
+│   │   └── providers/
+│   │       ├── index.ts          # Barrel export
+│   │       ├── anthropic-provider.ts
+│   │       ├── openai-provider.ts
+│   │       └── google-provider.ts
+│   ├── storage/
+│   │   ├── index.ts              # Barrel export
+│   │   └── file-storage.ts
+│   ├── config/
+│   │   ├── index.ts              # Barrel export
+│   │   └── config-manager.ts
+│   ├── utils/
+│   │   ├── index.ts              # Barrel export
+│   │   └── id-generator.ts
+│   └── errors/
+│       ├── index.ts              # Barrel export
+│       └── task-master-error.ts
+├── tests/
+│   ├── task-parser.test.ts
+│   ├── integration/
+│   │   └── parse-prd.test.ts
+│   └── mocks/
+│       └── mock-provider.ts
+├── package.json
+├── tsconfig.json
+├── tsup.config.js
+└── jest.config.js
+```
+
+## Specific Implementation Requirements
+
+### 1. Create types/index.ts
+Define these exact TypeScript interfaces:
+- `Task` interface with fields: id, title, description, status, priority, complexity, dependencies, subtasks, metadata, createdAt, updatedAt, source
+- `Subtask` interface with fields: id, title, description, completed
+- `TaskMetadata` interface with fields: parsedFrom, aiProvider, version, tags (optional)
+- Type literals: `TaskStatus` = 'pending' | 'in-progress' | 'completed' | 'blocked'
+- Type literals: `TaskPriority` = 'low' | 'medium' | 'high' | 'critical'
+- Type literals: `TaskComplexity` = 'simple' | 'moderate' | 'complex'
+- `ParseOptions` interface with fields: dryRun (optional), additionalContext (optional), tag (optional), maxTasks (optional)
+
+### 2. Create interfaces/storage.interface.ts
+Define `IStorage` interface with these exact methods:
+- `loadTasks(tag?: string): Promise<Task[]>`
+- `saveTasks(tasks: Task[], tag?: string): Promise<void>`
+- `appendTasks(tasks: Task[], tag?: string): Promise<void>`
+- `updateTask(id: string, task: Partial<Task>, tag?: string): Promise<void>`
+- `deleteTask(id: string, tag?: string): Promise<void>`
+- `exists(tag?: string): Promise<boolean>`
+
+### 3. Create interfaces/ai-provider.interface.ts
+Define `IAIProvider` interface with these exact methods:
+- `generateCompletion(prompt: string, options?: AIOptions): Promise<string>`
+- `calculateTokens(text: string): number`
+- `getName(): string`
+- `getModel(): string`
+
+Define `AIOptions` interface with fields: temperature (optional), maxTokens (optional), systemPrompt (optional)
+
+### 4. Create interfaces/configuration.interface.ts
+Define `IConfiguration` interface with fields:
+- `projectPath: string`
+- `aiProvider: string`
+- `apiKey?: string`
+- `aiOptions?: AIOptions`
+- `mainModel?: string`
+- `researchModel?: string`
+- `fallbackModel?: string`
+- `tasksPath?: string`
+- `enableTags?: boolean`
+
+### 5. Create tasks/task-parser.ts
+Create class `TaskParser` with:
+- Constructor accepting `aiProvider: IAIProvider` and `config: IConfiguration`
+- Private property `promptBuilder: PromptBuilder`
+- Public method `parsePRD(prdPath: string, options: ParseOptions = {}): Promise<Task[]>`
+- Private method `readPRD(prdPath: string): Promise<string>`
+- Private method `extractTasks(aiResponse: string): Partial<Task>[]`
+- Private method `enrichTasks(rawTasks: Partial<Task>[], prdPath: string): Task[]`
+- Apply **Dependency Injection** pattern via constructor
+
+### 6. Create ai/base-provider.ts
+Copy existing base-provider.js and convert to TypeScript abstract class:
+- Abstract class `BaseProvider` implementing `IAIProvider`
+- Protected properties: `apiKey: string`, `model: string`
+- Constructor accepting `apiKey: string` and `options: { model?: string }`
+- Abstract methods matching IAIProvider interface
+- Abstract method `getDefaultModel(): string`
+- Apply **Template Method** pattern for common provider logic
+
+### 7. Create ai/provider-factory.ts
+Create class `ProviderFactory` with:
+- Static method `create(config: { provider: string; apiKey?: string; model?: string }): Promise<IAIProvider>`
+- Switch statement for providers: 'anthropic', 'openai', 'google'
+- Dynamic imports for each provider
+- Throw error for unknown providers
+- Apply **Factory** pattern for creating provider instances
+
+Example implementation structure:
+```typescript
+switch (provider.toLowerCase()) {
+  case 'anthropic':
+    const { AnthropicProvider } = await import('./providers/anthropic-provider.js');
+    return new AnthropicProvider(apiKey, { model });
+}
+```
+
+### 8. Create ai/providers/anthropic-provider.ts
+Create class `AnthropicProvider` extending `BaseProvider`:
+- Import Anthropic SDK: `import { Anthropic } from '@anthropic-ai/sdk'`
+- Private property `client: Anthropic`
+- Implement all abstract methods from BaseProvider
+- Default model: 'claude-3-sonnet-20240229'
+- Handle API errors and wrap with meaningful messages
+
+### 9. Create ai/providers/openai-provider.ts (placeholder)
+Create class `OpenAIProvider` extending `BaseProvider`:
+- Import OpenAI SDK when implemented
+- For now, throw error: "OpenAI provider not yet implemented"
+
+### 10. Create ai/providers/google-provider.ts (placeholder)
+Create class `GoogleProvider` extending `BaseProvider`:
+- Import Google Generative AI SDK when implemented
+- For now, throw error: "Google provider not yet implemented"
+
+### 11. Create ai/prompt-builder.ts
+Create class `PromptBuilder` with:
+- Method `buildParsePrompt(prdContent: string, options: ParseOptions = {}): string`
+- Method `buildExpandPrompt(task: string, context?: string): string`
+- Use template literals for prompt construction
+- Include specific JSON format instructions in prompts
+
+### 9. Create storage/file-storage.ts
+Create class `FileStorage` implementing `IStorage`:
+- Private property `basePath: string` set to `{projectPath}/.taskmaster`
+- Constructor accepting `projectPath: string`
+- Private method `getTasksPath(tag?: string): string` returning correct path based on tag
+- Private method `ensureDirectory(dir: string): Promise<void>`
+- Implement all IStorage methods
+- Handle ENOENT errors by returning empty arrays
+- Use JSON format with structure: `{ tasks: Task[], metadata: { version: string, lastModified: string } }`
+- Apply **Repository** pattern for data access abstraction
+
+### 10. Create config/config-manager.ts
+Create class `ConfigManager`:
+- Private property `config: IConfiguration`
+- Constructor accepting `options: Partial<IConfiguration>`
+- Use Zod for validation with schema matching IConfiguration
+- Method `get<K extends keyof IConfiguration>(key: K): IConfiguration[K]`
+- Method `getAll(): IConfiguration`
+- Method `validate(): boolean`
+- Default values: projectPath = process.cwd(), aiProvider = 'anthropic', enableTags = true
+
+### 11. Create utils/id-generator.ts
+Export functions:
+- `generateTaskId(index: number = 0): string` returning format `task_{timestamp}_{index}_{random}`
+- `generateSubtaskId(parentId: string, index: number = 0): string` returning format `{parentId}_sub_{index}_{random}`
+
+### 16. Create src/index.ts
+Create main class `TaskMasterCore`:
+- Private properties: `config: ConfigManager`, `storage: IStorage`, `aiProvider?: IAIProvider`, `parser?: TaskParser`
+- Constructor accepting `options: Partial<IConfiguration>`
+- Method `initialize(): Promise<void>` for lazy loading
+- Method `parsePRD(prdPath: string, options: ParseOptions = {}): Promise<Task[]>`
+- Method `getTasks(tag?: string): Promise<Task[]>`
+- Apply **Facade** pattern to provide simple API over complex subsystems
+
+Export:
+- Class `TaskMasterCore`
+- Function `createTaskMaster(options: Partial<IConfiguration>): TaskMasterCore`
+- All types from './types'
+- All interfaces from './interfaces/*'
+
+Import statements should use kebab-case:
+```typescript
+import { TaskParser } from './tasks/task-parser';
+import { FileStorage } from './storage/file-storage';
+import { ConfigManager } from './config/config-manager';
+import { ProviderFactory } from './ai/provider-factory';
+```
+
+### 17. Configure package.json
+Create package.json with:
+- name: "@task-master/core"
+- version: "0.1.0"
+- type: "module"
+- main: "./dist/index.js"
+- module: "./dist/index.mjs"
+- types: "./dist/index.d.ts"
+- exports map for proper ESM/CJS support
+- scripts: build (tsup), dev (tsup --watch), test (jest), typecheck (tsc --noEmit)
+- dependencies: zod@^3.23.8
+- peerDependencies: @anthropic-ai/sdk, openai, @google/generative-ai
+- devDependencies: typescript, tsup, jest, ts-jest, @types/node, @types/jest
+
+### 18. Configure TypeScript
+Create tsconfig.json with:
+- target: "ES2022"
+- module: "ESNext"
+- strict: true (with all strict flags enabled)
+- declaration: true
+- outDir: "./dist"
+- rootDir: "./src"
+
+### 19. Configure tsup
+Create tsup.config.js with:
+- entry: ['src/index.ts']
+- format: ['cjs', 'esm']
+- dts: true
+- sourcemap: true
+- clean: true
+- external: AI provider SDKs
+
+### 20. Configure Jest
+Create jest.config.js with:
+- preset: 'ts-jest'
+- testEnvironment: 'node'
+- Coverage threshold: 80% for all metrics
+
+## Build Process
+1. Use tsup to compile TypeScript to both CommonJS and ESM
+2. Generate .d.ts files for TypeScript consumers
+3. Output to dist/ directory
+4. Ensure tree-shaking works properly
+
+## Testing Requirements
+- Create unit tests for TaskParser in tests/task-parser.test.ts
+- Create MockProvider class in tests/mocks/mock-provider.ts for testing without API calls
+- Test error scenarios (file not found, invalid JSON, etc.)
+- Create integration test in tests/integration/parse-prd.test.ts
+- Follow kebab-case naming for all test files
+
+## Success Criteria
+- TypeScript compilation with zero errors
+- No use of 'any' type
+- All interfaces properly exported
+- Compatible with existing tasks.json format
+- Feature flag support via USE_TM_CORE environment variable
+
+## Import/Export Conventions
+- Use named exports for all classes and interfaces
+- Use barrel exports (index.ts) in each directory
+- Import types/interfaces with type-only imports: `import type { Task } from '../types'`
+- Group imports in order: Node built-ins, external packages, internal packages, relative imports
+- Use .js extension in import paths for ESM compatibility
+
+## Error Handling Patterns
+- Create custom error classes in `src/errors/` directory
+- All public methods should catch and wrap errors with context
+- Use error codes for different error types (e.g., 'FILE_NOT_FOUND', 'PARSE_ERROR')
+- Never expose internal implementation details in error messages
+- Log errors to console.error only in development mode
+
+## Barrel Exports Content
+
+### interfaces/index.ts
+```typescript
+export type { IStorage } from './storage.interface';
+export type { IAIProvider, AIOptions } from './ai-provider.interface';
+export type { IConfiguration } from './configuration.interface';
+```
+
+### tasks/index.ts
+```typescript
+export { TaskParser } from './task-parser';
+```
+
+### ai/index.ts
+```typescript
+export { BaseProvider } from './base-provider';
+export { ProviderFactory } from './provider-factory';
+export { PromptBuilder } from './prompt-builder';
+```
+
+### ai/providers/index.ts
+```typescript
+export { AnthropicProvider } from './anthropic-provider';
+export { OpenAIProvider } from './openai-provider';
+export { GoogleProvider } from './google-provider';
+```
+
+### storage/index.ts
+```typescript
+export { FileStorage } from './file-storage';
+```
+
+### config/index.ts
+```typescript
+export { ConfigManager } from './config-manager';
+```
+
+### utils/index.ts
+```typescript
+export { generateTaskId, generateSubtaskId } from './id-generator';
+```
+
+### errors/index.ts
+```typescript
+export { TaskMasterError } from './task-master-error';
+```

.taskmaster/reports/task-complexity-report.json

@@ -1,373 +1,21 @@
 {
 	"meta": {
-		"generatedAt": "2025-05-27T16:34:53.088Z",
+		"generatedAt": "2025-08-02T14:28:59.851Z",
 		"tasksAnalyzed": 1,
-		"totalTasks": 84,
-		"analysisCount": 45,
+		"totalTasks": 93,
+		"analysisCount": 1,
 		"thresholdScore": 5,
 		"projectName": "Taskmaster",
-		"usedResearch": true
+		"usedResearch": false
 	},
 	"complexityAnalysis": [
 		{
 			"taskId": 24,
 			"taskTitle": "Implement AI-Powered Test Generation Command",
-			"complexityScore": 7,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "Break down the implementation of the AI-powered test generation command into detailed subtasks covering: command structure setup, AI prompt engineering, test file generation logic, integration with Claude API, and comprehensive error handling.",
-			"reasoning": "This task involves complex integration with an AI service (Claude), requires sophisticated prompt engineering, and needs to generate structured code files. The existing 3 subtasks are a good start but could be expanded to include more detailed steps for AI integration, error handling, and test file formatting."
-		},
-		{
-			"taskId": 26,
-			"taskTitle": "Implement Context Foundation for AI Operations",
-			"complexityScore": 6,
-			"recommendedSubtasks": 4,
-			"expansionPrompt": "The current 4 subtasks for implementing the context foundation appear comprehensive. Consider if any additional subtasks are needed for testing, documentation, or integration with existing systems.",
-			"reasoning": "This task involves creating a foundation for context integration with several well-defined components. The existing 4 subtasks cover the main implementation areas (context-file flag, cursor rules integration, context extraction utility, and command handler updates). The complexity is moderate as it requires careful integration with existing systems but has clear requirements."
-		},
-		{
-			"taskId": 27,
-			"taskTitle": "Implement Context Enhancements for AI Operations",
-			"complexityScore": 7,
-			"recommendedSubtasks": 4,
-			"expansionPrompt": "The current 4 subtasks for implementing context enhancements appear well-structured. Consider if any additional subtasks are needed for testing, documentation, or performance optimization.",
-			"reasoning": "This task builds upon the foundation from Task #26 and adds more sophisticated context handling features. The 4 existing subtasks cover the main implementation areas (code context extraction, task history context, PRD context integration, and context formatting). The complexity is higher than the foundation task due to the need for intelligent context selection and optimization."
-		},
-		{
-			"taskId": 28,
-			"taskTitle": "Implement Advanced ContextManager System",
-			"complexityScore": 8,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the advanced ContextManager system appear comprehensive. Consider if any additional subtasks are needed for testing, documentation, or backward compatibility with previous context implementations.",
-			"reasoning": "This task represents the most complex phase of the context implementation, requiring a sophisticated class design, optimization algorithms, and integration with multiple systems. The 5 existing subtasks cover the core implementation areas, but the complexity is high due to the need for intelligent context prioritization, token management, and performance monitoring."
-		},
-		{
-			"taskId": 40,
-			"taskTitle": "Implement 'plan' Command for Task Implementation Planning",
-			"complexityScore": 5,
-			"recommendedSubtasks": 4,
-			"expansionPrompt": "The current 4 subtasks for implementing the 'plan' command appear well-structured. Consider if any additional subtasks are needed for testing, documentation, or integration with existing task management workflows.",
-			"reasoning": "This task involves creating a new command that leverages AI to generate implementation plans. The existing 4 subtasks cover the main implementation areas (retrieving task content, generating plans with AI, formatting in XML, and error handling). The complexity is moderate as it builds on existing patterns for task updates but requires careful AI integration."
-		},
-		{
-			"taskId": 41,
-			"taskTitle": "Implement Visual Task Dependency Graph in Terminal",
-			"complexityScore": 8,
-			"recommendedSubtasks": 10,
-			"expansionPrompt": "The current 10 subtasks for implementing the visual task dependency graph appear comprehensive. Consider if any additional subtasks are needed for performance optimization with large graphs or additional visualization options.",
-			"reasoning": "This task involves creating a sophisticated visualization system for terminal display, which is inherently complex due to layout algorithms, ASCII/Unicode rendering, and handling complex dependency relationships. The 10 existing subtasks cover all major aspects of implementation, from CLI interface to accessibility features."
-		},
-		{
-			"taskId": 42,
-			"taskTitle": "Implement MCP-to-MCP Communication Protocol",
-			"complexityScore": 9,
-			"recommendedSubtasks": 8,
-			"expansionPrompt": "The current 8 subtasks for implementing the MCP-to-MCP communication protocol appear well-structured. Consider if any additional subtasks are needed for security hardening, performance optimization, or comprehensive documentation.",
-			"reasoning": "This task involves designing and implementing a complex communication protocol between different MCP tools and servers. It requires sophisticated adapter patterns, client-server architecture, and handling of multiple operational modes. The complexity is very high due to the need for standardization, security, and backward compatibility."
-		},
-		{
-			"taskId": 44,
-			"taskTitle": "Implement Task Automation with Webhooks and Event Triggers",
-			"complexityScore": 8,
-			"recommendedSubtasks": 7,
-			"expansionPrompt": "The current 7 subtasks for implementing task automation with webhooks appear comprehensive. Consider if any additional subtasks are needed for security testing, rate limiting implementation, or webhook monitoring tools.",
-			"reasoning": "This task involves creating a sophisticated event system with webhooks for integration with external services. The complexity is high due to the need for secure authentication, reliable delivery mechanisms, and handling of various webhook formats and protocols. The existing subtasks cover the main implementation areas but security and monitoring could be emphasized more."
-		},
-		{
-			"taskId": 45,
-			"taskTitle": "Implement GitHub Issue Import Feature",
-			"complexityScore": 6,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the GitHub issue import feature appear well-structured. Consider if any additional subtasks are needed for handling GitHub API rate limiting, caching, or supporting additional issue metadata.",
-			"reasoning": "This task involves integrating with the GitHub API to import issues as tasks. The complexity is moderate as it requires API authentication, data mapping, and error handling. The existing 5 subtasks cover the main implementation areas from design to end-to-end implementation."
-		},
-		{
-			"taskId": 46,
-			"taskTitle": "Implement ICE Analysis Command for Task Prioritization",
-			"complexityScore": 7,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the ICE analysis command appear comprehensive. Consider if any additional subtasks are needed for visualization of ICE scores or integration with other prioritization methods.",
-			"reasoning": "This task involves creating an AI-powered analysis system for task prioritization using the ICE methodology. The complexity is high due to the need for sophisticated scoring algorithms, AI integration, and report generation. The existing subtasks cover the main implementation areas from algorithm design to integration with existing systems."
-		},
-		{
-			"taskId": 47,
-			"taskTitle": "Enhance Task Suggestion Actions Card Workflow",
-			"complexityScore": 6,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for enhancing the task suggestion actions card workflow appear well-structured. Consider if any additional subtasks are needed for user testing, accessibility improvements, or performance optimization.",
-			"reasoning": "This task involves redesigning the UI workflow for task expansion and management. The complexity is moderate as it requires careful UX design and state management but builds on existing components. The 6 existing subtasks cover the main implementation areas from design to testing."
-		},
-		{
-			"taskId": 48,
-			"taskTitle": "Refactor Prompts into Centralized Structure",
-			"complexityScore": 4,
-			"recommendedSubtasks": 3,
-			"expansionPrompt": "The current 3 subtasks for refactoring prompts into a centralized structure appear appropriate. Consider if any additional subtasks are needed for prompt versioning, documentation, or testing.",
-			"reasoning": "This task involves a straightforward refactoring to improve code organization. The complexity is relatively low as it primarily involves moving code rather than creating new functionality. The 3 existing subtasks cover the main implementation areas from directory structure to integration."
-		},
-		{
-			"taskId": 49,
-			"taskTitle": "Implement Code Quality Analysis Command",
 			"complexityScore": 8,
 			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for implementing the code quality analysis command appear comprehensive. Consider if any additional subtasks are needed for performance optimization with large codebases or integration with existing code quality tools.",
-			"reasoning": "This task involves creating a sophisticated code analysis system with pattern recognition, best practice verification, and AI-powered recommendations. The complexity is high due to the need for code parsing, complex analysis algorithms, and integration with AI services. The existing subtasks cover the main implementation areas from algorithm design to user interface."
-		},
-		{
-			"taskId": 50,
-			"taskTitle": "Implement Test Coverage Tracking System by Task",
-			"complexityScore": 9,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the test coverage tracking system appear well-structured. Consider if any additional subtasks are needed for integration with CI/CD systems, performance optimization, or visualization tools.",
-			"reasoning": "This task involves creating a complex system that maps test coverage to specific tasks and subtasks. The complexity is very high due to the need for sophisticated data structures, integration with coverage tools, and AI-powered test generation. The existing subtasks are comprehensive and cover the main implementation areas from data structure design to AI integration."
-		},
-		{
-			"taskId": 51,
-			"taskTitle": "Implement Perplexity Research Command",
-			"complexityScore": 6,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the Perplexity research command appear comprehensive. Consider if any additional subtasks are needed for caching optimization, result formatting, or integration with other research tools.",
-			"reasoning": "This task involves creating a new command that integrates with the Perplexity AI API for research. The complexity is moderate as it requires API integration, context extraction, and result formatting. The 5 existing subtasks cover the main implementation areas from API client to caching system."
-		},
-		{
-			"taskId": 52,
-			"taskTitle": "Implement Task Suggestion Command for CLI",
-			"complexityScore": 6,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing the task suggestion command appear well-structured. Consider if any additional subtasks are needed for suggestion quality evaluation, user feedback collection, or integration with existing task workflows.",
-			"reasoning": "This task involves creating a new CLI command that generates contextually relevant task suggestions using AI. The complexity is moderate as it requires AI integration, context collection, and interactive CLI interfaces. The existing subtasks cover the main implementation areas from data collection to user interface."
-		},
-		{
-			"taskId": 53,
-			"taskTitle": "Implement Subtask Suggestion Feature for Parent Tasks",
-			"complexityScore": 6,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for implementing the subtask suggestion feature appear comprehensive. Consider if any additional subtasks are needed for suggestion quality metrics, user feedback collection, or performance optimization.",
-			"reasoning": "This task involves creating a feature that suggests contextually relevant subtasks for parent tasks. The complexity is moderate as it builds on existing task management systems but requires sophisticated AI integration and context analysis. The 6 existing subtasks cover the main implementation areas from validation to testing."
-		},
-		{
-			"taskId": 55,
-			"taskTitle": "Implement Positional Arguments Support for CLI Commands",
-			"complexityScore": 5,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing positional arguments support appear well-structured. Consider if any additional subtasks are needed for backward compatibility testing, documentation updates, or user experience improvements.",
-			"reasoning": "This task involves modifying the command parsing logic to support positional arguments alongside the existing flag-based syntax. The complexity is moderate as it requires careful handling of different argument styles and edge cases. The 5 existing subtasks cover the main implementation areas from analysis to documentation."
-		},
-		{
-			"taskId": 57,
-			"taskTitle": "Enhance Task-Master CLI User Experience and Interface",
-			"complexityScore": 7,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for enhancing the CLI user experience appear comprehensive. Consider if any additional subtasks are needed for accessibility testing, internationalization, or performance optimization.",
-			"reasoning": "This task involves a significant overhaul of the CLI interface to improve user experience. The complexity is high due to the breadth of changes (logging, visual elements, interactive components, etc.) and the need for consistent design across all commands. The 6 existing subtasks cover the main implementation areas from log management to help systems."
-		},
-		{
-			"taskId": 60,
-			"taskTitle": "Implement Mentor System with Round-Table Discussion Feature",
-			"complexityScore": 8,
-			"recommendedSubtasks": 7,
-			"expansionPrompt": "The current 7 subtasks for implementing the mentor system appear well-structured. Consider if any additional subtasks are needed for mentor personality consistency, discussion quality evaluation, or performance optimization with multiple mentors.",
-			"reasoning": "This task involves creating a sophisticated mentor simulation system with round-table discussions. The complexity is high due to the need for personality simulation, complex LLM integration, and structured discussion management. The 7 existing subtasks cover the main implementation areas from architecture to testing."
-		},
-		{
-			"taskId": 62,
-			"taskTitle": "Add --simple Flag to Update Commands for Direct Text Input",
-			"complexityScore": 4,
-			"recommendedSubtasks": 8,
-			"expansionPrompt": "The current 8 subtasks for implementing the --simple flag appear comprehensive. Consider if any additional subtasks are needed for user experience testing or documentation updates.",
-			"reasoning": "This task involves adding a simple flag option to bypass AI processing for updates. The complexity is relatively low as it primarily involves modifying existing command handlers and adding a flag. The 8 existing subtasks are very detailed and cover all aspects of implementation from command parsing to testing."
-		},
-		{
-			"taskId": 63,
-			"taskTitle": "Add pnpm Support for the Taskmaster Package",
-			"complexityScore": 5,
-			"recommendedSubtasks": 8,
-			"expansionPrompt": "The current 8 subtasks for adding pnpm support appear comprehensive. Consider if any additional subtasks are needed for CI/CD integration, performance comparison, or documentation updates.",
-			"reasoning": "This task involves ensuring the package works correctly with pnpm as an alternative package manager. The complexity is moderate as it requires careful testing of installation processes and scripts across different environments. The 8 existing subtasks cover all major aspects from documentation to binary verification."
-		},
-		{
-			"taskId": 64,
-			"taskTitle": "Add Yarn Support for Taskmaster Installation",
-			"complexityScore": 5,
-			"recommendedSubtasks": 9,
-			"expansionPrompt": "The current 9 subtasks for adding Yarn support appear comprehensive. Consider if any additional subtasks are needed for performance testing, CI/CD integration, or compatibility with different Yarn versions.",
-			"reasoning": "This task involves ensuring the package works correctly with Yarn as an alternative package manager. The complexity is moderate as it requires careful testing of installation processes and scripts across different environments. The 9 existing subtasks are very detailed and cover all aspects from configuration to testing."
-		},
-		{
-			"taskId": 65,
-			"taskTitle": "Add Bun Support for Taskmaster Installation",
-			"complexityScore": 6,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for adding Bun support appear well-structured. Consider if any additional subtasks are needed for handling Bun-specific issues, performance testing, or documentation updates.",
-			"reasoning": "This task involves adding support for the newer Bun package manager. The complexity is slightly higher than the other package manager tasks due to Bun's differences from Node.js and potential compatibility issues. The 6 existing subtasks cover the main implementation areas from research to documentation."
-		},
-		{
-			"taskId": 67,
-			"taskTitle": "Add CLI JSON output and Cursor keybindings integration",
-			"complexityScore": 5,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing JSON output and Cursor keybindings appear well-structured. Consider if any additional subtasks are needed for testing across different operating systems, documentation updates, or user experience improvements.",
-			"reasoning": "This task involves two distinct features: adding JSON output to CLI commands and creating a keybindings installation command. The complexity is moderate as it requires careful handling of different output formats and OS-specific file paths. The 5 existing subtasks cover the main implementation areas for both features."
-		},
-		{
-			"taskId": 68,
-			"taskTitle": "Ability to create tasks without parsing PRD",
-			"complexityScore": 3,
-			"recommendedSubtasks": 2,
-			"expansionPrompt": "The current 2 subtasks for implementing task creation without PRD appear appropriate. Consider if any additional subtasks are needed for validation, error handling, or integration with existing task management workflows.",
-			"reasoning": "This task involves a relatively simple modification to allow task creation without requiring a PRD document. The complexity is low as it primarily involves creating a form interface and saving functionality. The 2 existing subtasks cover the main implementation areas of UI design and data saving."
-		},
-		{
-			"taskId": 72,
-			"taskTitle": "Implement PDF Generation for Project Progress and Dependency Overview",
-			"complexityScore": 7,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for implementing PDF generation appear comprehensive. Consider if any additional subtasks are needed for handling large projects, additional visualization options, or integration with existing reporting tools.",
-			"reasoning": "This task involves creating a feature to generate PDF reports of project progress and dependency visualization. The complexity is high due to the need for PDF generation, data collection, and visualization integration. The 6 existing subtasks cover the main implementation areas from library selection to export options."
-		},
-		{
-			"taskId": 75,
-			"taskTitle": "Integrate Google Search Grounding for Research Role",
-			"complexityScore": 5,
-			"recommendedSubtasks": 4,
-			"expansionPrompt": "The current 4 subtasks for integrating Google Search Grounding appear well-structured. Consider if any additional subtasks are needed for testing with different query types, error handling, or performance optimization.",
-			"reasoning": "This task involves updating the AI service layer to enable Google Search Grounding for research roles. The complexity is moderate as it requires careful integration with the existing AI service architecture and conditional logic. The 4 existing subtasks cover the main implementation areas from service layer modification to testing."
-		},
-		{
-			"taskId": 76,
-			"taskTitle": "Develop E2E Test Framework for Taskmaster MCP Server (FastMCP over stdio)",
-			"complexityScore": 8,
-			"recommendedSubtasks": 7,
-			"expansionPrompt": "The current 7 subtasks for developing the E2E test framework appear comprehensive. Consider if any additional subtasks are needed for test result reporting, CI/CD integration, or performance benchmarking.",
-			"reasoning": "This task involves creating a sophisticated end-to-end testing framework for the MCP server. The complexity is high due to the need for subprocess management, protocol handling, and robust test case definition. The 7 existing subtasks cover the main implementation areas from architecture to documentation."
-		},
-		{
-			"taskId": 77,
-			"taskTitle": "Implement AI Usage Telemetry for Taskmaster (with external analytics endpoint)",
-			"complexityScore": 7,
-			"recommendedSubtasks": 18,
-			"expansionPrompt": "The current 18 subtasks for implementing AI usage telemetry appear very comprehensive. Consider if any additional subtasks are needed for security hardening, privacy compliance, or user feedback collection.",
-			"reasoning": "This task involves creating a telemetry system to track AI usage metrics. The complexity is high due to the need for secure data transmission, comprehensive data collection, and integration across multiple commands. The 18 existing subtasks are extremely detailed and cover all aspects of implementation from core utility to provider-specific updates."
-		},
-		{
-			"taskId": 80,
-			"taskTitle": "Implement Unique User ID Generation and Storage During Installation",
-			"complexityScore": 4,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "The current 5 subtasks for implementing unique user ID generation appear well-structured. Consider if any additional subtasks are needed for privacy compliance, security auditing, or integration with the telemetry system.",
-			"reasoning": "This task involves generating and storing a unique user identifier during installation. The complexity is relatively low as it primarily involves UUID generation and configuration file management. The 5 existing subtasks cover the main implementation areas from script structure to documentation."
-		},
-		{
-			"taskId": 81,
-			"taskTitle": "Task #81: Implement Comprehensive Local Telemetry System with Future Server Integration Capability",
-			"complexityScore": 8,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "The current 6 subtasks for implementing the comprehensive local telemetry system appear well-structured. Consider if any additional subtasks are needed for data migration, storage optimization, or visualization tools.",
-			"reasoning": "This task involves expanding the telemetry system to capture additional metrics and implement local storage with future server integration capability. The complexity is high due to the breadth of data collection, storage requirements, and privacy considerations. The 6 existing subtasks cover the main implementation areas from data collection to user-facing benefits."
-		},
-		{
-			"taskId": 82,
-			"taskTitle": "Update supported-models.json with token limit fields",
-			"complexityScore": 3,
-			"recommendedSubtasks": 1,
-			"expansionPrompt": "This task appears straightforward enough to be implemented without further subtasks. Focus on researching accurate token limit values for each model and ensuring backward compatibility.",
-			"reasoning": "This task involves a simple update to the supported-models.json file to include new token limit fields. The complexity is low as it primarily involves research and data entry. No subtasks are necessary as the task is well-defined and focused."
-		},
-		{
-			"taskId": 83,
-			"taskTitle": "Update config-manager.js defaults and getters",
-			"complexityScore": 4,
-			"recommendedSubtasks": 1,
-			"expansionPrompt": "This task appears straightforward enough to be implemented without further subtasks. Focus on updating the DEFAULTS object and related getter functions while maintaining backward compatibility.",
-			"reasoning": "This task involves updating the config-manager.js module to replace maxTokens with more specific token limit fields. The complexity is relatively low as it primarily involves modifying existing code rather than creating new functionality. No subtasks are necessary as the task is well-defined and focused."
-		},
-		{
-			"taskId": 84,
-			"taskTitle": "Implement token counting utility",
-			"complexityScore": 5,
-			"recommendedSubtasks": 1,
-			"expansionPrompt": "This task appears well-defined enough to be implemented without further subtasks. Focus on implementing accurate token counting for different models and proper fallback mechanisms.",
-			"reasoning": "This task involves creating a utility function to count tokens for different AI models. The complexity is moderate as it requires integration with the tiktoken library and handling different tokenization schemes. No subtasks are necessary as the task is well-defined and focused."
-		},
-		{
-			"taskId": 69,
-			"taskTitle": "Enhance Analyze Complexity for Specific Task IDs",
-			"complexityScore": 7,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "Break down the task 'Enhance Analyze Complexity for Specific Task IDs' into 6 subtasks focusing on: 1) Core logic modification to accept ID parameters, 2) Report merging functionality, 3) CLI interface updates, 4) MCP tool integration, 5) Documentation updates, and 6) Comprehensive testing across all components.",
-			"reasoning": "This task involves modifying existing functionality across multiple components (core logic, CLI, MCP) with complex logic for filtering tasks and merging reports. The implementation requires careful handling of different parameter combinations and edge cases. The task has interdependent components that need to work together seamlessly, and the report merging functionality adds significant complexity."
-		},
-		{
-			"taskId": 70,
-			"taskTitle": "Implement 'diagram' command for Mermaid diagram generation",
-			"complexityScore": 6,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "Break down the 'diagram' command implementation into 5 subtasks: 1) Command interface and parameter handling, 2) Task data extraction and transformation to Mermaid syntax, 3) Diagram rendering with status color coding, 4) Output formatting and file export functionality, and 5) Error handling and edge case management.",
-			"reasoning": "This task requires implementing a new feature rather than modifying existing code, which reduces complexity from integration challenges. However, it involves working with visualization logic, dependency mapping, and multiple output formats. The color coding based on status and handling of dependency relationships adds moderate complexity. The task is well-defined but requires careful attention to diagram formatting and error handling."
-		},
-		{
-			"taskId": 85,
-			"taskTitle": "Update ai-services-unified.js for dynamic token limits",
-			"complexityScore": 7,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "Break down the update of ai-services-unified.js for dynamic token limits into subtasks such as: (1) Import and integrate the token counting utility, (2) Refactor _unifiedServiceRunner to calculate and enforce dynamic token limits, (3) Update error handling for token limit violations, (4) Add and verify logging for token usage, (5) Write and execute tests for various prompt and model scenarios.",
-			"reasoning": "This task involves significant code changes to a core function, integration of a new utility, dynamic logic for multiple models, and robust error handling. It also requires comprehensive testing for edge cases and integration, making it moderately complex and best managed by splitting into focused subtasks."
-		},
-		{
-			"taskId": 87,
-			"taskTitle": "Implement validation and error handling",
-			"complexityScore": 5,
-			"recommendedSubtasks": 4,
-			"expansionPrompt": "Decompose this task into: (1) Add validation logic for model and config loading, (2) Implement error handling and fallback mechanisms, (3) Enhance logging and reporting for token usage, (4) Develop helper functions for configuration suggestions and improvements.",
-			"reasoning": "This task is primarily about adding validation, error handling, and logging. While important for robustness, the logic is straightforward and can be modularized into a few clear subtasks."
-		},
-		{
-			"taskId": 89,
-			"taskTitle": "Introduce Prioritize Command with Enhanced Priority Levels",
-			"complexityScore": 6,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "Expand this task into: (1) Implement the prioritize command with all required flags and shorthands, (2) Update CLI output and help documentation for new priority levels, (3) Ensure backward compatibility with existing commands, (4) Add error handling for invalid inputs, (5) Write and run tests for all command scenarios.",
-			"reasoning": "This CLI feature requires command parsing, updating internal logic for new priority levels, documentation, and robust error handling. The complexity is moderate due to the need for backward compatibility and comprehensive testing."
-		},
-		{
-			"taskId": 90,
-			"taskTitle": "Implement Subtask Progress Analyzer and Reporting System",
-			"complexityScore": 8,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "Break down the analyzer implementation into: (1) Design and implement progress tracking logic, (2) Develop status validation and issue detection, (3) Build the reporting system with multiple output formats, (4) Integrate analyzer with the existing task management system, (5) Optimize for performance and scalability, (6) Write unit, integration, and performance tests.",
-			"reasoning": "This is a complex, multi-faceted feature involving data analysis, reporting, integration, and performance optimization. It touches many parts of the system and requires careful design, making it one of the most complex tasks in the list."
-		},
-		{
-			"taskId": 91,
-			"taskTitle": "Implement Move Command for Tasks and Subtasks",
-			"complexityScore": 7,
-			"recommendedSubtasks": 5,
-			"expansionPrompt": "Expand this task into: (1) Implement move logic for tasks and subtasks, (2) Handle edge cases (invalid ids, non-existent parents, circular dependencies), (3) Update CLI to support move command with flags, (4) Ensure data integrity and update relationships, (5) Write and execute tests for various move scenarios.",
-			"reasoning": "Moving tasks and subtasks requires careful handling of hierarchical data, edge cases, and data integrity. The command must be robust and user-friendly, necessitating multiple focused subtasks for safe implementation."
-		},
-		{
-			"taskId": 92,
-			"taskTitle": "Add Global Joke Flag to All CLI Commands",
-			"complexityScore": 8,
-			"recommendedSubtasks": 7,
-			"expansionPrompt": "Break down the implementation of the global --joke flag into the following subtasks: (1) Update CLI foundation to support global flags, (2) Develop the joke-service module with joke management and category support, (3) Integrate joke output into existing output utilities, (4) Update all CLI commands for joke flag compatibility, (5) Add configuration options for joke categories and custom jokes, (6) Implement comprehensive testing (flag recognition, output, content, integration, performance, regression), (7) Update documentation and usage examples.",
-			"reasoning": "This task requires changes across the CLI foundation, output utilities, all command modules, and configuration management. It introduces a new service module, global flag handling, and output logic that must not interfere with existing features (including JSON output). The need for robust testing and backward compatibility further increases complexity. The scope spans multiple code areas and requires careful integration, justifying a high complexity score and a detailed subtask breakdown to manage risk and ensure maintainability.[2][3][5]"
-		},
-		{
-			"taskId": 94,
-			"taskTitle": "Implement Standalone 'research' CLI Command for AI-Powered Queries",
-			"complexityScore": 7,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "Break down the implementation of the 'research' CLI command into logical subtasks covering command registration, parameter handling, context gathering, AI service integration, output formatting, and documentation.",
-			"reasoning": "This task has moderate to high complexity (7/10) due to multiple interconnected components: CLI argument parsing, integration with AI services, context gathering from various sources, and output formatting with different modes. The cyclomatic complexity would be significant with multiple decision paths for handling different flags and options. The task requires understanding existing patterns and extending the codebase in a consistent manner, suggesting the need for careful decomposition into manageable subtasks."
-		},
-		{
-			"taskId": 86,
-			"taskTitle": "Implement GitHub Issue Export Feature",
-			"complexityScore": 9,
-			"recommendedSubtasks": 10,
-			"expansionPrompt": "Break down the implementation of the GitHub Issue Export Feature into detailed subtasks covering: command structure and CLI integration, GitHub API client development, authentication and error handling, task-to-issue mapping logic, content formatting and markdown conversion, bidirectional linking and metadata management, extensible architecture and adapter interfaces, configuration and settings management, documentation, and comprehensive testing (unit, integration, edge cases, performance).",
-			"reasoning": "This task involves designing and implementing a robust, extensible export system with deep integration into GitHub, including bidirectional workflows, complex data mapping, error handling, and support for future platforms. The requirements span CLI design, API integration, content transformation, metadata management, extensibility, configuration, and extensive testing. The breadth and depth of these requirements, along with the need for maintainability and future extensibility, place this task at a high complexity level. Breaking it into at least 10 subtasks will ensure each major component and concern is addressed systematically, reducing risk and improving quality."
+			"expansionPrompt": "Expand task 24 'Implement AI-Powered Test Generation Command' into 6 subtasks, focusing on: 1) Command structure implementation, 2) AI prompt engineering for test generation, 3) Test file generation and output, 4) Framework-specific template implementation, 5) MCP tool integration, and 6) Documentation and help system integration. Include detailed implementation steps, dependencies, and testing approaches for each subtask.",
+			"reasoning": "This task has high complexity due to several challenging aspects: 1) AI integration requiring sophisticated prompt engineering, 2) Test generation across multiple frameworks, 3) File system operations with proper error handling, 4) MCP tool integration, 5) Complex configuration requirements, and 6) Framework-specific template generation. The task already has 5 subtasks but could benefit from reorganization based on the updated implementation details in the info blocks, particularly around framework support and configuration."
 		}
 	]
 }

.taskmaster/reports/task-complexity-report_cc-kiro-hooks.json

@@ -0,0 +1,93 @@
+{
+	"meta": {
+		"generatedAt": "2025-07-22T09:41:10.517Z",
+		"tasksAnalyzed": 10,
+		"totalTasks": 10,
+		"analysisCount": 10,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": false
+	},
+	"complexityAnalysis": [
+		{
+			"taskId": 1,
+			"taskTitle": "Implement Task Integration Layer (TIL) Core",
+			"complexityScore": 8,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down the TIL Core implementation into distinct components: hook registration system, task lifecycle management, event coordination, state persistence layer, and configuration validation. Each subtask should focus on a specific architectural component with clear interfaces and testable boundaries.",
+			"reasoning": "This is a foundational component with multiple complex subsystems including event-driven architecture, API integration, state management, and configuration validation. The existing 5 subtasks are well-structured and appropriately sized."
+		},
+		{
+			"taskId": 2,
+			"taskTitle": "Develop Dependency Monitor with Taskmaster MCP Integration",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide the dependency monitor into: dependency graph data structure implementation, circular dependency detection algorithm, Taskmaster MCP integration layer, and real-time notification system. Focus on performance optimization for large graphs and efficient caching strategies.",
+			"reasoning": "Complex graph algorithms and real-time monitoring require careful implementation. The task involves sophisticated data structures, algorithm design, and API integration with performance constraints."
+		},
+		{
+			"taskId": 3,
+			"taskTitle": "Build Execution Manager with Priority Queue and Parallel Execution",
+			"complexityScore": 8,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Structure the execution manager into: priority queue implementation, resource conflict detection system, parallel execution coordinator, timeout and cancellation handler, and execution history persistence layer. Each component should handle specific aspects of concurrent task management.",
+			"reasoning": "Managing concurrent execution with resource conflicts, priority scheduling, and persistence is highly complex. Requires careful synchronization, error handling, and performance optimization."
+		},
+		{
+			"taskId": 4,
+			"taskTitle": "Implement Safety Manager with Configurable Constraints and Emergency Controls",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Break down into: constraint validation engine, emergency control system (stop/pause), user approval workflow implementation, and safety monitoring/audit logging. Each subtask should address specific safety aspects with fail-safe mechanisms.",
+			"reasoning": "Safety systems require careful design with multiple fail-safes. The task involves validation logic, real-time controls, workflow management, and comprehensive logging."
+		},
+		{
+			"taskId": 5,
+			"taskTitle": "Develop Event-Based Hook Processor",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Organize into: file system event integration, Git/VCS event listeners, build system event connectors, and event filtering/debouncing mechanism. Focus on modular event source integration with configurable processing pipelines.",
+			"reasoning": "While conceptually straightforward, integrating multiple event sources with proper filtering and performance optimization requires careful implementation. Each event source has unique characteristics."
+		},
+		{
+			"taskId": 6,
+			"taskTitle": "Implement Prompt-Based Hook Processor with AI Integration",
+			"complexityScore": 7,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide into: prompt interception mechanism, NLP-based task suggestion engine, context injection system, and conversation-based status updater. Each component should handle specific aspects of AI conversation integration.",
+			"reasoning": "AI integration with prompt analysis and dynamic context injection is complex. Requires understanding of conversation flow, relevance scoring, and seamless integration with existing systems."
+		},
+		{
+			"taskId": 7,
+			"taskTitle": "Create Update-Based Hook Processor for Automatic Progress Tracking",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Structure as: code change monitor, acceptance criteria validator, dependency update propagator, and conflict detection/resolution system. Focus on accurate progress tracking and automated validation logic.",
+			"reasoning": "Automatic progress tracking requires integration with version control and intelligent analysis of code changes. Conflict detection and dependency propagation add complexity."
+		},
+		{
+			"taskId": 8,
+			"taskTitle": "Develop Real-Time Automation Dashboard and User Controls",
+			"complexityScore": 7,
+			"recommendedSubtasks": 5,
+			"expansionPrompt": "Break down into: WebSocket real-time communication layer, interactive dependency graph visualization, task queue and status displays, user control interfaces, and analytics/charting components. Each UI component should be modular and reusable.",
+			"reasoning": "Building a responsive real-time dashboard with complex visualizations and interactive controls is challenging. Requires careful state management, performance optimization, and user experience design."
+		},
+		{
+			"taskId": 9,
+			"taskTitle": "Integrate Kiro IDE and Taskmaster MCP with Core Services",
+			"complexityScore": 8,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Organize into: KiroHookAdapter implementation, TaskmasterMCPAdapter development, error handling and retry logic layer, and IDE UI component integration. Focus on robust adapter patterns and comprehensive error recovery.",
+			"reasoning": "End-to-end integration of multiple systems with different architectures is highly complex. Requires careful adapter design, extensive error handling, and thorough testing across all integration points."
+		},
+		{
+			"taskId": 10,
+			"taskTitle": "Implement Configuration Management and Safety Profiles",
+			"complexityScore": 6,
+			"recommendedSubtasks": 4,
+			"expansionPrompt": "Divide into: visual configuration editor UI, JSON Schema validation engine, import/export functionality, and version control integration. Each component should provide intuitive configuration management with robust validation.",
+			"reasoning": "While technically less complex than core systems, building an intuitive configuration editor with validation, versioning, and import/export requires careful UI/UX design and robust data handling."
+		}
+	]
+}

.taskmaster/state.json

@@ -1,6 +1,6 @@
 {
 	"currentTag": "master",
-	"lastSwitched": "2025-06-14T20:37:15.456Z",
+	"lastSwitched": "2025-08-01T14:09:25.838Z",
 	"branchTagMapping": {
 		"v017-adds": "v017-adds",
 		"next": "next"

CHANGELOG.md

@@ -1,5 +1,759 @@
 # task-master-ai
 
+## 0.26.0
+
+### Minor Changes
+
+- [#1133](https://github.com/eyaltoledano/claude-task-master/pull/1133) [`df26c65`](https://github.com/eyaltoledano/claude-task-master/commit/df26c65632000874a73504963b08f18c46283144) Thanks [@neonwatty](https://github.com/neonwatty)! - Restore Taskmaster claude-code commands and move clear commands under /remove to avoid collision with the claude-code /clear command.
+
+- [#1163](https://github.com/eyaltoledano/claude-task-master/pull/1163) [`37af0f1`](https://github.com/eyaltoledano/claude-task-master/commit/37af0f191227a68d119b7f89a377bf932ee3ac66) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Gemini CLI provider with codebase-aware task generation
+
+  Added automatic codebase analysis for Gemini CLI provider in parse-prd, and analyze-complexity, add-task, udpate-task, update, update-subtask commands
+  When using Gemini CLI as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1165](https://github.com/eyaltoledano/claude-task-master/pull/1165) [`c4f92f6`](https://github.com/eyaltoledano/claude-task-master/commit/c4f92f6a0aee3435c56eb8d27d9aa9204284833e) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add configurable codebase analysis feature flag with multiple configuration sources
+
+  Users can now control whether codebase analysis features (Claude Code and Gemini CLI integration) are enabled through environment variables, MCP configuration, or project config files.
+
+  Priority order: .env > MCP session env > .taskmaster/config.json.
+
+  Set `TASKMASTER_ENABLE_CODEBASE_ANALYSIS=false` in `.env` to disable codebase analysis prompts and tool integration.
+
+- [#1135](https://github.com/eyaltoledano/claude-task-master/pull/1135) [`8783708`](https://github.com/eyaltoledano/claude-task-master/commit/8783708e5e3389890a78fcf685d3da0580e73b3f) Thanks [@mm-parthy](https://github.com/mm-parthy)! - feat(move): improve cross-tag move UX and safety
+  - CLI: print "Next Steps" tips after cross-tag moves that used --ignore-dependencies (validate/fix guidance)
+  - CLI: show dedicated help block on ID collisions (destination tag already has the ID)
+  - Core: add structured suggestions to TASK_ALREADY_EXISTS errors
+  - MCP: map ID collision errors to TASK_ALREADY_EXISTS and include suggestions
+  - Tests: cover MCP options, error suggestions, CLI tips printing, and integration error payload suggestions
+
+  ***
+
+- [#1162](https://github.com/eyaltoledano/claude-task-master/pull/1162) [`4dad2fd`](https://github.com/eyaltoledano/claude-task-master/commit/4dad2fd613ceac56a65ae9d3c1c03092b8860ac9) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code and Google CLI integration with automatic codebase analysis for task operations
+
+  When using Claude Code as the AI provider, task management commands now automatically analyze your codebase before generating or updating tasks. This provides more accurate, context-aware implementation details that align with your project's existing architecture and patterns.
+
+  Commands contextualised:
+  - add-task
+  - update-subtask
+  - update-task
+  - update
+
+### Patch Changes
+
+- [#1135](https://github.com/eyaltoledano/claude-task-master/pull/1135) [`8783708`](https://github.com/eyaltoledano/claude-task-master/commit/8783708e5e3389890a78fcf685d3da0580e73b3f) Thanks [@mm-parthy](https://github.com/mm-parthy)! - docs(move): clarify cross-tag move docs; deprecate "force"; add explicit --with-dependencies/--ignore-dependencies examples
+
+## 0.26.0-rc.1
+
+### Minor Changes
+
+- [#1165](https://github.com/eyaltoledano/claude-task-master/pull/1165) [`c4f92f6`](https://github.com/eyaltoledano/claude-task-master/commit/c4f92f6a0aee3435c56eb8d27d9aa9204284833e) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add configurable codebase analysis feature flag with multiple configuration sources
+
+  Users can now control whether codebase analysis features (Claude Code and Gemini CLI integration) are enabled through environment variables, MCP configuration, or project config files.
+
+  Priority order: .env > MCP session env > .taskmaster/config.json.
+
+  Set `TASKMASTER_ENABLE_CODEBASE_ANALYSIS=false` in `.env` to disable codebase analysis prompts and tool integration.
+
+## 0.26.0-rc.0
+
+### Minor Changes
+
+- [#1163](https://github.com/eyaltoledano/claude-task-master/pull/1163) [`37af0f1`](https://github.com/eyaltoledano/claude-task-master/commit/37af0f191227a68d119b7f89a377bf932ee3ac66) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Gemini CLI provider with codebase-aware task generation
+
+  Added automatic codebase analysis for Gemini CLI provider in parse-prd, and analyze-complexity, add-task, udpate-task, update, update-subtask commands
+  When using Gemini CLI as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1135](https://github.com/eyaltoledano/claude-task-master/pull/1135) [`8783708`](https://github.com/eyaltoledano/claude-task-master/commit/8783708e5e3389890a78fcf685d3da0580e73b3f) Thanks [@mm-parthy](https://github.com/mm-parthy)! - feat(move): improve cross-tag move UX and safety
+  - CLI: print "Next Steps" tips after cross-tag moves that used --ignore-dependencies (validate/fix guidance)
+  - CLI: show dedicated help block on ID collisions (destination tag already has the ID)
+  - Core: add structured suggestions to TASK_ALREADY_EXISTS errors
+  - MCP: map ID collision errors to TASK_ALREADY_EXISTS and include suggestions
+  - Tests: cover MCP options, error suggestions, CLI tips printing, and integration error payload suggestions
+
+  ***
+
+- [#1162](https://github.com/eyaltoledano/claude-task-master/pull/1162) [`4dad2fd`](https://github.com/eyaltoledano/claude-task-master/commit/4dad2fd613ceac56a65ae9d3c1c03092b8860ac9) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code and Google CLI integration with automatic codebase analysis for task operations
+
+  When using Claude Code as the AI provider, task management commands now automatically analyze your codebase before generating or updating tasks. This provides more accurate, context-aware implementation details that align with your project's existing architecture and patterns.
+
+  Commands contextualised:
+  - add-task
+  - update-subtask
+  - update-task
+  - update
+
+### Patch Changes
+
+- [#1135](https://github.com/eyaltoledano/claude-task-master/pull/1135) [`8783708`](https://github.com/eyaltoledano/claude-task-master/commit/8783708e5e3389890a78fcf685d3da0580e73b3f) Thanks [@mm-parthy](https://github.com/mm-parthy)! - docs(move): clarify cross-tag move docs; deprecate "force"; add explicit --with-dependencies/--ignore-dependencies examples
+
+## 0.25.1
+
+### Patch Changes
+
+- [#1152](https://github.com/eyaltoledano/claude-task-master/pull/1152) [`8933557`](https://github.com/eyaltoledano/claude-task-master/commit/89335578ffffc65504b2055c0c85aa7521e5e79b) Thanks [@ben-vargas](https://github.com/ben-vargas)! - fix(claude-code): prevent crash/hang when the optional `@anthropic-ai/claude-code` SDK is missing by guarding `AbortError instanceof` checks and adding explicit SDK presence checks in `doGenerate`/`doStream`. Also bump the optional dependency to `^1.0.88` for improved export consistency.
+
+  Related to JSON truncation handling in #920; this change addresses a separate error-path crash reported in #1142.
+
+- [#1151](https://github.com/eyaltoledano/claude-task-master/pull/1151) [`db720a9`](https://github.com/eyaltoledano/claude-task-master/commit/db720a954d390bb44838cd021b8813dde8f3d8de) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Temporarily disable streaming for improved model compatibility - will be re-enabled in upcoming release
+
+## 0.25.0
+
+### Minor Changes
+
+- [#1088](https://github.com/eyaltoledano/claude-task-master/pull/1088) [`04e11b5`](https://github.com/eyaltoledano/claude-task-master/commit/04e11b5e828597c0ba5b82ca7d5fb6f933e4f1e8) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Add cross-tag task movement functionality for organizing tasks across different contexts.
+
+  This feature enables moving tasks between different tags (contexts) in your project, making it easier to organize work across different branches, environments, or project phases.
+
+  ## CLI Usage Examples
+
+  Move a single task from one tag to another:
+
+  ```bash
+  # Move task 5 from backlog tag to in-progress tag
+  task-master move --from=5 --from-tag=backlog --to-tag=feature-1
+
+  # Move task with its dependencies
+  task-master move --from=5 --from-tag=backlog --to-tag=feature-2 --with-dependencies
+
+  # Move task without checking dependencies
+  task-master move --from=5 --from-tag=backlog --to-tag=bug-3 --ignore-dependencies
+  ```
+
+  Move multiple tasks at once:
+
+  ```bash
+  # Move multiple tasks between tags
+  task-master move --from=5,6,7 --from-tag=backlog --to-tag=bug-4 --with-dependencies
+  ```
+
+- [#1040](https://github.com/eyaltoledano/claude-task-master/pull/1040) [`fc47714`](https://github.com/eyaltoledano/claude-task-master/commit/fc477143400fd11d953727bf1b4277af5ad308d1) Thanks [@DomVidja](https://github.com/DomVidja)! - "Add Kilo Code profile integration with custom modes and MCP configuration"
+
+- [#1054](https://github.com/eyaltoledano/claude-task-master/pull/1054) [`782728f`](https://github.com/eyaltoledano/claude-task-master/commit/782728ff95aa2e3b766d48273b57f6c6753e8573) Thanks [@martincik](https://github.com/martincik)! - Add compact mode --compact / -c flag to the `tm list` CLI command
+  - outputs tasks in a minimal, git-style one-line format. This reduces verbose output from ~30+ lines of dashboards and tables to just 1 line per task, making it much easier to quickly scan available tasks.
+    - Git-style format: ID STATUS TITLE (PRIORITY) → DEPS
+    - Color-coded status, priority, and dependencies
+    - Smart title truncation and dependency abbreviation
+    - Subtask support with indentation
+    - Full backward compatibility with existing list options
+
+- [#1048](https://github.com/eyaltoledano/claude-task-master/pull/1048) [`e3ed4d7`](https://github.com/eyaltoledano/claude-task-master/commit/e3ed4d7c14b56894d7da675eb2b757423bea8f9d) Thanks [@joedanz](https://github.com/joedanz)! - Add CLI & MCP progress tracking for parse-prd command.
+
+- [#1124](https://github.com/eyaltoledano/claude-task-master/pull/1124) [`95640dc`](https://github.com/eyaltoledano/claude-task-master/commit/95640dcde87ce7879858c0a951399fb49f3b6397) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add support for ollama `gpt-oss:20b` and `gpt-oss:120b`
+
+- [#1123](https://github.com/eyaltoledano/claude-task-master/pull/1123) [`311b243`](https://github.com/eyaltoledano/claude-task-master/commit/311b2433e23c771c8d3a4d3f5ac577302b8321e5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Remove `clear` Taskmaster claude code commands since they were too close to the claude-code clear command
+
+### Patch Changes
+
+- [#1131](https://github.com/eyaltoledano/claude-task-master/pull/1131) [`3dee60d`](https://github.com/eyaltoledano/claude-task-master/commit/3dee60dc3d566e3cff650accb30f994b8bb3a15e) Thanks [@joedanz](https://github.com/joedanz)! - Update Cursor one-click install link to new URL format
+
+- [#1088](https://github.com/eyaltoledano/claude-task-master/pull/1088) [`04e11b5`](https://github.com/eyaltoledano/claude-task-master/commit/04e11b5e828597c0ba5b82ca7d5fb6f933e4f1e8) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Fix `add-tag --from-branch` command error where `projectRoot` was not properly referenced
+
+  The command was failing with "projectRoot is not defined" error because the code was directly referencing `projectRoot` instead of `context.projectRoot` in the git repository checks. This fix corrects the variable references to use the proper context object.
+
+## 0.25.0-rc.0
+
+### Minor Changes
+
+- [#1088](https://github.com/eyaltoledano/claude-task-master/pull/1088) [`04e11b5`](https://github.com/eyaltoledano/claude-task-master/commit/04e11b5e828597c0ba5b82ca7d5fb6f933e4f1e8) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Add cross-tag task movement functionality for organizing tasks across different contexts.
+
+  This feature enables moving tasks between different tags (contexts) in your project, making it easier to organize work across different branches, environments, or project phases.
+
+  ## CLI Usage Examples
+
+  Move a single task from one tag to another:
+
+  ```bash
+  # Move task 5 from backlog tag to in-progress tag
+  task-master move --from=5 --from-tag=backlog --to-tag=feature-1
+
+  # Move task with its dependencies
+  task-master move --from=5 --from-tag=backlog --to-tag=feature-2 --with-dependencies
+
+  # Move task without checking dependencies
+  task-master move --from=5 --from-tag=backlog --to-tag=bug-3 --ignore-dependencies
+  ```
+
+  Move multiple tasks at once:
+
+  ```bash
+  # Move multiple tasks between tags
+  task-master move --from=5,6,7 --from-tag=backlog --to-tag=bug-4 --with-dependencies
+  ```
+
+- [#1040](https://github.com/eyaltoledano/claude-task-master/pull/1040) [`fc47714`](https://github.com/eyaltoledano/claude-task-master/commit/fc477143400fd11d953727bf1b4277af5ad308d1) Thanks [@DomVidja](https://github.com/DomVidja)! - "Add Kilo Code profile integration with custom modes and MCP configuration"
+
+- [#1054](https://github.com/eyaltoledano/claude-task-master/pull/1054) [`782728f`](https://github.com/eyaltoledano/claude-task-master/commit/782728ff95aa2e3b766d48273b57f6c6753e8573) Thanks [@martincik](https://github.com/martincik)! - Add compact mode --compact / -c flag to the `tm list` CLI command
+  - outputs tasks in a minimal, git-style one-line format. This reduces verbose output from ~30+ lines of dashboards and tables to just 1 line per task, making it much easier to quickly scan available tasks.
+    - Git-style format: ID STATUS TITLE (PRIORITY) → DEPS
+    - Color-coded status, priority, and dependencies
+    - Smart title truncation and dependency abbreviation
+    - Subtask support with indentation
+    - Full backward compatibility with existing list options
+
+- [#1048](https://github.com/eyaltoledano/claude-task-master/pull/1048) [`e3ed4d7`](https://github.com/eyaltoledano/claude-task-master/commit/e3ed4d7c14b56894d7da675eb2b757423bea8f9d) Thanks [@joedanz](https://github.com/joedanz)! - Add CLI & MCP progress tracking for parse-prd command.
+
+- [#1124](https://github.com/eyaltoledano/claude-task-master/pull/1124) [`95640dc`](https://github.com/eyaltoledano/claude-task-master/commit/95640dcde87ce7879858c0a951399fb49f3b6397) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add support for ollama `gpt-oss:20b` and `gpt-oss:120b`
+
+- [#1123](https://github.com/eyaltoledano/claude-task-master/pull/1123) [`311b243`](https://github.com/eyaltoledano/claude-task-master/commit/311b2433e23c771c8d3a4d3f5ac577302b8321e5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Remove `clear` Taskmaster claude code commands since they were too close to the claude-code clear command
+
+### Patch Changes
+
+- [#1131](https://github.com/eyaltoledano/claude-task-master/pull/1131) [`3dee60d`](https://github.com/eyaltoledano/claude-task-master/commit/3dee60dc3d566e3cff650accb30f994b8bb3a15e) Thanks [@joedanz](https://github.com/joedanz)! - Update Cursor one-click install link to new URL format
+
+- [#1088](https://github.com/eyaltoledano/claude-task-master/pull/1088) [`04e11b5`](https://github.com/eyaltoledano/claude-task-master/commit/04e11b5e828597c0ba5b82ca7d5fb6f933e4f1e8) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Fix `add-tag --from-branch` command error where `projectRoot` was not properly referenced
+
+  The command was failing with "projectRoot is not defined" error because the code was directly referencing `projectRoot` instead of `context.projectRoot` in the git repository checks. This fix corrects the variable references to use the proper context object.
+
+## 0.24.0
+
+### Minor Changes
+
+- [#1098](https://github.com/eyaltoledano/claude-task-master/pull/1098) [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code provider with codebase-aware task generation
+  - Added automatic codebase analysis for Claude Code provider in `parse-prd`, `expand-task`, and `analyze-complexity` commands
+  - When using Claude Code as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  - Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1105](https://github.com/eyaltoledano/claude-task-master/pull/1105) [`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add GPT-5 support with proper parameter handling
+  - Added GPT-5 model to supported models configuration with SWE score of 0.749
+
+- [#1091](https://github.com/eyaltoledano/claude-task-master/pull/1091) [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code subagent support with task-orchestrator, task-executor, and task-checker
+
+  ## New Claude Code Agents
+
+  Added specialized agents for Claude Code users to enable parallel task execution, intelligent task orchestration, and quality assurance:
+
+  ### task-orchestrator
+
+  Coordinates and manages the execution of Task Master tasks with intelligent dependency analysis:
+  - Analyzes task dependencies to identify parallelizable work
+  - Deploys multiple task-executor agents for concurrent execution
+  - Monitors task completion and updates the dependency graph
+  - Automatically identifies and starts newly unblocked tasks
+
+  ### task-executor
+
+  Handles the actual implementation of individual tasks:
+  - Executes specific tasks identified by the orchestrator
+  - Works on concrete implementation rather than planning
+  - Updates task status and logs progress
+  - Can work in parallel with other executors on independent tasks
+
+  ### task-checker
+
+  Verifies that completed tasks meet their specifications:
+  - Reviews tasks marked as 'review' status
+  - Validates implementation against requirements
+  - Runs tests and checks for best practices
+  - Ensures quality before marking tasks as 'done'
+
+  ## Installation
+
+  When using the Claude profile (`task-master rules add claude`), the agents are automatically installed to `.claude/agents/` directory.
+
+  ## Usage Example
+
+  ```bash
+  # In Claude Code, after initializing a project with tasks:
+
+  # Use task-orchestrator to analyze and coordinate work
+  # The orchestrator will:
+  # 1. Check task dependencies
+  # 2. Identify tasks that can run in parallel
+  # 3. Deploy executors for available work
+  # 4. Monitor progress and deploy new executors as tasks complete
+
+  # Use task-executor for specific task implementation
+  # When the orchestrator identifies task 2.3 needs work:
+  # The executor will implement that specific task
+  ```
+
+  ## Benefits
+  - **Parallel Execution**: Multiple independent tasks can be worked on simultaneously
+  - **Intelligent Scheduling**: Orchestrator understands dependencies and optimizes execution order
+  - **Separation of Concerns**: Planning (orchestrator) is separated from execution (executor)
+  - **Progress Tracking**: Real-time updates as tasks are completed
+  - **Automatic Progression**: As tasks complete, newly unblocked tasks are automatically started
+
+### Patch Changes
+
+- [#1094](https://github.com/eyaltoledano/claude-task-master/pull/1094) [`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix expand task generating unrelated generic subtasks
+
+  Fixed an issue where `task-master expand` would generate generic authentication-related subtasks regardless of the parent task context when using complexity reports. The expansion now properly includes the parent task details alongside any expansion guidance.
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix scope-up/down prompts to include all required fields for better AI model compatibility
+  - Added missing `priority` field to scope adjustment prompts to prevent validation errors with Claude-code and other models
+  - Ensures generated JSON includes all fields required by the schema
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP scope-up/down tools not finding tasks
+  - Fixed task ID parsing in MCP layer - now correctly converts string IDs to numbers
+  - scope_up_task and scope_down_task MCP tools now work properly
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve AI provider compatibility for JSON generation
+  - Fixed schema compatibility issues between Perplexity and OpenAI o3 models
+  - Removed nullable/default modifiers from Zod schemas for broader compatibility
+  - Added automatic JSON repair for malformed AI responses (handles cases like missing array values)
+  - Perplexity now uses JSON mode for more reliable structured output
+  - Post-processing handles default values separately from schema validation
+
+## 0.24.0-rc.2
+
+### Minor Changes
+
+- [#1105](https://github.com/eyaltoledano/claude-task-master/pull/1105) [`75c514c`](https://github.com/eyaltoledano/claude-task-master/commit/75c514cf5b2ca47f95c0ad7fa92654a4f2a6be4b) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add GPT-5 support with proper parameter handling
+  - Added GPT-5 model to supported models configuration with SWE score of 0.749
+
+## 0.24.0-rc.1
+
+### Minor Changes
+
+- [#1093](https://github.com/eyaltoledano/claude-task-master/pull/1093) [`36468f3`](https://github.com/eyaltoledano/claude-task-master/commit/36468f3c93faf4035a5c442ccbc501077f3440f1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhanced Claude Code provider with codebase-aware task generation
+  - Added automatic codebase analysis for Claude Code provider in `parse-prd`, `expand-task`, and `analyze-complexity` commands
+  - When using Claude Code as the AI provider, Task Master now instructs the AI to analyze the project structure, existing implementations, and patterns before generating tasks or subtasks
+  - Tasks and subtasks generated by Claude Code are now informed by actual codebase analysis, resulting in more accurate and contextual outputs
+
+- [#1091](https://github.com/eyaltoledano/claude-task-master/pull/1091) [`4bb6370`](https://github.com/eyaltoledano/claude-task-master/commit/4bb63706b80c28d1b2d782ba868a725326f916c7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code subagent support with task-orchestrator, task-executor, and task-checker
+
+  ## New Claude Code Agents
+
+  Added specialized agents for Claude Code users to enable parallel task execution, intelligent task orchestration, and quality assurance:
+
+  ### task-orchestrator
+
+  Coordinates and manages the execution of Task Master tasks with intelligent dependency analysis:
+  - Analyzes task dependencies to identify parallelizable work
+  - Deploys multiple task-executor agents for concurrent execution
+  - Monitors task completion and updates the dependency graph
+  - Automatically identifies and starts newly unblocked tasks
+
+  ### task-executor
+
+  Handles the actual implementation of individual tasks:
+  - Executes specific tasks identified by the orchestrator
+  - Works on concrete implementation rather than planning
+  - Updates task status and logs progress
+  - Can work in parallel with other executors on independent tasks
+
+  ### task-checker
+
+  Verifies that completed tasks meet their specifications:
+  - Reviews tasks marked as 'review' status
+  - Validates implementation against requirements
+  - Runs tests and checks for best practices
+  - Ensures quality before marking tasks as 'done'
+
+  ## Installation
+
+  When using the Claude profile (`task-master rules add claude`), the agents are automatically installed to `.claude/agents/` directory.
+
+  ## Usage Example
+
+  ```bash
+  # In Claude Code, after initializing a project with tasks:
+
+  # Use task-orchestrator to analyze and coordinate work
+  # The orchestrator will:
+  # 1. Check task dependencies
+  # 2. Identify tasks that can run in parallel
+  # 3. Deploy executors for available work
+  # 4. Monitor progress and deploy new executors as tasks complete
+
+  # Use task-executor for specific task implementation
+  # When the orchestrator identifies task 2.3 needs work:
+  # The executor will implement that specific task
+  ```
+
+  ## Benefits
+  - **Parallel Execution**: Multiple independent tasks can be worked on simultaneously
+  - **Intelligent Scheduling**: Orchestrator understands dependencies and optimizes execution order
+  - **Separation of Concerns**: Planning (orchestrator) is separated from execution (executor)
+  - **Progress Tracking**: Real-time updates as tasks are completed
+  - **Automatic Progression**: As tasks complete, newly unblocked tasks are automatically started
+
+### Patch Changes
+
+- [#1094](https://github.com/eyaltoledano/claude-task-master/pull/1094) [`4357af3`](https://github.com/eyaltoledano/claude-task-master/commit/4357af3f13859d90bca8795215e5d5f1d94abde5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix expand task generating unrelated generic subtasks
+
+  Fixed an issue where `task-master expand` would generate generic authentication-related subtasks regardless of the parent task context when using complexity reports. The expansion now properly includes the parent task details alongside any expansion guidance.
+
+## 0.23.1-rc.0
+
+### Patch Changes
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix scope-up/down prompts to include all required fields for better AI model compatibility
+  - Added missing `priority` field to scope adjustment prompts to prevent validation errors with Claude-code and other models
+  - Ensures generated JSON includes all fields required by the schema
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP scope-up/down tools not finding tasks
+  - Fixed task ID parsing in MCP layer - now correctly converts string IDs to numbers
+  - scope_up_task and scope_down_task MCP tools now work properly
+
+- [#1079](https://github.com/eyaltoledano/claude-task-master/pull/1079) [`e495b2b`](https://github.com/eyaltoledano/claude-task-master/commit/e495b2b55950ee54c7d0f1817d8530e28bd79c05) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve AI provider compatibility for JSON generation
+  - Fixed schema compatibility issues between Perplexity and OpenAI o3 models
+  - Removed nullable/default modifiers from Zod schemas for broader compatibility
+  - Added automatic JSON repair for malformed AI responses (handles cases like missing array values)
+  - Perplexity now uses JSON mode for more reliable structured output
+  - Post-processing handles default values separately from schema validation
+
+## 0.23.0
+
+### Minor Changes
+
+- [#1064](https://github.com/eyaltoledano/claude-task-master/pull/1064) [`53903f1`](https://github.com/eyaltoledano/claude-task-master/commit/53903f1e8eee23ac512eb13a6d81d8cbcfe658cb) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add new `scope-up` and `scope-down` commands for dynamic task complexity adjustment
+
+  This release introduces two powerful new commands that allow you to dynamically adjust the complexity of your tasks and subtasks without recreating them from scratch.
+
+  **New CLI Commands:**
+  - `task-master scope-up` - Increase task complexity (add more detail, requirements, or implementation steps)
+  - `task-master scope-down` - Decrease task complexity (simplify, remove unnecessary details, or streamline)
+
+  **Key Features:**
+  - **Multiple tasks**: Support comma-separated IDs to adjust multiple tasks at once (`--id=5,7,12`)
+  - **Strength levels**: Choose adjustment intensity with `--strength=light|regular|heavy` (defaults to regular)
+  - **Custom prompts**: Use `--prompt` flag to specify exactly how you want tasks adjusted
+  - **MCP integration**: Available as `scope_up_task` and `scope_down_task` tools in Cursor and other MCP environments
+  - **Smart context**: AI considers your project context and task dependencies when making adjustments
+
+  **Usage Examples:**
+
+  ```bash
+  # Make a task more detailed
+  task-master scope-up --id=5
+
+  # Simplify multiple tasks with light touch
+  task-master scope-down --id=10,11,12 --strength=light
+
+  # Custom adjustment with specific instructions
+  task-master scope-up --id=7 --prompt="Add more error handling and edge cases"
+  ```
+
+  **Why use this?**
+  - **Iterative refinement**: Adjust task complexity as your understanding evolves
+  - **Project phase adaptation**: Scale tasks up for implementation, down for planning
+  - **Team coordination**: Adjust complexity based on team member experience levels
+  - **Milestone alignment**: Fine-tune tasks to match project phase requirements
+
+  Perfect for agile workflows where task requirements change as you learn more about the problem space.
+
+### Patch Changes
+
+- [#1063](https://github.com/eyaltoledano/claude-task-master/pull/1063) [`2ae6e7e`](https://github.com/eyaltoledano/claude-task-master/commit/2ae6e7e6be3605c3c4d353f34666e54750dba973) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix for tasks not found when using string IDs
+
+- [#1049](https://github.com/eyaltoledano/claude-task-master/pull/1049) [`45a14c3`](https://github.com/eyaltoledano/claude-task-master/commit/45a14c323d21071c15106335e89ad1f4a20976ab) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix tag-specific complexity report detection in expand command
+
+  The expand command now correctly finds and uses tag-specific complexity reports (e.g., `task-complexity-report_feature-xyz.json`) when operating in a tag context. Previously, it would always look for the generic `task-complexity-report.json` file due to a default value in the CLI option definition.
+
+## 0.23.0-rc.2
+
+### Minor Changes
+
+- [#1064](https://github.com/eyaltoledano/claude-task-master/pull/1064) [`53903f1`](https://github.com/eyaltoledano/claude-task-master/commit/53903f1e8eee23ac512eb13a6d81d8cbcfe658cb) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add new `scope-up` and `scope-down` commands for dynamic task complexity adjustment
+
+  This release introduces two powerful new commands that allow you to dynamically adjust the complexity of your tasks and subtasks without recreating them from scratch.
+
+  **New CLI Commands:**
+  - `task-master scope-up` - Increase task complexity (add more detail, requirements, or implementation steps)
+  - `task-master scope-down` - Decrease task complexity (simplify, remove unnecessary details, or streamline)
+
+  **Key Features:**
+  - **Multiple tasks**: Support comma-separated IDs to adjust multiple tasks at once (`--id=5,7,12`)
+  - **Strength levels**: Choose adjustment intensity with `--strength=light|regular|heavy` (defaults to regular)
+  - **Custom prompts**: Use `--prompt` flag to specify exactly how you want tasks adjusted
+  - **MCP integration**: Available as `scope_up_task` and `scope_down_task` tools in Cursor and other MCP environments
+  - **Smart context**: AI considers your project context and task dependencies when making adjustments
+
+  **Usage Examples:**
+
+  ```bash
+  # Make a task more detailed
+  task-master scope-up --id=5
+
+  # Simplify multiple tasks with light touch
+  task-master scope-down --id=10,11,12 --strength=light
+
+  # Custom adjustment with specific instructions
+  task-master scope-up --id=7 --prompt="Add more error handling and edge cases"
+  ```
+
+  **Why use this?**
+  - **Iterative refinement**: Adjust task complexity as your understanding evolves
+  - **Project phase adaptation**: Scale tasks up for implementation, down for planning
+  - **Team coordination**: Adjust complexity based on team member experience levels
+  - **Milestone alignment**: Fine-tune tasks to match project phase requirements
+
+  Perfect for agile workflows where task requirements change as you learn more about the problem space.
+
+## 0.22.1-rc.1
+
+### Patch Changes
+
+- [#1069](https://github.com/eyaltoledano/claude-task-master/pull/1069) [`72ca68e`](https://github.com/eyaltoledano/claude-task-master/commit/72ca68edeb870ff7a3b0d2d632e09dae921dc16a) Thanks [@eyaltoledano](https://github.com/eyaltoledano)! - Add new `scope-up` and `scope-down` commands for dynamic task complexity adjustment
+
+  This release introduces two powerful new commands that allow you to dynamically adjust the complexity of your tasks and subtasks without recreating them from scratch.
+
+  **New CLI Commands:**
+  - `task-master scope-up` - Increase task complexity (add more detail, requirements, or implementation steps)
+  - `task-master scope-down` - Decrease task complexity (simplify, remove unnecessary details, or streamline)
+
+  **Key Features:**
+  - **Multiple tasks**: Support comma-separated IDs to adjust multiple tasks at once (`--id=5,7,12`)
+  - **Strength levels**: Choose adjustment intensity with `--strength=light|regular|heavy` (defaults to regular)
+  - **Custom prompts**: Use `--prompt` flag to specify exactly how you want tasks adjusted
+  - **MCP integration**: Available as `scope_up_task` and `scope_down_task` tools in Cursor and other MCP environments
+  - **Smart context**: AI considers your project context and task dependencies when making adjustments
+
+  **Usage Examples:**
+
+  ```bash
+  # Make a task more detailed
+  task-master scope-up --id=5
+
+  # Simplify multiple tasks with light touch
+  task-master scope-down --id=10,11,12 --strength=light
+
+  # Custom adjustment with specific instructions
+  task-master scope-up --id=7 --prompt="Add more error handling and edge cases"
+  ```
+
+  **Why use this?**
+  - **Iterative refinement**: Adjust task complexity as your understanding evolves
+  - **Project phase adaptation**: Scale tasks up for implementation, down for planning
+  - **Team coordination**: Adjust complexity based on team member experience levels
+  - **Milestone alignment**: Fine-tune tasks to match project phase requirements
+
+  Perfect for agile workflows where task requirements change as you learn more about the problem space.
+
+## 0.22.1-rc.0
+
+### Patch Changes
+
+- [#1063](https://github.com/eyaltoledano/claude-task-master/pull/1063) [`2ae6e7e`](https://github.com/eyaltoledano/claude-task-master/commit/2ae6e7e6be3605c3c4d353f34666e54750dba973) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix for tasks not found when using string IDs
+
+- [#1049](https://github.com/eyaltoledano/claude-task-master/pull/1049) [`45a14c3`](https://github.com/eyaltoledano/claude-task-master/commit/45a14c323d21071c15106335e89ad1f4a20976ab) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix tag-specific complexity report detection in expand command
+
+  The expand command now correctly finds and uses tag-specific complexity reports (e.g., `task-complexity-report_feature-xyz.json`) when operating in a tag context. Previously, it would always look for the generic `task-complexity-report.json` file due to a default value in the CLI option definition.
+
+## 0.22.0
+
+### Minor Changes
+
+- [#1043](https://github.com/eyaltoledano/claude-task-master/pull/1043) [`dc44ed9`](https://github.com/eyaltoledano/claude-task-master/commit/dc44ed9de8a57aca5d39d3a87565568bd0a82068) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prompt to generate a complexity report when it is missing
+
+- [#1032](https://github.com/eyaltoledano/claude-task-master/pull/1032) [`4423119`](https://github.com/eyaltoledano/claude-task-master/commit/4423119a5ec53958c9dffa8bf564da8be7a2827d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add comprehensive Kiro IDE integration with autonomous task management hooks
+  - **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
+  - **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
+  - **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
+  - **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
+  - **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
+  - **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
+
+  Key hooks included:
+  - Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
+  - Code Change Task Tracker: Updates task progress as you save files
+  - Test Success Task Completer: Marks tasks done when tests pass
+  - Daily Standup Assistant: Provides personalized task status summaries
+  - PR Readiness Checker: Validates task completion before creating pull requests
+  - Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
+  - Git Commit Task Linker: Links commits to tasks for better traceability
+
+  This creates a truly autonomous development workflow where task management happens naturally as you code!
+
+### Patch Changes
+
+- [#1033](https://github.com/eyaltoledano/claude-task-master/pull/1033) [`7b90568`](https://github.com/eyaltoledano/claude-task-master/commit/7b9056832653464f934c91c22997077065d738c4) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.
+
+- [#1038](https://github.com/eyaltoledano/claude-task-master/pull/1038) [`77cc5e4`](https://github.com/eyaltoledano/claude-task-master/commit/77cc5e4537397642f2664f61940a101433ee6fb4) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.
+
+- [#1025](https://github.com/eyaltoledano/claude-task-master/pull/1025) [`8781794`](https://github.com/eyaltoledano/claude-task-master/commit/8781794c56d454697fc92c88a3925982d6b81205) Thanks [@joedanz](https://github.com/joedanz)! - Clean up remaining automatic task file generation calls
+
+- [#1035](https://github.com/eyaltoledano/claude-task-master/pull/1035) [`fb7d588`](https://github.com/eyaltoledano/claude-task-master/commit/fb7d588137e8c53b0d0f54bd1dd8d387648583ee) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens limits for OpenRouter and Groq models
+  - Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
+  - Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
+  - Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
+  - This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list
+
+- [#1027](https://github.com/eyaltoledano/claude-task-master/pull/1027) [`6ae66b2`](https://github.com/eyaltoledano/claude-task-master/commit/6ae66b2afbfe911340fa25e0236c3db83deaa7eb) Thanks [@andreswebs](https://github.com/andreswebs)! - Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).
+
+## 0.22.0-rc.1
+
+### Minor Changes
+
+- [#1043](https://github.com/eyaltoledano/claude-task-master/pull/1043) [`dc44ed9`](https://github.com/eyaltoledano/claude-task-master/commit/dc44ed9de8a57aca5d39d3a87565568bd0a82068) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prompt to generate a complexity report when it is missing
+
+## 0.22.0-rc.0
+
+### Minor Changes
+
+- [#1032](https://github.com/eyaltoledano/claude-task-master/pull/1032) [`4423119`](https://github.com/eyaltoledano/claude-task-master/commit/4423119a5ec53958c9dffa8bf564da8be7a2827d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add comprehensive Kiro IDE integration with autonomous task management hooks
+  - **Kiro Profile**: Added full support for Kiro IDE with automatic installation of 7 Taskmaster agent hooks
+  - **Hook-Driven Workflow**: Introduced natural language automation hooks that eliminate manual task status updates
+  - **Automatic Hook Installation**: Hooks are now automatically copied to `.kiro/hooks/` when running `task-master rules add kiro`
+  - **Language-Agnostic Support**: All hooks support multiple programming languages (JS, Python, Go, Rust, Java, etc.)
+  - **Frontmatter Transformation**: Kiro rules use simplified `inclusion: always` format instead of Cursor's complex frontmatter
+  - **Special Rule**: Added `taskmaster_hooks_workflow.md` that guides AI assistants to prefer hook-driven completion
+
+  Key hooks included:
+  - Task Dependency Auto-Progression: Automatically starts tasks when dependencies complete
+  - Code Change Task Tracker: Updates task progress as you save files
+  - Test Success Task Completer: Marks tasks done when tests pass
+  - Daily Standup Assistant: Provides personalized task status summaries
+  - PR Readiness Checker: Validates task completion before creating pull requests
+  - Complexity Analyzer: Auto-expands complex tasks into manageable subtasks
+  - Git Commit Task Linker: Links commits to tasks for better traceability
+
+  This creates a truly autonomous development workflow where task management happens naturally as you code!
+
+### Patch Changes
+
+- [#1033](https://github.com/eyaltoledano/claude-task-master/pull/1033) [`7b90568`](https://github.com/eyaltoledano/claude-task-master/commit/7b9056832653464f934c91c22997077065d738c4) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix compatibility with @google/gemini-cli-core v0.1.12+ by updating ai-sdk-provider-gemini-cli to v0.1.1.
+
+- [#1038](https://github.com/eyaltoledano/claude-task-master/pull/1038) [`77cc5e4`](https://github.com/eyaltoledano/claude-task-master/commit/77cc5e4537397642f2664f61940a101433ee6fb4) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix 'expand --all' and 'show' commands to correctly handle tag contexts for complexity reports and task display.
+
+- [#1025](https://github.com/eyaltoledano/claude-task-master/pull/1025) [`8781794`](https://github.com/eyaltoledano/claude-task-master/commit/8781794c56d454697fc92c88a3925982d6b81205) Thanks [@joedanz](https://github.com/joedanz)! - Clean up remaining automatic task file generation calls
+
+- [#1035](https://github.com/eyaltoledano/claude-task-master/pull/1035) [`fb7d588`](https://github.com/eyaltoledano/claude-task-master/commit/fb7d588137e8c53b0d0f54bd1dd8d387648583ee) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix max_tokens limits for OpenRouter and Groq models
+  - Add special handling in config-manager.js for custom OpenRouter models to use a conservative default of 32,768 max_tokens
+  - Update qwen/qwen-turbo model max_tokens from 1,000,000 to 32,768 to match OpenRouter's actual limits
+  - Fix moonshotai/kimi-k2-instruct max_tokens to 16,384 to match Groq's actual limit (fixes #1028)
+  - This prevents "maximum context length exceeded" errors when using OpenRouter models not in our supported models list
+
+- [#1027](https://github.com/eyaltoledano/claude-task-master/pull/1027) [`6ae66b2`](https://github.com/eyaltoledano/claude-task-master/commit/6ae66b2afbfe911340fa25e0236c3db83deaa7eb) Thanks [@andreswebs](https://github.com/andreswebs)! - Fix VSCode profile generation to use correct rule file names (using `.instructions.md` extension instead of `.md`) and front-matter properties (removing the unsupported `alwaysApply` property from instructions files' front-matter).
+
+## 0.21.0
+
+### Minor Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`9c58a92`](https://github.com/eyaltoledano/claude-task-master/commit/9c58a922436c0c5e7ff1b20ed2edbc269990c772) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
+  - Add support for Kiro IDE with custom rule files and MCP configuration
+  - Generate rule files in `.kiro/steering/` directory with markdown format
+  - Include MCP server configuration with enhanced file inclusion patterns
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`58a301c`](https://github.com/eyaltoledano/claude-task-master/commit/58a301c380d18a9d9509137f3e989d24200a5faa) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
+  - Fixed Groq provider registration
+  - Added Groq API key validation
+  - Added GROQ_API_KEY to .env.example
+  - Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`b0e09c7`](https://github.com/eyaltoledano/claude-task-master/commit/b0e09c76ed73b00434ac95606679f570f1015a3d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6c5e0f9`](https://github.com/eyaltoledano/claude-task-master/commit/6c5e0f97f8403c4da85c1abba31cb8b1789511a7) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`36c4a7a`](https://github.com/eyaltoledano/claude-task-master/commit/36c4a7a86924c927ad7f86a4f891f66ad55eb4d2) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
+
+  The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
+
+  When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`6d69d02`](https://github.com/eyaltoledano/claude-task-master/commit/6d69d02fe03edcc785380415995d5cfcdd97acbb) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
+  - Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
+  - Adds an import section to the user's CLAUDE.md that references the Task Master instructions
+  - Preserves existing user content in CLAUDE.md files
+  - Provides clean uninstall that only removes Task Master's additions
+
+  **Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`fd005c4`](https://github.com/eyaltoledano/claude-task-master/commit/fd005c4c5481ffac58b11f01a448fa5b29056b8d) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`444aa5a`](https://github.com/eyaltoledano/claude-task-master/commit/444aa5ae1943ba72d012b3f01b1cc9362a328248) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`624922c`](https://github.com/eyaltoledano/claude-task-master/commit/624922ca598c4ce8afe9a5646ebb375d4616db63) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix: show command no longer requires complexity report file to exist
+
+  The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`858d4a1`](https://github.com/eyaltoledano/claude-task-master/commit/858d4a1c5486d20e7e3a8e37e3329d7fb8200310) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Update VS Code profile with MCP config transformation
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0451ebc`](https://github.com/eyaltoledano/claude-task-master/commit/0451ebcc32cd7e9d395b015aaa8602c4734157e1) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0a70ab6`](https://github.com/eyaltoledano/claude-task-master/commit/0a70ab6179cb2b5b4b2d9dc256a7a3b69a0e5dd6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add MCP configuration support to Claude Code rules
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`4629128`](https://github.com/eyaltoledano/claude-task-master/commit/4629128943f6283385f4762c09cf2752f855cc33) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
+  - Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`0886c83`](https://github.com/eyaltoledano/claude-task-master/commit/0886c83d0c678417c0313256a6dd96f7ee2c9ac6) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#1009](https://github.com/eyaltoledano/claude-task-master/pull/1009) [`88c434a`](https://github.com/eyaltoledano/claude-task-master/commit/88c434a9393e429d9277f59b3e20f1005076bbe0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add missing API keys to .env.example and README.md
+
+## 0.21.0-rc.0
+
+### Minor Changes
+
+- [#1001](https://github.com/eyaltoledano/claude-task-master/pull/1001) [`75a36ea`](https://github.com/eyaltoledano/claude-task-master/commit/75a36ea99a1c738a555bdd4fe7c763d0c5925e37) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Kiro editor rule profile support
+  - Add support for Kiro IDE with custom rule files and MCP configuration
+  - Generate rule files in `.kiro/steering/` directory with markdown format
+  - Include MCP server configuration with enhanced file inclusion patterns
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Created a comprehensive documentation site for Task Master AI. Visit https://docs.task-master.dev to explore guides, API references, and examples.
+
+- [#978](https://github.com/eyaltoledano/claude-task-master/pull/978) [`fedfd6a`](https://github.com/eyaltoledano/claude-task-master/commit/fedfd6a0f41a78094f7ee7f69be689b699475a79) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Complete Groq provider integration and add MoonshotAI Kimi K2 model support
+  - Fixed Groq provider registration
+  - Added Groq API key validation
+  - Added GROQ_API_KEY to .env.example
+  - Added moonshotai/kimi-k2-instruct model with $1/$3 per 1M token pricing and 16k max output
+
+- [#974](https://github.com/eyaltoledano/claude-task-master/pull/974) [`5b0eda0`](https://github.com/eyaltoledano/claude-task-master/commit/5b0eda07f20a365aa2ec1736eed102bca81763a9) Thanks [@joedanz](https://github.com/joedanz)! - feat: Add Zed editor rule profile with agent rules and MCP config
+  - Resolves #637
+
+- [#973](https://github.com/eyaltoledano/claude-task-master/pull/973) [`6d05e86`](https://github.com/eyaltoledano/claude-task-master/commit/6d05e8622c1d761acef10414940ff9a766b3b57d) Thanks [@joedanz](https://github.com/joedanz)! - Add Amp rule profile with AGENT.md and MCP config
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve project root detection
+  - No longer creates an infinite loop when unable to detect your code workspace
+
+- [#970](https://github.com/eyaltoledano/claude-task-master/pull/970) [`b87499b`](https://github.com/eyaltoledano/claude-task-master/commit/b87499b56e626001371a87ed56ffc72675d829f3) Thanks [@joedanz](https://github.com/joedanz)! - Add OpenCode profile with AGENTS.md and MCP config
+  - Resolves #965
+
+### Patch Changes
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Make `task-master update` more reliable with AI responses
+
+  The `update` command now handles AI responses more robustly. If the AI forgets to include certain task fields, the command will automatically fill in the missing data from your original tasks instead of failing. This means smoother bulk task updates without losing important information like IDs, dependencies, or completed subtasks.
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix subtask dependency validation when expanding tasks
+
+  When using `task-master expand` to break down tasks into subtasks, dependencies between subtasks are now properly validated. Previously, subtasks with dependencies would fail validation. Now subtasks can correctly depend on their siblings within the same parent task.
+
+- [#949](https://github.com/eyaltoledano/claude-task-master/pull/949) [`f662654`](https://github.com/eyaltoledano/claude-task-master/commit/f662654afb8e7a230448655265d6f41adf6df62c) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Prevent CLAUDE.md overwrite by using Claude Code's import feature
+  - Task Master now creates its instructions in `.taskmaster/CLAUDE.md` instead of overwriting the user's `CLAUDE.md`
+  - Adds an import section to the user's CLAUDE.md that references the Task Master instructions
+  - Preserves existing user content in CLAUDE.md files
+  - Provides clean uninstall that only removes Task Master's additions
+
+  **Breaking Change**: Task Master instructions for Claude Code are now stored in `.taskmaster/CLAUDE.md` and imported into the main CLAUDE.md file. Users who previously had Task Master content directly in their CLAUDE.md will need to run `task-master rules remove claude` followed by `task-master rules add claude` to migrate to the new structure.
+
+- [#943](https://github.com/eyaltoledano/claude-task-master/pull/943) [`f98df5c`](https://github.com/eyaltoledano/claude-task-master/commit/f98df5c0fdb253b2b55d4278c11d626529c4dba4) Thanks [@mm-parthy](https://github.com/mm-parthy)! - Implement Boundary-First Tag Resolution to ensure consistent and deterministic tag handling across CLI and MCP, resolving potential race conditions.
+
+- [#1011](https://github.com/eyaltoledano/claude-task-master/pull/1011) [`3eb050a`](https://github.com/eyaltoledano/claude-task-master/commit/3eb050aaddb90fca1a04517e2ee24f73934323be) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix `task-master lang --setup` breaking when no language is defined, now defaults to English
+
+- [#979](https://github.com/eyaltoledano/claude-task-master/pull/979) [`ab2e946`](https://github.com/eyaltoledano/claude-task-master/commit/ab2e94608749a2f148118daa0443bd32bca6e7a1) Thanks [@ben-vargas](https://github.com/ben-vargas)! - Fix: show command no longer requires complexity report file to exist
+
+  The `tm show` command was incorrectly requiring the complexity report file to exist even when not needed. Now it only validates the complexity report path when a custom report file is explicitly provided via the -r/--report option.
+
+- [#971](https://github.com/eyaltoledano/claude-task-master/pull/971) [`5544222`](https://github.com/eyaltoledano/claude-task-master/commit/55442226d0aa4870470d2a9897f5538d6a0e329e) Thanks [@joedanz](https://github.com/joedanz)! - Update VS Code profile with MCP config transformation
+
+- [#1002](https://github.com/eyaltoledano/claude-task-master/pull/1002) [`6d0654c`](https://github.com/eyaltoledano/claude-task-master/commit/6d0654cb4191cee794e1c8cbf2b92dc33d4fb410) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix MCP server error when retrieving tools and resources
+
+- [#980](https://github.com/eyaltoledano/claude-task-master/pull/980) [`cc4fe20`](https://github.com/eyaltoledano/claude-task-master/commit/cc4fe205fb468e7144c650acc92486df30731560) Thanks [@joedanz](https://github.com/joedanz)! - Add MCP configuration support to Claude Code rules
+
+- [#968](https://github.com/eyaltoledano/claude-task-master/pull/968) [`7b4803a`](https://github.com/eyaltoledano/claude-task-master/commit/7b4803a479105691c7ed032fd878fe3d48d82724) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fixed the comprehensive taskmaster system integration via custom slash commands with proper syntax
+  - Provide claude clode with a complete set of of commands that can trigger task master events directly within Claude Code
+
+- [#995](https://github.com/eyaltoledano/claude-task-master/pull/995) [`b78de8d`](https://github.com/eyaltoledano/claude-task-master/commit/b78de8dbb4d6dc93b48e2f81c32960ef069736ed) Thanks [@joedanz](https://github.com/joedanz)! - Correct MCP server name and use 'Add to Cursor' button with updated placeholder keys.
+
+- [#972](https://github.com/eyaltoledano/claude-task-master/pull/972) [`1c7badf`](https://github.com/eyaltoledano/claude-task-master/commit/1c7badff2f5c548bfa90a3b2634e63087a382a84) Thanks [@joedanz](https://github.com/joedanz)! - Add missing API keys to .env.example and README.md
+
 ## 0.20.0
 
 ### Minor Changes

CLAUDE.md

@@ -0,0 +1,9 @@
+# Claude Code Instructions
+
+## Task Master AI Instructions
+**Import Task Master's development workflow commands and guidelines, treat as if import is in the main CLAUDE.md file.**
+@./.taskmaster/CLAUDE.md
+
+## Changeset Guidelines
+
+- When creating changesets, remember that it's user-facing, meaning we don't have to get into the specifics of the code, but rather mention what the end-user is getting or fixing from this changeset.

README.md

@@ -1,20 +1,51 @@
-# Task Master [![GitHub stars](https://img.shields.io/github/stars/eyaltoledano/claude-task-master?style=social)](https://github.com/eyaltoledano/claude-task-master/stargazers)
+<a name="readme-top"></a>
 
-[![CI](https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml/badge.svg)](https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml) [![npm version](https://badge.fury.io/js/task-master-ai.svg)](https://badge.fury.io/js/task-master-ai) [![Discord](https://dcbadge.limes.pink/api/server/https://discord.gg/taskmasterai?style=flat)](https://discord.gg/taskmasterai) [![License: MIT with Commons Clause](https://img.shields.io/badge/license-MIT%20with%20Commons%20Clause-blue.svg)](LICENSE)
+<div align='center'>
+<a href="https://trendshift.io/repositories/13971" target="_blank"><img src="https://trendshift.io/api/badge/repositories/13971" alt="eyaltoledano%2Fclaude-task-master | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</div>
 
-[![NPM Downloads](https://img.shields.io/npm/d18m/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai) [![NPM Downloads](https://img.shields.io/npm/dm/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai) [![NPM Downloads](https://img.shields.io/npm/dw/task-master-ai?style=flat)](https://www.npmjs.com/package/task-master-ai)
+<p align="center">
+  <a href="https://task-master.dev"><img src="./images/logo.png?raw=true" alt="Taskmaster logo"></a>
+</p>
 
-## By [@eyaltoledano](https://x.com/eyaltoledano), [@RalphEcom](https://x.com/RalphEcom) & [@jasonzhou1993](https://x.com/jasonzhou1993)
+<p align="center">
+<b>Taskmaster</b>: A task management system for AI-driven development, designed to work seamlessly with any AI chat.
+</p>
+
+<p align="center">
+  <a href="https://discord.gg/taskmasterai" target="_blank"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/taskmasterai?style=flat" alt="Discord"></a> |
+  <a href="https://docs.task-master.dev" target="_blank">Docs</a>
+</p>
+
+<p align="center">
+  <a href="https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml"><img src="https://github.com/eyaltoledano/claude-task-master/actions/workflows/ci.yml/badge.svg" alt="CI"></a>
+  <a href="https://github.com/eyaltoledano/claude-task-master/stargazers"><img src="https://img.shields.io/github/stars/eyaltoledano/claude-task-master?style=social" alt="GitHub stars"></a>
+  <a href="https://badge.fury.io/js/task-master-ai"><img src="https://badge.fury.io/js/task-master-ai.svg" alt="npm version"></a>
+  <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT%20with%20Commons%20Clause-blue.svg" alt="License"></a>
+</p>
+
+<p align="center">
+  <a href="https://www.npmjs.com/package/task-master-ai"><img src="https://img.shields.io/npm/d18m/task-master-ai?style=flat" alt="NPM Downloads"></a>
+  <a href="https://www.npmjs.com/package/task-master-ai"><img src="https://img.shields.io/npm/dm/task-master-ai?style=flat" alt="NPM Downloads"></a>
+  <a href="https://www.npmjs.com/package/task-master-ai"><img src="https://img.shields.io/npm/dw/task-master-ai?style=flat" alt="NPM Downloads"></a>
+</p>
+
+## By [@eyaltoledano](https://x.com/eyaltoledano) & [@RalphEcom](https://x.com/RalphEcom)
 
 [![Twitter Follow](https://img.shields.io/twitter/follow/eyaltoledano)](https://x.com/eyaltoledano)
 [![Twitter Follow](https://img.shields.io/twitter/follow/RalphEcom)](https://x.com/RalphEcom)
-[![Twitter Follow](https://img.shields.io/twitter/follow/jasonzhou1993)](https://x.com/jasonzhou1993)
 
 A task management system for AI-driven development with Claude, designed to work seamlessly with Cursor AI.
 
 ## Documentation
 
-For more detailed information, check out the documentation in the `docs` directory:
+📚 **[View Full Documentation](https://docs.task-master.dev)**
+
+For detailed guides, API references, and comprehensive examples, visit our documentation site.
+
+### Quick Reference
+
+The following documentation is also available in the `docs` directory:
 
 - [Configuration Guide](docs/configuration.md) - Set up environment variables and customize Task Master
 - [Tutorial](docs/tutorial.md) - Step-by-step guide to getting started with Task Master
@@ -25,7 +56,7 @@ For more detailed information, check out the documentation in the `docs` directo
 
 #### Quick Install for Cursor 1.0+ (One-Click)
 
-[![Add task-master-ai MCP server to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/install-mcp?name=task-master-ai&config=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%3D%3D)
+[![Add task-master-ai MCP server to Cursor](https://cursor.com/deeplink/mcp-install-dark.svg)](https://cursor.com/en/install-mcp?name=task-master-ai&config=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%3D%3D)
 
 > **Note:** After clicking the link, you'll still need to add your API keys to the configuration. The link installs the MCP server with placeholder keys that you'll need to replace with your actual API keys.
 
@@ -224,6 +255,11 @@ task-master show 1,3,5
 # Research fresh information with project context
 task-master research "What are the latest best practices for JWT authentication?"
 
+# Move tasks between tags (cross-tag movement)
+task-master move --from=5 --from-tag=backlog --to-tag=in-progress
+task-master move --from=5,6,7 --from-tag=backlog --to-tag=done --with-dependencies
+task-master move --from=5 --from-tag=backlog --to-tag=in-progress --ignore-dependencies
+
 # Generate task files
 task-master generate
 

apps/docs/CHANGELOG.md

@@ -0,0 +1,5 @@
+# docs
+
+## 0.0.2
+
+## 0.0.1

apps/docs/README.md

@@ -0,0 +1,22 @@
+# Task Master Documentation
+
+Welcome to the Task Master documentation. Use the links below to navigate to the information you need:
+
+## Getting Started
+
+- [Configuration Guide](archive/configuration.md) - Set up environment variables and customize Task Master
+- [Tutorial](archive/ctutorial.md) - Step-by-step guide to getting started with Task Master
+
+## Reference
+
+- [Command Reference](archive/ccommand-reference.md) - Complete list of all available commands
+- [Task Structure](archive/ctask-structure.md) - Understanding the task format and features
+
+## Examples & Licensing
+
+- [Example Interactions](archive/cexamples.md) - Common Cursor AI interaction examples
+- [Licensing Information](archive/clicensing.md) - Detailed information about the license
+
+## Need More Help?
+
+If you can't find what you're looking for in these docs, please check the [main README](../README.md) or visit our [GitHub repository](https://github.com/eyaltoledano/claude-task-master).

apps/docs/archive/Installation.mdx

@@ -0,0 +1,114 @@
+---
+title: "Installation(2)"
+description: "This guide walks you through setting up Task Master in your development environment."
+---
+
+## Initial Setup
+
+<Tip>
+  MCP (Model Control Protocol) provides the easiest way to get started with Task Master directly in your editor.
+</Tip>
+
+<AccordionGroup>
+  <Accordion title="Option 1: Using MCP (Recommended)" icon="sparkles">
+    <Steps>
+      <Step title="Add the MCP config to your editor">
+        <Link href="https://cursor.sh">Cursor</Link> recommended, but it works with other text editors
+        ```json
+        {
+        	"mcpServers": {
+        		"taskmaster-ai": {
+        			"command": "npx",
+        			"args": ["-y", "--package", "task-master-ai", "task-master-mcp"],
+        			"env": {
+        				"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        				"PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        				"MODEL": "claude-3-7-sonnet-20250219",
+        				"PERPLEXITY_MODEL": "sonar-pro",
+        				"MAX_TOKENS": 128000,
+        				"TEMPERATURE": 0.2,
+        				"DEFAULT_SUBTASKS": 5,
+        				"DEFAULT_PRIORITY": "medium"
+        			}
+        		}
+        	}
+        }
+        ```
+      </Step>
+      <Step title="Enable the MCP in your editor settings">
+        
+      </Step>
+      <Step title="Prompt the AI to initialize Task Master">
+        > "Can you please initialize taskmaster-ai into my project?"
+
+        **The AI will:**
+
+        1. Create necessary project structure
+        2. Set up initial configuration files
+        3. Guide you through the rest of the process
+        4. Place your PRD document in the `scripts/` directory (e.g., `scripts/prd.txt`)
+        5. **Use natural language commands** to interact with Task Master:
+
+           > "Can you parse my PRD at scripts/prd.txt?"
+           >
+           > "What's the next task I should work on?"
+           >
+           > "Can you help me implement task 3?"
+      </Step>
+    </Steps>
+  </Accordion>
+  <Accordion title="Option 2: Manual Installation">
+    If you prefer to use the command line interface directly:
+
+    <Steps>
+      <Step title="Install">
+        <CodeGroup>
+
+        ```bash Global
+        npm install -g task-master-ai
+        ```
+
+        
+        ```bash Local
+        npm install task-master-ai
+        ```
+
+        </CodeGroup>
+      </Step>
+      <Step title="Initialize a new project">
+        <CodeGroup>
+
+        ```bash Global
+        task-master init
+        ```
+
+        
+        ```bash Local
+        npx task-master-init
+        ```
+
+        </CodeGroup>
+      </Step>
+    </Steps>
+    This will prompt you for project details and set up a new project with the necessary files and structure.
+  </Accordion>
+</AccordionGroup>
+
+## Common Commands
+
+<Tip>
+  After setting up Task Master, you can use these commands (either via AI prompts or CLI)
+</Tip>
+
+```bash
+# Parse a PRD and generate tasks
+task-master parse-prd your-prd.txt
+
+# List all tasks
+task-master list
+
+# Show the next task to work on
+task-master next
+
+# Generate task files
+task-master generate 

apps/docs/archive/ai-client-utils-example.mdx

@@ -0,0 +1,263 @@
+---
+title: "AI Client Utilities for MCP Tools"
+description: "This document provides examples of how to use the new AI client utilities with AsyncOperationManager in MCP tools."
+---
+## Examples
+<AccordionGroup>
+  <Accordion title="Basic Usage with Direct Functions">
+    ```javascript
+    // In your direct function implementation:
+    import {
+        getAnthropicClientForMCP,
+        getModelConfig,
+        handleClaudeError
+    } from '../utils/ai-client-utils.js';
+
+    export async function someAiOperationDirect(args, log, context) {
+        try {
+            // Initialize Anthropic client with session from context
+            const client = getAnthropicClientForMCP(context.session, log);
+
+            // Get model configuration with defaults or session overrides
+            const modelConfig = getModelConfig(context.session);
+
+            // Make API call with proper error handling
+            try {
+                const response = await client.messages.create({
+                    model: modelConfig.model,
+                    max_tokens: modelConfig.maxTokens,
+                    temperature: modelConfig.temperature,
+                    messages: [{ role: 'user', content: 'Your prompt here' }]
+                });
+
+                return {
+                    success: true,
+                    data: response
+                };
+            } catch (apiError) {
+                // Use helper to get user-friendly error message
+                const friendlyMessage = handleClaudeError(apiError);
+
+                return {
+                    success: false,
+                    error: {
+                        code: 'AI_API_ERROR',
+                        message: friendlyMessage
+                    }
+                };
+            }
+        } catch (error) {
+            // Handle client initialization errors
+            return {
+                success: false,
+                error: {
+                    code: 'AI_CLIENT_ERROR',
+                    message: error.message
+                }
+            };
+        }
+    }
+    ```
+  </Accordion>
+
+  <Accordion title="Integration with AsyncOperationManager">
+    ```javascript
+    // In your MCP tool implementation:
+    import {
+        AsyncOperationManager,
+        StatusCodes
+    } from '../../utils/async-operation-manager.js';
+    import { someAiOperationDirect } from '../../core/direct-functions/some-ai-operation.js';
+
+    export async function someAiOperation(args, context) {
+        const { session, mcpLog } = context;
+        const log = mcpLog || console;
+
+        try {
+            // Create operation description
+            const operationDescription = `AI operation: ${args.someParam}`;
+
+            // Start async operation
+            const operation = AsyncOperationManager.createOperation(
+                operationDescription,
+                async (reportProgress) => {
+                    try {
+                        // Initial progress report
+                        reportProgress({
+                            progress: 0,
+                            status: 'Starting AI operation...'
+                        });
+
+                        // Call direct function with session and progress reporting
+                        const result = await someAiOperationDirect(args, log, {
+                            reportProgress,
+                            mcpLog: log,
+                            session
+                        });
+
+                        // Final progress update
+                        reportProgress({
+                            progress: 100,
+                            status: result.success ? 'Operation completed' : 'Operation failed',
+                            result: result.data,
+                            error: result.error
+                        });
+
+                        return result;
+                    } catch (error) {
+                        // Handle errors in the operation
+                        reportProgress({
+                            progress: 100,
+                            status: 'Operation failed',
+                            error: {
+                                message: error.message,
+                                code: error.code || 'OPERATION_FAILED'
+                            }
+                        });
+                        throw error;
+                    }
+                }
+            );
+
+            // Return immediate response with operation ID
+            return {
+                status: StatusCodes.ACCEPTED,
+                body: {
+                    success: true,
+                    message: 'Operation started',
+                    operationId: operation.id
+                }
+            };
+        } catch (error) {
+            // Handle errors in the MCP tool
+            log.error(`Error in someAiOperation: ${error.message}`);
+            return {
+                status: StatusCodes.INTERNAL_SERVER_ERROR,
+                body: {
+                    success: false,
+                    error: {
+                        code: 'OPERATION_FAILED',
+                        message: error.message
+                    }
+                }
+            };
+        }
+    }
+    ```
+  </Accordion>
+
+  <Accordion title="Using Research Capabilities with Perplexity">
+    ```javascript
+    // In your direct function:
+    import {
+        getPerplexityClientForMCP,
+        getBestAvailableAIModel
+    } from '../utils/ai-client-utils.js';
+
+    export async function researchOperationDirect(args, log, context) {
+        try {
+            // Get the best AI model for this operation based on needs
+            const { type, client } = await getBestAvailableAIModel(
+                context.session,
+                { requiresResearch: true },
+                log
+            );
+
+            // Report which model we're using
+            if (context.reportProgress) {
+                await context.reportProgress({
+                    progress: 10,
+                    status: `Using ${type} model for research...`
+                });
+            }
+
+            // Make API call based on the model type
+            if (type === 'perplexity') {
+                // Call Perplexity
+                const response = await client.chat.completions.create({
+                    model: context.session?.env?.PERPLEXITY_MODEL || 'sonar-medium-online',
+                    messages: [{ role: 'user', content: args.researchQuery }],
+                    temperature: 0.1
+                });
+
+                return {
+                    success: true,
+                    data: response.choices[0].message.content
+                };
+            } else {
+                // Call Claude as fallback
+                // (Implementation depends on specific needs)
+                // ...
+            }
+        } catch (error) {
+            // Handle errors
+            return {
+                success: false,
+                error: {
+                    code: 'RESEARCH_ERROR',
+                    message: error.message
+                }
+            };
+        }
+    }
+    ```
+  </Accordion>
+
+  <Accordion title="Model Configuration Override">
+    ```javascript
+    // In your direct function:
+    import { getModelConfig } from '../utils/ai-client-utils.js';
+
+    // Using custom defaults for a specific operation
+    const operationDefaults = {
+        model: 'claude-3-haiku-20240307', // Faster, smaller model
+        maxTokens: 1000, // Lower token limit
+        temperature: 0.2 // Lower temperature for more deterministic output
+    };
+
+    // Get model config with operation-specific defaults
+    const modelConfig = getModelConfig(context.session, operationDefaults);
+
+    // Now use modelConfig in your API calls
+    const response = await client.messages.create({
+        model: modelConfig.model,
+        max_tokens: modelConfig.maxTokens,
+        temperature: modelConfig.temperature
+        // Other parameters...
+    });
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## Best Practices
+
+<AccordionGroup>
+  <Accordion title="Error Handling">
+    - Always use try/catch blocks around both client initialization and API calls
+    - Use `handleClaudeError` to provide user-friendly error messages
+    - Return standardized error objects with code and message
+  </Accordion>
+  
+  <Accordion title="Progress Reporting">
+    - Report progress at key points (starting, processing, completing)
+    - Include meaningful status messages
+    - Include error details in progress reports when failures occur
+  </Accordion>
+  
+  <Accordion title="Session Handling">
+    - Always pass the session from the context to the AI client getters
+    - Use `getModelConfig` to respect user settings from session
+  </Accordion>
+  
+  <Accordion title="Model Selection">
+    - Use `getBestAvailableAIModel` when you need to select between different models
+    - Set `requiresResearch: true` when you need Perplexity capabilities
+  </Accordion>
+  
+  <Accordion title="AsyncOperationManager Integration">
+    - Create descriptive operation names
+    - Handle all errors within the operation function
+    - Return standardized results from direct functions
+    - Return immediate responses with operation IDs
+  </Accordion>
+</AccordionGroup>

apps/docs/archive/ai-development-workflow.mdx

@@ -0,0 +1,180 @@
+---
+title: "AI Development Workflow"
+description: "Learn how Task Master and Cursor AI work together to streamline your development workflow"
+---
+
+<Tip>The Cursor agent is pre-configured (via the rules file) to follow this workflow</Tip>
+
+<AccordionGroup>
+  <Accordion title="1. Task Discovery and Selection">
+    Ask the agent to list available tasks:
+
+    ```
+    What tasks are available to work on next?
+    ```
+
+    The agent will:
+
+    - Run `task-master list` to see all tasks
+    - Run `task-master next` to determine the next task to work on
+    - Analyze dependencies to determine which tasks are ready to be worked on
+    - Prioritize tasks based on priority level and ID order
+    - Suggest the next task(s) to implement
+  </Accordion>
+
+  <Accordion title="2. Task Implementation">
+    When implementing a task, the agent will:
+
+    - Reference the task's details section for implementation specifics
+    - Consider dependencies on previous tasks
+    - Follow the project's coding standards
+    - Create appropriate tests based on the task's testStrategy
+
+    You can ask:
+
+    ```
+    Let's implement task 3. What does it involve?
+    ```
+  </Accordion>
+
+  <Accordion title="3. Task Verification">
+    Before marking a task as complete, verify it according to:
+
+    - The task's specified testStrategy
+    - Any automated tests in the codebase
+    - Manual verification if required
+  </Accordion>
+
+  <Accordion title="4. Task Completion">
+    When a task is completed, tell the agent:
+
+    ```
+    Task 3 is now complete. Please update its status.
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master set-status --id=3 --status=done
+    ```
+  </Accordion>
+
+  <Accordion title="5. Handling Implementation Drift">
+    If during implementation, you discover that:
+
+    - The current approach differs significantly from what was planned
+    - Future tasks need to be modified due to current implementation choices
+    - New dependencies or requirements have emerged
+
+    Tell the agent:
+
+    ```
+    We've changed our approach. We're now using Express instead of Fastify. Please update all future tasks to reflect this change.
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master update --from=4 --prompt="Now we are using Express instead of Fastify."
+    ```
+
+    This will rewrite or re-scope subsequent tasks in tasks.json while preserving completed work.
+  </Accordion>
+
+  <Accordion title="6. Breaking Down Complex Tasks">
+    For complex tasks that need more granularity:
+
+    ```
+    Task 5 seems complex. Can you break it down into subtasks?
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master expand --id=5 --num=3
+    ```
+
+    You can provide additional context:
+
+    ```
+    Please break down task 5 with a focus on security considerations.
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master expand --id=5 --prompt="Focus on security aspects"
+    ```
+
+    You can also expand all pending tasks:
+
+    ```
+    Please break down all pending tasks into subtasks.
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master expand --all
+    ```
+
+    For research-backed subtask generation using Perplexity AI:
+
+    ```
+    Please break down task 5 using research-backed generation.
+    ```
+
+    The agent will execute:
+
+    ```bash
+    task-master expand --id=5 --research
+    ```
+  </Accordion>
+</AccordionGroup>
+
+## Example Cursor AI Interactions
+
+<AccordionGroup>
+  <Accordion title="Starting a new project">
+    ```
+    I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
+    Can you help me parse it and set up the initial tasks?
+    ```
+  </Accordion>
+  <Accordion title="Working on tasks">
+    ```
+    What's the next task I should work on? Please consider dependencies and priorities.
+    ```
+  </Accordion>
+  <Accordion title="Implementing a specific task">
+    ```
+    I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
+    ```
+  </Accordion>
+  <Accordion title="Managing subtasks">
+    ```
+    I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
+    ```
+  </Accordion>
+  <Accordion title="Handling changes">
+    ```
+    We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
+    ```
+  </Accordion>
+  <Accordion title="Completing work">
+    ```
+    I've finished implementing the authentication system described in task 2. All tests are passing.
+    Please mark it as complete and tell me what I should work on next.
+    ```
+  </Accordion>
+  <Accordion title="Analyzing complexity">
+    ```
+    Can you analyze the complexity of our tasks to help me understand which ones need to be broken down further?
+    ```
+  </Accordion>
+  <Accordion title="Viewing complexity report">
+    ```
+    Can you show me the complexity report in a more readable format?
+    ```
+  </Accordion>
+</AccordionGroup>

apps/docs/archive/command-reference.mdx

@@ -0,0 +1,208 @@
+---
+title: "Task Master Commands"
+description: "A comprehensive reference of all available Task Master commands"
+---
+
+<AccordionGroup>
+  <Accordion title="Parse PRD">
+    ```bash
+    # Parse a PRD file and generate tasks
+    task-master parse-prd <prd-file.txt>
+
+    # Limit the number of tasks generated
+    task-master parse-prd <prd-file.txt> --num-tasks=10
+    ```
+  </Accordion>
+
+  <Accordion title="List Tasks">
+    ```bash
+    # List all tasks
+    task-master list
+
+    # List tasks with a specific status
+    task-master list --status=<status>
+
+    # List tasks with subtasks
+    task-master list --with-subtasks
+
+    # List tasks with a specific status and include subtasks
+    task-master list --status=<status> --with-subtasks
+    ```
+  </Accordion>
+
+  <Accordion title="Show Next Task">
+    ```bash
+    # Show the next task to work on based on dependencies and status
+    task-master next
+    ```
+  </Accordion>
+
+  <Accordion title="Show Specific Task">
+    ```bash
+    # Show details of a specific task
+    task-master show <id>
+    # or
+    task-master show --id=<id>
+
+    # View a specific subtask (e.g., subtask 2 of task 1)
+    task-master show 1.2
+    ```
+  </Accordion>
+
+  <Accordion title="Update Tasks">
+    ```bash
+    # Update tasks from a specific ID and provide context
+    task-master update --from=<id> --prompt="<prompt>"
+    ```
+  </Accordion>
+
+  <Accordion title="Update a Specific Task">
+    ```bash
+    # Update a single task by ID with new information
+    task-master update-task --id=<id> --prompt="<prompt>"
+
+    # Use research-backed updates with Perplexity AI
+    task-master update-task --id=<id> --prompt="<prompt>" --research
+    ```
+  </Accordion>
+
+  <Accordion title="Update a Subtask">
+    ```bash
+    # Append additional information to a specific subtask
+    task-master update-subtask --id=<parentId.subtaskId> --prompt="<prompt>"
+
+    # Example: Add details about API rate limiting to subtask 2 of task 5
+    task-master update-subtask --id=5.2 --prompt="Add rate limiting of 100 requests per minute"
+
+    # Use research-backed updates with Perplexity AI
+    task-master update-subtask --id=<parentId.subtaskId> --prompt="<prompt>" --research
+    ```
+
+    Unlike the `update-task` command which replaces task information, the `update-subtask` command _appends_ new information to the existing subtask details, marking it with a timestamp. This is useful for iteratively enhancing subtasks while preserving the original content.
+  </Accordion>
+
+  <Accordion title="Generate Task Files">
+    ```bash
+    # Generate individual task files from tasks.json
+    task-master generate
+    ```
+  </Accordion>
+
+  <Accordion title="Set Task Status">
+    ```bash
+    # Set status of a single task
+    task-master set-status --id=<id> --status=<status>
+
+    # Set status for multiple tasks
+    task-master set-status --id=1,2,3 --status=<status>
+
+    # Set status for subtasks
+    task-master set-status --id=1.1,1.2 --status=<status>
+    ```
+
+    When marking a task as "done", all of its subtasks will automatically be marked as "done" as well.
+  </Accordion>
+
+  <Accordion title="Expand Tasks">
+    ```bash
+    # Expand a specific task with subtasks
+    task-master expand --id=<id> --num=<number>
+
+    # Expand with additional context
+    task-master expand --id=<id> --prompt="<context>"
+
+    # Expand all pending tasks
+    task-master expand --all
+
+    # Force regeneration of subtasks for tasks that already have them
+    task-master expand --all --force
+
+    # Research-backed subtask generation for a specific task
+    task-master expand --id=<id> --research
+
+    # Research-backed generation for all tasks
+    task-master expand --all --research
+    ```
+  </Accordion>
+
+  <Accordion title="Clear Subtasks">
+    ```bash
+    # Clear subtasks from a specific task
+    task-master clear-subtasks --id=<id>
+
+    # Clear subtasks from multiple tasks
+    task-master clear-subtasks --id=1,2,3
+
+    # Clear subtasks from all tasks
+    task-master clear-subtasks --all
+    ```
+  </Accordion>
+
+  <Accordion title="Analyze Task Complexity">
+    ```bash
+    # Analyze complexity of all tasks
+    task-master analyze-complexity
+
+    # Save report to a custom location
+    task-master analyze-complexity --output=my-report.json
+
+    # Use a specific LLM model
+    task-master analyze-complexity --model=claude-3-opus-20240229
+
+    # Set a custom complexity threshold (1-10)
+    task-master analyze-complexity --threshold=6
+
+    # Use an alternative tasks file
+    task-master analyze-complexity --file=custom-tasks.json
+
+    # Use Perplexity AI for research-backed complexity analysis
+    task-master analyze-complexity --research
+    ```
+  </Accordion>
+
+  <Accordion title="View Complexity Report">
+    ```bash
+    # Display the task complexity analysis report
+    task-master complexity-report
+
+    # View a report at a custom location
+    task-master complexity-report --file=my-report.json
+    ```
+  </Accordion>
+
+  <Accordion title="Managing Task Dependencies">
+    ```bash
+    # Add a dependency to a task
+    task-master add-dependency --id=<id> --depends-on=<id>
+
+    # Remove a dependency from a task
+    task-master remove-dependency --id=<id> --depends-on=<id>
+
+    # Validate dependencies without fixing them
+    task-master validate-dependencies
+
+    # Find and fix invalid dependencies automatically
+    task-master fix-dependencies
+    ```
+  </Accordion>
+
+  <Accordion title="Add a New Task">
+    ```bash
+    # Add a new task using AI
+    task-master add-task --prompt="Description of the new task"
+
+    # Add a task with dependencies
+    task-master add-task --prompt="Description" --dependencies=1,2,3
+
+    # Add a task with priority
+    task-master add-task --prompt="Description" --priority=high
+    ```
+  </Accordion>
+
+  <Accordion title="Initialize a Project">
+    ```bash
+    # Initialize a new project with Task Master structure
+    task-master init
+    ```
+  </Accordion>
+</AccordionGroup>

apps/docs/archive/configuration.mdx

@@ -0,0 +1,80 @@
+---
+title: "Configuration"
+description: "Configure Task Master through environment variables in a .env file"
+---
+
+## Required Configuration
+
+<Note>
+  Task Master requires an Anthropic API key to function. Add this to your `.env` file:
+
+  ```bash
+  ANTHROPIC_API_KEY=sk-ant-api03-your-api-key
+  ```
+
+  You can obtain an API key from the [Anthropic Console](https://console.anthropic.com/).
+</Note>
+
+## Optional Configuration
+
+| Variable | Default Value | Description | Example |
+| --- | --- | --- | --- |
+| `MODEL` | `"claude-3-7-sonnet-20250219"` | Claude model to use | `MODEL=claude-3-opus-20240229` |
+| `MAX_TOKENS` | `"4000"` | Maximum tokens for responses | `MAX_TOKENS=8000` |
+| `TEMPERATURE` | `"0.7"` | Temperature for model responses | `TEMPERATURE=0.5` |
+| `DEBUG` | `"false"` | Enable debug logging | `DEBUG=true` |
+| `LOG_LEVEL` | `"info"` | Console output level | `LOG_LEVEL=debug` |
+| `DEFAULT_SUBTASKS` | `"3"` | Default subtask count | `DEFAULT_SUBTASKS=5` |
+| `DEFAULT_PRIORITY` | `"medium"` | Default priority | `DEFAULT_PRIORITY=high` |
+| `PROJECT_NAME` | `"MCP SaaS MVP"` | Project name in metadata | `PROJECT_NAME=My Awesome Project` |
+| `PROJECT_VERSION` | `"1.0.0"` | Version in metadata | `PROJECT_VERSION=2.1.0` |
+| `PERPLEXITY_API_KEY` | - | For research-backed features | `PERPLEXITY_API_KEY=pplx-...` |
+| `PERPLEXITY_MODEL` | `"sonar-medium-online"` | Perplexity model | `PERPLEXITY_MODEL=sonar-large-online` |
+
+## Example .env File
+
+```
+# Required
+ANTHROPIC_API_KEY=sk-ant-api03-your-api-key
+
+# Optional - Claude Configuration
+MODEL=claude-3-7-sonnet-20250219
+MAX_TOKENS=4000
+TEMPERATURE=0.7
+
+# Optional - Perplexity API for Research
+PERPLEXITY_API_KEY=pplx-your-api-key
+PERPLEXITY_MODEL=sonar-medium-online
+
+# Optional - Project Info
+PROJECT_NAME=My Project
+PROJECT_VERSION=1.0.0
+
+# Optional - Application Configuration
+DEFAULT_SUBTASKS=3
+DEFAULT_PRIORITY=medium
+DEBUG=false
+LOG_LEVEL=info
+```
+
+## Troubleshooting
+
+### If `task-master init` doesn't respond:
+
+Try running it with Node directly:
+
+```bash
+node node_modules/claude-task-master/scripts/init.js
+```
+
+Or clone the repository and run:
+
+```bash
+git clone https://github.com/eyaltoledano/claude-task-master.git
+cd claude-task-master
+node scripts/init.js
+```
+
+<Note>
+For advanced configuration options and detailed customization, see our [Advanced Configuration Guide] page.
+</Note>

apps/docs/archive/cursor-setup.mdx

@@ -0,0 +1,95 @@
+---
+title: "Cursor AI Integration"
+description: "Learn how to set up and use Task Master with Cursor AI"
+---
+
+## Setting up Cursor AI Integration
+
+<Check>
+  Task Master is designed to work seamlessly with [Cursor AI](https://www.cursor.so/), providing a structured workflow for AI-driven development.
+</Check>
+
+<AccordionGroup>
+  <Accordion title="Using Cursor with MCP (Recommended)" icon="sparkles">
+    If you've already set up Task Master with MCP in Cursor, the integration is automatic. You can simply use natural language to interact with Task Master:
+
+    ```
+    What tasks are available to work on next?
+    Can you analyze the complexity of our tasks?
+    I'd like to implement task 4. What does it involve?
+    ```
+  </Accordion>
+  <Accordion title="Manual Cursor Setup">
+    If you're not using MCP, you can still set up Cursor integration:
+
+    <Steps>
+      <Step title="After initializing your project, open it in Cursor">
+        The `.cursor/rules/dev_workflow.mdc` file is automatically loaded by Cursor, providing the AI with knowledge about the task management system
+      </Step>
+      <Step title="Place your PRD document in the scripts/ directory (e.g., scripts/prd.txt)">
+        
+      </Step>
+      <Step title="Open Cursor's AI chat and switch to Agent mode">
+        
+      </Step>
+    </Steps>
+  </Accordion>
+  <Accordion title="Alternative MCP Setup in Cursor">
+    <Steps>
+      <Step title="Go to Cursor settings">
+        
+      </Step>
+      <Step title="Navigate to the MCP section">
+        
+      </Step>
+      <Step title="Click on 'Add New MCP Server'">
+        
+      </Step>
+      <Step title="Configure with the following details:">
+        - Name: "Task Master"
+        - Type: "Command"
+        - Command: "npx -y --package task-master-ai task-master-mcp"
+      </Step>
+      <Step title="Save Settings">
+        
+      </Step>
+    </Steps>
+    Once configured, you can interact with Task Master's task management commands directly through Cursor's interface, providing a more integrated experience.
+  </Accordion>
+</AccordionGroup>
+
+## Initial Task Generation
+
+In Cursor's AI chat, instruct the agent to generate tasks from your PRD:
+
+```
+Please use the task-master parse-prd command to generate tasks from my PRD. The PRD is located at scripts/prd.txt.
+```
+
+The agent will execute:
+
+```bash
+task-master parse-prd scripts/prd.txt
+```
+
+This will:
+
+- Parse your PRD document
+- Generate a structured `tasks.json` file with tasks, dependencies, priorities, and test strategies
+- The agent will understand this process due to the Cursor rules
+
+### Generate Individual Task Files
+
+Next, ask the agent to generate individual task files:
+
+```
+Please generate individual task files from tasks.json
+```
+
+The agent will execute:
+
+```bash
+task-master generate
+```
+
+This creates individual task files in the `tasks/` directory (e.g., `task_001.txt`, `task_002.txt`), making it easier to reference specific tasks.

apps/docs/archive/examples.mdx

@@ -0,0 +1,56 @@
+---
+title: "Example Cursor AI Interactions"
+description: "Below are some common interactions with Cursor AI when using Task Master"
+---
+
+<AccordionGroup>
+  <Accordion title="Starting a new project">
+    ```
+    I've just initialized a new project with Claude Task Master. I have a PRD at scripts/prd.txt.
+    Can you help me parse it and set up the initial tasks?
+    ```
+  </Accordion>
+
+  <Accordion title="Working on tasks">
+    ```
+    What's the next task I should work on? Please consider dependencies and priorities.
+    ```
+  </Accordion>
+
+  <Accordion title="Implementing a specific task">
+    ```
+    I'd like to implement task 4. Can you help me understand what needs to be done and how to approach it?
+    ```
+  </Accordion>
+
+  <Accordion title="Managing subtasks">
+    ```
+    I need to regenerate the subtasks for task 3 with a different approach. Can you help me clear and regenerate them?
+    ```
+  </Accordion>
+
+  <Accordion title="Handling changes">
+    ```
+    We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks to reflect this change?
+    ```
+  </Accordion>
+
+  <Accordion title="Completing work">
+    ```
+    I've finished implementing the authentication system described in task 2. All tests are passing.
+    Please mark it as complete and tell me what I should work on next.
+    ```
+  </Accordion>
+
+  <Accordion title="Analyzing complexity">
+    ```
+    Can you analyze the complexity of our tasks to help me understand which ones need to be broken down further?
+    ```
+  </Accordion>
+
+  <Accordion title="Viewing complexity report">
+    ```
+    Can you show me the complexity report in a more readable format?
+    ```
+  </Accordion>
+</AccordionGroup>

apps/docs/best-practices/advanced-tasks.mdx

@@ -0,0 +1,210 @@
+---
+title: Advanced Tasks
+sidebarTitle: "Advanced Tasks"
+---
+
+## AI-Driven Development Workflow
+
+The Cursor agent is pre-configured (via the rules file) to follow this workflow:
+
+### 1. Task Discovery and Selection
+
+Ask the agent to list available tasks:
+
+```
+What tasks are available to work on next?
+```
+
+```
+Can you show me tasks 1, 3, and 5 to understand their current status?
+```
+
+The agent will:
+
+- Run `task-master list` to see all tasks
+- Run `task-master next` to determine the next task to work on
+- Run `task-master show 1,3,5` to display multiple tasks with interactive options
+- Analyze dependencies to determine which tasks are ready to be worked on
+- Prioritize tasks based on priority level and ID order
+- Suggest the next task(s) to implement
+
+### 2. Task Implementation
+
+When implementing a task, the agent will:
+
+- Reference the task's details section for implementation specifics
+- Consider dependencies on previous tasks
+- Follow the project's coding standards
+- Create appropriate tests based on the task's testStrategy
+
+You can ask:
+
+```
+Let's implement task 3. What does it involve?
+```
+
+### 2.1. Viewing Multiple Tasks
+
+For efficient context gathering and batch operations:
+
+```
+Show me tasks 5, 7, and 9 so I can plan my implementation approach.
+```
+
+The agent will:
+
+- Run `task-master show 5,7,9` to display a compact summary table
+- Show task status, priority, and progress indicators
+- Provide an interactive action menu with batch operations
+- Allow you to perform group actions like marking multiple tasks as in-progress
+
+### 3. Task Verification
+
+Before marking a task as complete, verify it according to:
+
+- The task's specified testStrategy
+- Any automated tests in the codebase
+- Manual verification if required
+
+### 4. Task Completion
+
+When a task is completed, tell the agent:
+
+```
+Task 3 is now complete. Please update its status.
+```
+
+The agent will execute:
+
+```bash
+task-master set-status --id=3 --status=done
+```
+
+### 5. Handling Implementation Drift
+
+If during implementation, you discover that:
+
+- The current approach differs significantly from what was planned
+- Future tasks need to be modified due to current implementation choices
+- New dependencies or requirements have emerged
+
+Tell the agent:
+
+```
+We've decided to use MongoDB instead of PostgreSQL. Can you update all future tasks (from ID 4) to reflect this change?
+```
+
+The agent will execute:
+
+```bash
+task-master update --from=4 --prompt="Now we are using MongoDB instead of PostgreSQL."
+
+# OR, if research is needed to find best practices for MongoDB:
+task-master update --from=4 --prompt="Update to use MongoDB, researching best practices" --research
+```
+
+This will rewrite or re-scope subsequent tasks in tasks.json while preserving completed work.
+
+### 6. Reorganizing Tasks
+
+If you need to reorganize your task structure:
+
+```
+I think subtask 5.2 would fit better as part of task 7 instead. Can you move it there?
+```
+
+The agent will execute:
+
+```bash
+task-master move --from=5.2 --to=7.3
+```
+
+You can reorganize tasks in various ways:
+
+- Moving a standalone task to become a subtask: `--from=5 --to=7`
+- Moving a subtask to become a standalone task: `--from=5.2 --to=7`
+- Moving a subtask to a different parent: `--from=5.2 --to=7.3`
+- Reordering subtasks within the same parent: `--from=5.2 --to=5.4`
+- Moving a task to a new ID position: `--from=5 --to=25` (even if task 25 doesn't exist yet)
+- Moving multiple tasks at once: `--from=10,11,12 --to=16,17,18` (must have same number of IDs, Taskmaster will look through each position)
+
+When moving tasks to new IDs:
+
+- The system automatically creates placeholder tasks for non-existent destination IDs
+- This prevents accidental data loss during reorganization
+- Any tasks that depend on moved tasks will have their dependencies updated
+- When moving a parent task, all its subtasks are automatically moved with it and renumbered
+
+This is particularly useful as your project understanding evolves and you need to refine your task structure.
+
+### 7. Resolving Merge Conflicts with Tasks
+
+When working with a team, you might encounter merge conflicts in your tasks.json file if multiple team members create tasks on different branches. The move command makes resolving these conflicts straightforward:
+
+```
+I just merged the main branch and there's a conflict with tasks.json. My teammates created tasks 10-15 while I created tasks 10-12 on my branch. Can you help me resolve this?
+```
+
+The agent will help you:
+
+1. Keep your teammates' tasks (10-15)
+2. Move your tasks to new positions to avoid conflicts:
+
+```bash
+# Move your tasks to new positions (e.g., 16-18)
+task-master move --from=10 --to=16
+task-master move --from=11 --to=17
+task-master move --from=12 --to=18
+```
+
+This approach preserves everyone's work while maintaining a clean task structure, making it much easier to handle task conflicts than trying to manually merge JSON files.
+
+### 8. Breaking Down Complex Tasks
+
+For complex tasks that need more granularity:
+
+```
+Task 5 seems complex. Can you break it down into subtasks?
+```
+
+The agent will execute:
+
+```bash
+task-master expand --id=5 --num=3
+```
+
+You can provide additional context:
+
+```
+Please break down task 5 with a focus on security considerations.
+```
+
+The agent will execute:
+
+```bash
+task-master expand --id=5 --prompt="Focus on security aspects"
+```
+
+You can also expand all pending tasks:
+
+```
+Please break down all pending tasks into subtasks.
+```
+
+The agent will execute:
+
+```bash
+task-master expand --all
+```
+
+For research-backed subtask generation using the configured research model:
+
+```
+Please break down task 5 using research-backed generation.
+```
+
+The agent will execute:
+
+```bash
+task-master expand --id=5 --research
+```

apps/docs/best-practices/configuration-advanced.mdx

@@ -0,0 +1,317 @@
+---
+title: Advanced Configuration
+sidebarTitle: "Advanced Configuration"
+---
+
+
+Taskmaster uses two primary methods for configuration:
+
+1.  **`.taskmaster/config.json` File (Recommended - New Structure)**
+
+    - This JSON file stores most configuration settings, including AI model selections, parameters, logging levels, and project defaults.
+    - **Location:** This file is created in the `.taskmaster/` directory when you run the `task-master models --setup` interactive setup or initialize a new project with `task-master init`.
+    - **Migration:** Existing projects with `.taskmasterconfig` in the root will continue to work, but should be migrated to the new structure using `task-master migrate`.
+    - **Management:** Use the `task-master models --setup` command (or `models` MCP tool) to interactively create and manage this file. You can also set specific models directly using `task-master models --set-<role>=<model_id>`, adding `--ollama` or `--openrouter` flags for custom models. Manual editing is possible but not recommended unless you understand the structure.
+    - **Example Structure:**
+      ```json
+      {
+        "models": {
+          "main": {
+            "provider": "anthropic",
+            "modelId": "claude-3-7-sonnet-20250219",
+            "maxTokens": 64000,
+            "temperature": 0.2,
+            "baseURL": "https://api.anthropic.com/v1"
+          },
+          "research": {
+            "provider": "perplexity",
+            "modelId": "sonar-pro",
+            "maxTokens": 8700,
+            "temperature": 0.1,
+            "baseURL": "https://api.perplexity.ai/v1"
+          },
+          "fallback": {
+            "provider": "anthropic",
+            "modelId": "claude-3-5-sonnet",
+            "maxTokens": 64000,
+            "temperature": 0.2
+          }
+        },
+        "global": {
+          "logLevel": "info",
+          "debug": false,
+          "defaultSubtasks": 5,
+          "defaultPriority": "medium",
+          "defaultTag": "master",
+          "projectName": "Your Project Name",
+          "ollamaBaseURL": "http://localhost:11434/api",
+          "azureBaseURL": "https://your-endpoint.azure.com/openai/deployments",
+          "vertexProjectId": "your-gcp-project-id",
+          "vertexLocation": "us-central1"
+        }
+      }
+      ```
+
+
+2.  **Legacy `.taskmasterconfig` File (Backward Compatibility)**
+
+    - For projects that haven't migrated to the new structure yet.
+    - **Location:** Project root directory.
+    - **Migration:** Use `task-master migrate` to move this to `.taskmaster/config.json`.
+    - **Deprecation:** While still supported, you'll see warnings encouraging migration to the new structure.
+
+## Environment Variables (`.env` file or MCP `env` block - For API Keys Only)
+
+- Used **exclusively** for sensitive API keys and specific endpoint URLs.
+- **Location:**
+  - For CLI usage: Create a `.env` file in your project root.
+  - For MCP/Cursor usage: Configure keys in the `env` section of your `.cursor/mcp.json` file.
+- **Required API Keys (Depending on configured providers):**
+  - `ANTHROPIC_API_KEY`: Your Anthropic API key.
+  - `PERPLEXITY_API_KEY`: Your Perplexity API key.
+  - `OPENAI_API_KEY`: Your OpenAI API key.
+  - `GOOGLE_API_KEY`: Your Google API key (also used for Vertex AI provider).
+  - `MISTRAL_API_KEY`: Your Mistral API key.
+  - `AZURE_OPENAI_API_KEY`: Your Azure OpenAI API key (also requires `AZURE_OPENAI_ENDPOINT`).
+  - `OPENROUTER_API_KEY`: Your OpenRouter API key.
+  - `XAI_API_KEY`: Your X-AI API key.
+- **Optional Endpoint Overrides:**
+  - **Per-role `baseURL` in `.taskmasterconfig`:** You can add a `baseURL` property to any model role (`main`, `research`, `fallback`) to override the default API endpoint for that provider. If omitted, the provider's standard endpoint is used.
+  - **Environment Variable Overrides (`<PROVIDER>_BASE_URL`):** For greater flexibility, especially with third-party services, you can set an environment variable like `OPENAI_BASE_URL` or `MISTRAL_BASE_URL`. This will override any `baseURL` set in the configuration file for that provider. This is the recommended way to connect to OpenAI-compatible APIs.
+  - `AZURE_OPENAI_ENDPOINT`: Required if using Azure OpenAI key (can also be set as `baseURL` for the Azure model role).
+  - `OLLAMA_BASE_URL`: Override the default Ollama API URL (Default: `http://localhost:11434/api`).
+  - `VERTEX_PROJECT_ID`: Your Google Cloud project ID for Vertex AI. Required when using the 'vertex' provider.
+  - `VERTEX_LOCATION`: Google Cloud region for Vertex AI (e.g., 'us-central1'). Default is 'us-central1'.
+  - `GOOGLE_APPLICATION_CREDENTIALS`: Path to service account credentials JSON file for Google Cloud auth (alternative to API key for Vertex AI).
+
+**Important:** Settings like model ID selections (`main`, `research`, `fallback`), `maxTokens`, `temperature`, `logLevel`, `defaultSubtasks`, `defaultPriority`, and `projectName` are **managed in `.taskmaster/config.json`** (or `.taskmasterconfig` for unmigrated projects), not environment variables.
+
+## Tagged Task Lists Configuration (v0.17+)
+
+Taskmaster includes a tagged task lists system for multi-context task management.
+
+### Global Tag Settings
+
+```json
+"global": {
+  "defaultTag": "master"
+}
+```
+
+- **`defaultTag`** (string): Default tag context for new operations (default: "master")
+
+### Git Integration
+
+Task Master provides manual git integration through the `--from-branch` option:
+
+- **Manual Tag Creation**: Use `task-master add-tag --from-branch` to create a tag based on your current git branch name
+- **User Control**: No automatic tag switching - you control when and how tags are created
+- **Flexible Workflow**: Supports any git workflow without imposing rigid branch-tag mappings
+
+## State Management File
+
+Taskmaster uses `.taskmaster/state.json` to track tagged system runtime information:
+
+```json
+{
+  "currentTag": "master",
+  "lastSwitched": "2025-06-11T20:26:12.598Z",
+  "migrationNoticeShown": true
+}
+```
+
+- **`currentTag`**: Currently active tag context
+- **`lastSwitched`**: Timestamp of last tag switch
+- **`migrationNoticeShown`**: Whether migration notice has been displayed
+
+This file is automatically created during tagged system migration and should not be manually edited.
+
+## Example `.env` File (for API Keys)
+
+```
+# Required API keys for providers configured in .taskmaster/config.json
+ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
+PERPLEXITY_API_KEY=pplx-your-key-here
+# OPENAI_API_KEY=sk-your-key-here
+# GOOGLE_API_KEY=AIzaSy...
+# AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
+# etc.
+
+# Optional Endpoint Overrides
+# Use a specific provider's base URL, e.g., for an OpenAI-compatible API
+# OPENAI_BASE_URL=https://api.third-party.com/v1
+#
+# Azure OpenAI Configuration
+# AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/ or https://your-endpoint-name.cognitiveservices.azure.com/openai/deployments
+# OLLAMA_BASE_URL=http://custom-ollama-host:11434/api
+
+# Google Vertex AI Configuration (Required if using 'vertex' provider)
+# VERTEX_PROJECT_ID=your-gcp-project-id
+```
+
+## Troubleshooting
+
+### Configuration Errors
+
+- If Task Master reports errors about missing configuration or cannot find the config file, run `task-master models --setup` in your project root to create or repair the file.
+- For new projects, config will be created at `.taskmaster/config.json`. For legacy projects, you may want to use `task-master migrate` to move to the new structure.
+- Ensure API keys are correctly placed in your `.env` file (for CLI) or `.cursor/mcp.json` (for MCP) and are valid for the providers selected in your config file.
+
+### If `task-master init` doesn't respond:
+
+Try running it with Node directly:
+
+```bash
+node node_modules/claude-task-master/scripts/init.js
+```
+
+Or clone the repository and run:
+
+```bash
+git clone https://github.com/eyaltoledano/claude-task-master.git
+cd claude-task-master
+node scripts/init.js
+```
+
+## Provider-Specific Configuration
+
+### Google Vertex AI Configuration
+
+Google Vertex AI is Google Cloud's enterprise AI platform and requires specific configuration:
+
+1. **Prerequisites**:
+   - A Google Cloud account with Vertex AI API enabled
+   - Either a Google API key with Vertex AI permissions OR a service account with appropriate roles
+   - A Google Cloud project ID
+2. **Authentication Options**:
+   - **API Key**: Set the `GOOGLE_API_KEY` environment variable
+   - **Service Account**: Set `GOOGLE_APPLICATION_CREDENTIALS` to point to your service account JSON file
+3. **Required Configuration**:
+   - Set `VERTEX_PROJECT_ID` to your Google Cloud project ID
+   - Set `VERTEX_LOCATION` to your preferred Google Cloud region (default: us-central1)
+4. **Example Setup**:
+
+   ```bash
+   # In .env file
+   GOOGLE_API_KEY=AIzaSyXXXXXXXXXXXXXXXXXXXXXXXXX
+   VERTEX_PROJECT_ID=my-gcp-project-123
+   VERTEX_LOCATION=us-central1
+   ```
+
+   Or using service account:
+
+   ```bash
+   # In .env file
+   GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
+   VERTEX_PROJECT_ID=my-gcp-project-123
+   VERTEX_LOCATION=us-central1
+   ```
+
+5. **In .taskmaster/config.json**:
+   ```json
+   "global": {
+     "vertexProjectId": "my-gcp-project-123",
+     "vertexLocation": "us-central1"
+   }
+   ```
+
+### Azure OpenAI Configuration
+
+Azure OpenAI provides enterprise-grade OpenAI models through Microsoft's Azure cloud platform and requires specific configuration:
+
+1. **Prerequisites**:
+   - An Azure account with an active subscription
+   - Azure OpenAI service resource created in the Azure portal
+   - Azure OpenAI API key and endpoint URL
+   - Deployed models (e.g., gpt-4o, gpt-4o-mini, gpt-4.1, etc) in your Azure OpenAI resource
+
+2. **Authentication**:
+   - Set the `AZURE_OPENAI_API_KEY` environment variable with your Azure OpenAI API key
+   - Configure the endpoint URL using one of the methods below
+
+3. **Configuration Options**:
+
+   **Option 1: Using Global Azure Base URL (affects all Azure models)**
+   ```json
+   // In .taskmaster/config.json
+   {
+     "models": {
+       "main": {
+         "provider": "azure",
+         "modelId": "gpt-4o",
+         "maxTokens": 16000,
+         "temperature": 0.7
+       },
+       "fallback": {
+         "provider": "azure", 
+         "modelId": "gpt-4o-mini",
+         "maxTokens": 10000,
+         "temperature": 0.7
+       }
+     },
+     "global": {
+       "azureBaseURL": "https://your-resource-name.azure.com/openai/deployments"
+     }
+   }
+   ```
+
+   **Option 2: Using Per-Model Base URLs (recommended for flexibility)**
+   ```json
+   // In .taskmaster/config.json
+   {
+     "models": {
+       "main": {
+         "provider": "azure",
+         "modelId": "gpt-4o", 
+         "maxTokens": 16000,
+         "temperature": 0.7,
+         "baseURL": "https://your-resource-name.azure.com/openai/deployments"
+       },
+       "research": {
+         "provider": "perplexity",
+         "modelId": "sonar-pro",
+         "maxTokens": 8700,
+         "temperature": 0.1
+       },
+       "fallback": {
+         "provider": "azure",
+         "modelId": "gpt-4o-mini",
+         "maxTokens": 10000, 
+         "temperature": 0.7,
+         "baseURL": "https://your-resource-name.azure.com/openai/deployments"
+       }
+     }
+   }
+   ```
+
+4. **Environment Variables**:
+   ```bash
+   # In .env file
+   AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
+   
+   # Optional: Override endpoint for all Azure models
+   AZURE_OPENAI_ENDPOINT=https://your-resource-name.azure.com/openai/deployments
+   ```
+
+5. **Important Notes**:
+   - **Model Deployment Names**: The `modelId` in your configuration should match the **deployment name** you created in Azure OpenAI Studio, not the underlying model name
+   - **Base URL Priority**: Per-model `baseURL` settings override the global `azureBaseURL` setting
+   - **Endpoint Format**: When using per-model `baseURL`, use the full path including `/openai/deployments`
+
+6. **Troubleshooting**:
+
+   **"Resource not found" errors:**
+   - Ensure your `baseURL` includes the full path: `https://your-resource-name.openai.azure.com/openai/deployments`
+   - Verify that your deployment name in `modelId` exactly matches what's configured in Azure OpenAI Studio
+   - Check that your Azure OpenAI resource is in the correct region and properly deployed
+
+   **Authentication errors:**
+   - Verify your `AZURE_OPENAI_API_KEY` is correct and has not expired
+   - Ensure your Azure OpenAI resource has the necessary permissions
+   - Check that your subscription has not been suspended or reached quota limits
+
+   **Model availability errors:**
+   - Confirm the model is deployed in your Azure OpenAI resource
+   - Verify the deployment name matches your configuration exactly (case-sensitive)
+   - Ensure the model deployment is in a "Succeeded" state in Azure OpenAI Studio
+   - Ensure youre not getting rate limited by `maxTokens` maintain appropriate Tokens per Minute Rate Limit (TPM) in your deployment.

apps/docs/best-practices/index.mdx

@@ -0,0 +1,8 @@
+---
+title: Intro to Advanced Usage
+sidebarTitle: "Advanced Usage"
+---
+
+# Best Practices
+
+Explore advanced tips, recommended workflows, and best practices for getting the most out of Task Master. 

apps/docs/capabilities/cli-root-commands.mdx

@@ -0,0 +1,209 @@
+---
+title: CLI Commands
+sidebarTitle: "CLI Commands"
+---
+
+
+<AccordionGroup>
+  <Accordion title="Parse PRD">
+    ```bash
+    # Parse a PRD file and generate tasks
+    task-master parse-prd <prd-file.txt>
+
+    # Limit the number of tasks generated
+    task-master parse-prd <prd-file.txt> --num-tasks=10
+    ```
+  </Accordion>
+
+  <Accordion title="List Tasks">
+    ```bash
+    # List all tasks
+    task-master list
+
+    # List tasks with a specific status
+    task-master list --status=<status>
+
+    # List tasks with subtasks
+    task-master list --with-subtasks
+
+    # List tasks with a specific status and include subtasks
+    task-master list --status=<status> --with-subtasks
+    ```
+  </Accordion>
+
+  <Accordion title="Show Next Task">
+    ```bash
+    # Show the next task to work on based on dependencies and status
+    task-master next
+    ```
+  </Accordion>
+
+  <Accordion title="Show Specific Task">
+    ```bash
+    # Show details of a specific task
+    task-master show <id>
+    # or
+    task-master show --id=<id>
+
+    # View a specific subtask (e.g., subtask 2 of task 1)
+    task-master show 1.2
+    ```
+  </Accordion>
+
+  <Accordion title="Update Tasks">
+    ```bash
+    # Update tasks from a specific ID and provide context
+    task-master update --from=<id> --prompt="<prompt>"
+    ```
+  </Accordion>
+
+  <Accordion title="Update a Specific Task">
+    ```bash
+    # Update a single task by ID with new information
+    task-master update-task --id=<id> --prompt="<prompt>"
+
+    # Use research-backed updates with Perplexity AI
+    task-master update-task --id=<id> --prompt="<prompt>" --research
+    ```
+  </Accordion>
+
+  <Accordion title="Update a Subtask">
+    ```bash
+    # Append additional information to a specific subtask
+    task-master update-subtask --id=<parentId.subtaskId> --prompt="<prompt>"
+
+    # Example: Add details about API rate limiting to subtask 2 of task 5
+    task-master update-subtask --id=5.2 --prompt="Add rate limiting of 100 requests per minute"
+
+    # Use research-backed updates with Perplexity AI
+    task-master update-subtask --id=<parentId.subtaskId> --prompt="<prompt>" --research
+    ```
+
+    Unlike the `update-task` command which replaces task information, the `update-subtask` command _appends_ new information to the existing subtask details, marking it with a timestamp. This is useful for iteratively enhancing subtasks while preserving the original content.
+  </Accordion>
+
+  <Accordion title="Generate Task Files">
+    ```bash
+    # Generate individual task files from tasks.json
+    task-master generate
+    ```
+  </Accordion>
+
+  <Accordion title="Set Task Status">
+    ```bash
+    # Set status of a single task
+    task-master set-status --id=<id> --status=<status>
+
+    # Set status for multiple tasks
+    task-master set-status --id=1,2,3 --status=<status>
+
+    # Set status for subtasks
+    task-master set-status --id=1.1,1.2 --status=<status>
+    ```
+
+    When marking a task as "done", all of its subtasks will automatically be marked as "done" as well.
+  </Accordion>
+
+  <Accordion title="Expand Tasks">
+    ```bash
+    # Expand a specific task with subtasks
+    task-master expand --id=<id> --num=<number>
+
+    # Expand with additional context
+    task-master expand --id=<id> --prompt="<context>"
+
+    # Expand all pending tasks
+    task-master expand --all
+
+    # Force regeneration of subtasks for tasks that already have them
+    task-master expand --all --force
+
+    # Research-backed subtask generation for a specific task
+    task-master expand --id=<id> --research
+
+    # Research-backed generation for all tasks
+    task-master expand --all --research
+    ```
+  </Accordion>
+
+  <Accordion title="Clear Subtasks">
+    ```bash
+    # Clear subtasks from a specific task
+    task-master clear-subtasks --id=<id>
+
+    # Clear subtasks from multiple tasks
+    task-master clear-subtasks --id=1,2,3
+
+    # Clear subtasks from all tasks
+    task-master clear-subtasks --all
+    ```
+  </Accordion>
+
+  <Accordion title="Analyze Task Complexity">
+    ```bash
+    # Analyze complexity of all tasks
+    task-master analyze-complexity
+
+    # Save report to a custom location
+    task-master analyze-complexity --output=my-report.json
+
+    # Use a specific LLM model
+    task-master analyze-complexity --model=claude-3-opus-20240229
+
+    # Set a custom complexity threshold (1-10)
+    task-master analyze-complexity --threshold=6
+
+    # Use an alternative tasks file
+    task-master analyze-complexity --file=custom-tasks.json
+
+    # Use Perplexity AI for research-backed complexity analysis
+    task-master analyze-complexity --research
+    ```
+  </Accordion>
+
+  <Accordion title="View Complexity Report">
+    ```bash
+    # Display the task complexity analysis report
+    task-master complexity-report
+
+    # View a report at a custom location
+    task-master complexity-report --file=my-report.json
+    ```
+  </Accordion>
+
+  <Accordion title="Managing Task Dependencies">
+    ```bash
+    # Add a dependency to a task
+    task-master add-dependency --id=<id> --depends-on=<id>
+
+    # Remove a dependency from a task
+    task-master remove-dependency --id=<id> --depends-on=<id>
+
+    # Validate dependencies without fixing them
+    task-master validate-dependencies
+
+    # Find and fix invalid dependencies automatically
+    task-master fix-dependencies
+    ```
+  </Accordion>
+
+  <Accordion title="Add a New Task">
+    ```bash
+    # Add a new task using AI
+    task-master add-task --prompt="Description of the new task"
+
+    # Add a task with dependencies
+    task-master add-task --prompt="Description" --dependencies=1,2,3
+
+    # Add a task with priority
+    task-master add-task --prompt="Description" --priority=high
+    ```
+  </Accordion>
+
+  <Accordion title="Initialize a Project">
+    ```bash
+    # Initialize a new project with Task Master structure
+    task-master init
+    ```
+  </Accordion>
+</AccordionGroup>

apps/docs/capabilities/index.mdx

@@ -0,0 +1,241 @@
+---
+title: Technical Capabilities
+sidebarTitle: "Technical Capabilities"
+---
+
+# Capabilities (Technical)
+
+Discover the technical capabilities of Task Master, including supported models, integrations, and more. 
+
+# CLI Interface Synopsis
+
+This document outlines the command-line interface (CLI) for the Task Master application, as defined in `bin/task-master.js` and the `scripts/modules/commands.js` file (which I will assume exists based on the context). This guide is intended for those writing user-facing documentation to understand how users interact with the application from the command line.
+
+## Entry Point
+
+The main entry point for the CLI is the `task-master` command, which is an executable script that spawns the main application logic in `scripts/dev.js`.
+
+## Global Options
+
+The following options are available for all commands:
+
+-   `-h, --help`: Display help information.
+-   `--version`: Display the application's version.
+
+## Commands
+
+The CLI is organized into a series of commands, each with its own set of options. The following is a summary of the available commands, categorized by their functionality.
+
+### 1. Task and Subtask Management
+
+-   **`add`**: Creates a new task using an AI-powered prompt.
+    -   `--prompt <prompt>`: The prompt to use for generating the task.
+    -   `--dependencies <dependencies>`: A comma-separated list of task IDs that this task depends on.
+    -   `--priority <priority>`: The priority of the task (e.g., `high`, `medium`, `low`).
+-   **`add-subtask`**: Adds a subtask to a parent task.
+    -   `--parent-id <parentId>`: The ID of the parent task.
+    -   `--task-id <taskId>`: The ID of an existing task to convert to a subtask.
+    -   `--title <title>`: The title of the new subtask.
+-   **`remove`**: Removes one or more tasks or subtasks.
+    -   `--ids <ids>`: A comma-separated list of task or subtask IDs to remove.
+-   **`remove-subtask`**: Removes a subtask from its parent.
+    -   `--id <subtaskId>`: The ID of the subtask to remove (in the format `parentId.subtaskId`).
+    -   `--convert-to-task`: Converts the subtask to a standalone task.
+-   **`update`**: Updates multiple tasks starting from a specific ID.
+    -   `--from <fromId>`: The ID of the task to start updating from.
+    -   `--prompt <prompt>`: The new context to apply to the tasks.
+-   **`update-task`**: Updates a single task.
+    -   `--id <taskId>`: The ID of the task to update.
+    -   `--prompt <prompt>`: The new context to apply to the task.
+-   **`update-subtask`**: Appends information to a subtask.
+    -   `--id <subtaskId>`: The ID of the subtask to update (in the format `parentId.subtaskId`).
+    -   `--prompt <prompt>`: The information to append to the subtask.
+-   **`move`**: Moves a task or subtask.
+    -   `--from <sourceId>`: The ID of the task or subtask to move.
+    -   `--to <destinationId>`: The destination ID.
+-   **`clear-subtasks`**: Clears all subtasks from one or more tasks.
+    -   `--ids <ids>`: A comma-separated list of task IDs.
+
+### 2. Task Information and Status
+
+-   **`list`**: Lists all tasks.
+    -   `--status <status>`: Filters tasks by status.
+    -   `--with-subtasks`: Includes subtasks in the list.
+-   **`show`**: Shows the details of a specific task.
+    -   `--id <taskId>`: The ID of the task to show.
+-   **`next`**: Shows the next task to work on.
+-   **`set-status`**: Sets the status of a task or subtask.
+    -   `--id <id>`: The ID of the task or subtask.
+    -   `--status <status>`: The new status.
+
+### 3. Task Analysis and Expansion
+
+-   **`parse-prd`**: Parses a PRD to generate tasks.
+    -   `--file <file>`: The path to the PRD file.
+    -   `--num-tasks <numTasks>`: The number of tasks to generate.
+-   **`expand`**: Expands a task into subtasks.
+    -   `--id <taskId>`: The ID of the task to expand.
+    -   `--num-subtasks <numSubtasks>`: The number of subtasks to generate.
+-   **`expand-all`**: Expands all eligible tasks.
+    -   `--num-subtasks <numSubtasks>`: The number of subtasks to generate for each task.
+-   **`analyze-complexity`**: Analyzes task complexity.
+    -   `--file <file>`: The path to the tasks file.
+-   **`complexity-report`**: Displays the complexity analysis report.
+
+### 4. Project and Configuration
+
+-   **`init`**: Initializes a new project.
+-   **`generate`**: Generates individual task files.
+-   **`migrate`**: Migrates a project to the new directory structure.
+-   **`research`**: Performs AI-powered research.
+    -   `--query <query>`: The research query.
+
+This synopsis provides a comprehensive overview of the CLI commands and their options, which should be helpful for creating user-facing documentation.
+
+
+# Core Implementation Synopsis
+
+This document provides a high-level overview of the core implementation of the Task Master application, focusing on the functionalities exposed through `scripts/modules/task-manager.js`. This serves as a guide for understanding the application's capabilities when writing user-facing documentation.
+
+## Core Concepts
+
+The application revolves around the management of tasks and subtasks, which are stored in a `tasks.json` file. The core logic provides functionalities to create, read, update, and delete tasks and subtasks, as well as manage their dependencies and statuses.
+
+### Task Structure
+
+A task is a JSON object with the following key properties:
+
+-   `id`: A unique number identifying the task.
+-   `title`: A string representing the task's title.
+-   `description`: A string providing a brief description of the task.
+-   `details`: A string containing detailed information about the task.
+-   `testStrategy`: A string describing how to test the task.
+-   `status`: A string representing the task's current status (e.g., `pending`, `in-progress`, `done`).
+-   `dependencies`: An array of task IDs that this task depends on.
+-   `priority`: A string representing the task's priority (e.g., `high`, `medium`, `low`).
+-   `subtasks`: An array of subtask objects.
+
+A subtask has a similar structure to a task but is nested within a parent task.
+
+## Feature Categories
+
+The core functionalities can be categorized as follows:
+
+### 1. Task and Subtask Management
+
+These functions are the bread and butter of the application, allowing for the creation, modification, and deletion of tasks and subtasks.
+
+-   **`addTask(prompt, dependencies, priority)`**: Creates a new task using an AI-powered prompt to generate the title, description, details, and test strategy. It can also be used to create a task manually by providing the task data directly.
+-   **`addSubtask(parentId, existingTaskId, newSubtaskData)`**: Adds a subtask to a parent task. It can either convert an existing task into a subtask or create a new subtask from scratch.
+-   **`removeTask(taskIds)`**: Removes one or more tasks or subtasks.
+-   **`removeSubtask(subtaskId, convertToTask)`**: Removes a subtask from its parent. It can optionally convert the subtask into a standalone task.
+-   **`updateTaskById(taskId, prompt)`**: Updates a task's information based on a prompt.
+-   **`updateSubtaskById(subtaskId, prompt)`**: Appends additional information to a subtask's details.
+-   **`updateTasks(fromId, prompt)`**: Updates multiple tasks starting from a specific ID based on a new context.
+-   **`moveTask(sourceId, destinationId)`**: Moves a task or subtask to a new position.
+-   **`clearSubtasks(taskIds)`**: Clears all subtasks from one or more tasks.
+
+### 2. Task Information and Status
+
+These functions are used to retrieve information about tasks and manage their status.
+
+-   **`listTasks(statusFilter, withSubtasks)`**: Lists all tasks, with options to filter by status and include subtasks.
+-   **`findTaskById(taskId)`**: Finds a task by its ID.
+-   **`taskExists(taskId)`**: Checks if a task with a given ID exists.
+-   **`setTaskStatus(taskIdInput, newStatus)`**: Sets the status of a task or subtask.
+-al
+-   **`updateSingleTaskStatus(taskIdInput, newStatus)`**: A helper function to update the status of a single task or subtask.
+-   **`findNextTask()`**: Determines the next task to work on based on dependencies and status.
+
+### 3. Task Analysis and Expansion
+
+These functions leverage AI to analyze and break down tasks.
+
+-   **`parsePRD(prdPath, numTasks)`**: Parses a Product Requirements Document (PRD) to generate an initial set of tasks.
+-   **`expandTask(taskId, numSubtasks)`**: Expands a task into a specified number of subtasks using AI.
+-   **`expandAllTasks(numSubtasks)`**: Expands all eligible pending or in-progress tasks.
+-   **`analyzeTaskComplexity(options)`**: Analyzes the complexity of tasks and generates recommendations for expansion.
+-   **`readComplexityReport()`**: Reads the complexity analysis report.
+
+### 4. Dependency Management
+
+These functions are crucial for managing the relationships between tasks.
+
+-   **`isTaskDependentOn(task, targetTaskId)`**: Checks if a task has a direct or indirect dependency on another task.
+
+### 5. Project and Configuration
+
+These functions are for managing the project and its configuration.
+
+-   **`generateTaskFiles()`**: Generates individual task files from `tasks.json`.
+-   **`migrateProject()`**: Migrates the project to the new `.taskmaster` directory structure.
+-   **`performResearch(query, options)`**: Performs AI-powered research with project context.
+
+This overview should provide a solid foundation for creating user-facing documentation. For more detailed information on each function, refer to the source code in `scripts/modules/task-manager/`.
+
+
+# MCP Interface Synopsis
+
+This document provides an overview of the MCP (Machine-to-Machine Communication Protocol) interface for the Task Master application. The MCP interface is defined in the `mcp-server/` directory and exposes the application's core functionalities as a set of tools that can be called remotely.
+
+## Core Concepts
+
+The MCP interface is built on top of the `fastmcp` library and registers a set of tools that correspond to the core functionalities of the Task Master application. These tools are defined in the `mcp-server/src/tools/` directory and are registered with the MCP server in `mcp-server/src/tools/index.js`.
+
+Each tool is defined with a name, a description, and a set of parameters that are validated using the `zod` library. The `execute` function of each tool calls the corresponding core logic function from `scripts/modules/task-manager.js`.
+
+## Tool Categories
+
+The MCP tools can be categorized in the same way as the core functionalities:
+
+### 1. Task and Subtask Management
+
+-   **`add_task`**: Creates a new task.
+-   **`add_subtask`**: Adds a subtask to a parent task.
+-   **`remove_task`**: Removes one or more tasks or subtasks.
+-   **`remove_subtask`**: Removes a subtask from its parent.
+-   **`update_task`**: Updates a single task.
+-   **`update_subtask`**: Appends information to a subtask.
+-   **`update`**: Updates multiple tasks.
+-   **`move_task`**: Moves a task or subtask.
+-   **`clear_subtasks`**: Clears all subtasks from one or more tasks.
+
+### 2. Task Information and Status
+
+-   **`get_tasks`**: Lists all tasks.
+-   **`get_task`**: Shows the details of a specific task.
+-   **`next_task`**: Shows the next task to work on.
+-   **`set_task_status`**: Sets the status of a task or subtask.
+
+### 3. Task Analysis and Expansion
+
+-   **`parse_prd`**: Parses a PRD to generate tasks.
+-   **`expand_task`**: Expands a task into subtasks.
+-   **`expand_all`**: Expands all eligible tasks.
+-   **`analyze_project_complexity`**: Analyzes task complexity.
+-   **`complexity_report`**: Displays the complexity analysis report.
+
+### 4. Dependency Management
+
+-   **`add_dependency`**: Adds a dependency to a task.
+-   **`remove_dependency`**: Removes a dependency from a task.
+-   **`validate_dependencies`**: Validates the dependencies of all tasks.
+-   **`fix_dependencies`**: Fixes any invalid dependencies.
+
+### 5. Project and Configuration
+
+-   **`initialize_project`**: Initializes a new project.
+-   **`generate`**: Generates individual task files.
+-   **`models`**: Manages AI model configurations.
+-   **`research`**: Performs AI-powered research.
+
+### 6. Tag Management
+
+-   **`add_tag`**: Creates a new tag.
+-   **`delete_tag`**: Deletes a tag.
+-   **`list_tags`**: Lists all tags.
+-   **`use_tag`**: Switches to a different tag.
+-   **`rename_tag`**: Renames a tag.
+-   **`copy_tag`**: Copies a tag.
+
+This synopsis provides a clear overview of the MCP interface and its available tools, which will be valuable for anyone writing documentation for developers who need to interact with the Task Master application programmatically.

apps/docs/capabilities/mcp.mdx

@@ -0,0 +1,68 @@
+---
+title: MCP Tools
+sidebarTitle: "MCP Tools"
+---
+
+# MCP Tools
+
+This document provides an overview of the MCP (Machine-to-Machine Communication Protocol) interface for the Task Master application. The MCP interface is defined in the `mcp-server/` directory and exposes the application's core functionalities as a set of tools that can be called remotely.
+
+## Core Concepts
+
+The MCP interface is built on top of the `fastmcp` library and registers a set of tools that correspond to the core functionalities of the Task Master application. These tools are defined in the `mcp-server/src/tools/` directory and are registered with the MCP server in `mcp-server/src/tools/index.js`.
+
+Each tool is defined with a name, a description, and a set of parameters that are validated using the `zod` library. The `execute` function of each tool calls the corresponding core logic function from `scripts/modules/task-manager.js`.
+
+## Tool Categories
+
+The MCP tools can be categorized in the same way as the core functionalities:
+
+### 1. Task and Subtask Management
+
+-   **`add_task`**: Creates a new task.
+-   **`add_subtask`**: Adds a subtask to a parent task.
+-   **`remove_task`**: Removes one or more tasks or subtasks.
+-   **`remove_subtask`**: Removes a subtask from its parent.
+-   **`update_task`**: Updates a single task.
+-   **`update_subtask`**: Appends information to a subtask.
+-   **`update`**: Updates multiple tasks.
+-   **`move_task`**: Moves a task or subtask.
+-   **`clear_subtasks`**: Clears all subtasks from one or more tasks.
+
+### 2. Task Information and Status
+
+-   **`get_tasks`**: Lists all tasks.
+-   **`get_task`**: Shows the details of a specific task.
+-   **`next_task`**: Shows the next task to work on.
+-   **`set_task_status`**: Sets the status of a task or subtask.
+
+### 3. Task Analysis and Expansion
+
+-   **`parse_prd`**: Parses a PRD to generate tasks.
+-   **`expand_task`**: Expands a task into subtasks.
+-   **`expand_all`**: Expands all eligible tasks.
+-   **`analyze_project_complexity`**: Analyzes task complexity.
+-   **`complexity_report`**: Displays the complexity analysis report.
+
+### 4. Dependency Management
+
+-   **`add_dependency`**: Adds a dependency to a task.
+-   **`remove_dependency`**: Removes a dependency from a task.
+-   **`validate_dependencies`**: Validates the dependencies of all tasks.
+-   **`fix_dependencies`**: Fixes any invalid dependencies.
+
+### 5. Project and Configuration
+
+-   **`initialize_project`**: Initializes a new project.
+-   **`generate`**: Generates individual task files.
+-   **`models`**: Manages AI model configurations.
+-   **`research`**: Performs AI-powered research.
+
+### 6. Tag Management
+
+-   **`add_tag`**: Creates a new tag.
+-   **`delete_tag`**: Deletes a tag.
+-   **`list_tags`**: Lists all tags.
+-   **`use_tag`**: Switches to a different tag.
+-   **`rename_tag`**: Renames a tag.
+-   **`copy_tag`**: Copies a tag.

apps/docs/capabilities/task-structure.mdx

@@ -0,0 +1,163 @@
+---
+title: "Task Structure"
+sidebarTitle: "Task Structure"
+description: "Tasks in Task Master follow a specific format designed to provide comprehensive information for both humans and AI assistants."
+---
+
+## Task Fields in tasks.json
+
+Tasks in tasks.json have the following structure:
+
+| Field          | Description                                    | Example                                                |
+| -------------- | ---------------------------------------------- | ------------------------------------------------------ |
+| `id`           | Unique identifier for the task.                | `1`                                                    |
+| `title`        | Brief, descriptive title.                      | `"Initialize Repo"`                                    |
+| `description`  | What the task involves.                        | `"Create a new repository, set up initial structure."` |
+| `status`       | Current state.                                 | `"pending"`, `"done"`, `"deferred"`                    |
+| `dependencies` | Prerequisite task IDs. ✅ Completed, ⏱️ Pending | `[1, 2]`                                               |
+| `priority`     | Task importance.                               | `"high"`, `"medium"`, `"low"`                          |
+| `details`      | Implementation instructions.                   | `"Use GitHub client ID/secret, handle callback..."`    |
+| `testStrategy` | How to verify success.                         | `"Deploy and confirm 'Hello World' response."`         |
+| `subtasks`     | Nested subtasks related to the main task.      | `[{"id": 1, "title": "Configure OAuth", ...}]`         |
+
+## Task File Format
+
+Individual task files follow this format:
+
+```
+# Task ID: <id>
+# Title: <title>
+# Status: <status>
+# Dependencies: <comma-separated list of dependency IDs>
+# Priority: <priority>
+# Description: <brief description>
+# Details:
+<detailed implementation notes>
+
+# Test Strategy:
+<verification approach>
+```
+
+## Features in Detail
+
+<AccordionGroup>
+<Accordion title="Analyzing Task Complexity">
+The `analyze-complexity` command:
+
+- Analyzes each task using AI to assess its complexity on a scale of 1-10
+- Recommends optimal number of subtasks based on configured DEFAULT_SUBTASKS
+- Generates tailored prompts for expanding each task
+- Creates a comprehensive JSON report with ready-to-use commands
+- Saves the report to scripts/task-complexity-report.json by default
+
+The generated report contains:
+
+- Complexity analysis for each task (scored 1-10)
+- Recommended number of subtasks based on complexity
+- AI-generated expansion prompts customized for each task
+- Ready-to-run expansion commands directly within each task analysis
+</Accordion>
+
+<Accordion title="Viewing Complexity Report">
+The `complexity-report` command:
+
+- Displays a formatted, easy-to-read version of the complexity analysis report
+- Shows tasks organized by complexity score (highest to lowest)
+- Provides complexity distribution statistics (low, medium, high)
+- Highlights tasks recommended for expansion based on threshold score
+- Includes ready-to-use expansion commands for each complex task
+- If no report exists, offers to generate one on the spot
+</Accordion>
+
+<Accordion title="Smart Task Expansion">
+The `expand` command automatically checks for and uses the complexity report:
+
+When a complexity report exists:
+
+- Tasks are automatically expanded using the recommended subtask count and prompts
+- When expanding all tasks, they're processed in order of complexity (highest first)
+- Research-backed generation is preserved from the complexity analysis
+- You can still override recommendations with explicit command-line options
+
+Example workflow:
+
+```bash
+# Generate the complexity analysis report with research capabilities
+task-master analyze-complexity --research
+
+# Review the report in a readable format
+task-master complexity-report
+
+# Expand tasks using the optimized recommendations
+task-master expand --id=8
+# or expand all tasks
+task-master expand --all
+```
+</Accordion>
+
+<Accordion title="Finding the Next Task">
+The `next` command:
+
+- Identifies tasks that are pending/in-progress and have all dependencies satisfied
+- Prioritizes tasks by priority level, dependency count, and task ID
+- Displays comprehensive information about the selected task:
+  - Basic task details (ID, title, priority, dependencies)
+  - Implementation details
+  - Subtasks (if they exist)
+- Provides contextual suggested actions:
+  - Command to mark the task as in-progress
+  - Command to mark the task as done
+  - Commands for working with subtasks
+</Accordion>
+
+<Accordion title="Viewing Specific Task Details">
+The `show` command:
+
+- Displays comprehensive details about a specific task or subtask
+- Shows task status, priority, dependencies, and detailed implementation notes
+- For parent tasks, displays all subtasks and their status
+- For subtasks, shows parent task relationship
+- Provides contextual action suggestions based on the task's state
+- Works with both regular tasks and subtasks (using the format taskId.subtaskId)
+</Accordion>
+</AccordionGroup>
+
+## Best Practices for AI-Driven Development
+
+<CardGroup cols={2}>
+  <Card title="📝 Detailed PRD" icon="lightbulb">
+    The more detailed your PRD, the better the generated tasks will be.
+  </Card>
+  
+  <Card title="👀 Review Tasks" icon="magnifying-glass">
+    After parsing the PRD, review the tasks to ensure they make sense and have appropriate dependencies.
+  </Card>
+  
+  <Card title="📊 Analyze Complexity" icon="chart-line">
+    Use the complexity analysis feature to identify which tasks should be broken down further.
+  </Card>
+  
+  <Card title="⛓️ Follow Dependencies" icon="link">
+    Always respect task dependencies - the Cursor agent will help with this.
+  </Card>
+  
+  <Card title="🔄 Update As You Go" icon="arrows-rotate">
+    If your implementation diverges from the plan, use the update command to keep future tasks aligned.
+  </Card>
+  
+  <Card title="📦 Break Down Tasks" icon="boxes-stacked">
+    Use the expand command to break down complex tasks into manageable subtasks.
+  </Card>
+  
+  <Card title="🔄 Regenerate Files" icon="file-arrow-up">
+    After any updates to tasks.json, regenerate the task files to keep them in sync.
+  </Card>
+  
+  <Card title="💬 Provide Context" icon="comment">
+    When asking the Cursor agent to help with a task, provide context about what you're trying to achieve.
+  </Card>
+  
+  <Card title="✅ Validate Dependencies" icon="circle-check">
+    Periodically run the validate-dependencies command to check for invalid or circular dependencies.
+  </Card>
+</CardGroup>

apps/docs/docs.json

@@ -0,0 +1,83 @@
+{
+	"$schema": "https://mintlify.com/docs.json",
+	"theme": "mint",
+	"name": "Task Master",
+	"colors": {
+		"primary": "#3366CC",
+		"light": "#6699FF",
+		"dark": "#24478F"
+	},
+	"favicon": "/favicon.svg",
+	"navigation": {
+		"tabs": [
+			{
+				"tab": "Task Master Documentation",
+				"groups": [
+					{
+						"group": "Welcome",
+						"pages": ["introduction"]
+					},
+					{
+						"group": "Getting Started",
+						"pages": [
+							{
+								"group": "Quick Start",
+								"pages": [
+									"getting-started/quick-start/quick-start",
+									"getting-started/quick-start/requirements",
+									"getting-started/quick-start/installation",
+									"getting-started/quick-start/configuration-quick",
+									"getting-started/quick-start/prd-quick",
+									"getting-started/quick-start/tasks-quick",
+									"getting-started/quick-start/execute-quick"
+								]
+							},
+							"getting-started/faq",
+							"getting-started/contribute"
+						]
+					},
+					{
+						"group": "Best Practices",
+						"pages": [
+							"best-practices/index",
+							"best-practices/configuration-advanced",
+							"best-practices/advanced-tasks"
+						]
+					},
+					{
+						"group": "Technical Capabilities",
+						"pages": [
+							"capabilities/mcp",
+							"capabilities/cli-root-commands",
+							"capabilities/task-structure"
+						]
+					}
+				]
+			}
+		],
+		"global": {
+			"anchors": [
+				{
+					"anchor": "Github",
+					"href": "https://github.com/eyaltoledano/claude-task-master",
+					"icon": "github"
+				},
+				{
+					"anchor": "Discord",
+					"href": "https://discord.gg/fWJkU7rf",
+					"icon": "discord"
+				}
+			]
+		}
+	},
+	"logo": {
+		"light": "/logo/task-master-logo.png",
+		"dark": "/logo/task-master-logo.png"
+	},
+	"footer": {
+		"socials": {
+			"x": "https://x.com/TaskmasterAI",
+			"github": "https://github.com/eyaltoledano/claude-task-master"
+		}
+	}
+}

apps/docs/favicon.svg

@@ -0,0 +1,9 @@
+<svg width="100" height="100" viewBox="0 0 100 100" xmlns="http://www.w3.org/2000/svg">
+  <!-- Blue form with check from logo -->
+  <rect x="16" y="10" width="68" height="80" rx="9" fill="#3366CC"/>
+  <polyline points="33,44 41,55 56,29" fill="none" stroke="#FFFFFF" stroke-width="6"/>
+  <circle cx="33" cy="64" r="4" fill="#FFFFFF"/>
+  <rect x="43" y="61" width="27" height="6" fill="#FFFFFF"/>
+  <circle cx="33" cy="77" r="4" fill="#FFFFFF"/>
+  <rect x="43" y="75" width="27" height="6" fill="#FFFFFF"/>
+</svg>

apps/docs/getting-started/contribute.mdx

@@ -0,0 +1,335 @@
+# Contributing to Task Master
+
+Thank you for your interest in contributing to Task Master! We're excited to work with you and appreciate your help in making this project better. 🚀
+
+## 🤝 Our Collaborative Approach
+
+We're a **PR-friendly team** that values collaboration:
+
+- ✅ **We review PRs quickly** - Usually within hours, not days
+- ✅ **We're super reactive** - Expect fast feedback and engagement
+- ✅ **We sometimes take over PRs** - If your contribution is valuable but needs cleanup, we might jump in to help finish it
+- ✅ **We're open to all contributions** - From bug fixes to major features
+
+**We don't mind AI-generated code**, but we do expect you to:
+
+- ✅ **Review and understand** what the AI generated
+- ✅ **Test the code thoroughly** before submitting
+- ✅ **Ensure it's well-written** and follows our patterns
+- ❌ **Don't submit "AI slop"** - untested, unreviewed AI output
+
+> **Why this matters**: We spend significant time reviewing PRs. Help us help you by submitting quality contributions that save everyone time!
+
+## 🚀 Quick Start for Contributors
+
+### 1. Fork and Clone
+
+```bash
+git clone https://github.com/YOUR_USERNAME/claude-task-master.git
+cd claude-task-master
+npm install
+```
+
+### 2. Create a Feature Branch
+
+**Important**: Always target the `next` branch, not `main`:
+
+```bash
+git checkout next
+git pull origin next
+git checkout -b feature/your-feature-name
+```
+
+### 3. Make Your Changes
+
+Follow our development guidelines below.
+
+### 4. Test Everything Yourself
+
+**Before submitting your PR**, ensure:
+
+```bash
+# Run all tests
+npm test
+
+# Check formatting
+npm run format-check
+
+# Fix formatting if needed
+npm run format
+```
+
+### 5. Create a Changeset
+
+**Required for most changes**:
+
+```bash
+npm run changeset
+```
+
+See the [Changeset Guidelines](#changeset-guidelines) below for details.
+
+### 6. Submit Your PR
+
+- Target the `next` branch
+- Write a clear description
+- Reference any related issues
+
+## 📋 Development Guidelines
+
+### Branch Strategy
+
+- **`main`**: Production-ready code
+- **`next`**: Development branch - **target this for PRs**
+- **Feature branches**: `feature/description` or `fix/description`
+
+### Code Quality Standards
+
+1. **Write tests** for new functionality
+2. **Follow existing patterns** in the codebase
+3. **Add JSDoc comments** for functions
+4. **Keep functions focused** and single-purpose
+
+### Testing Requirements
+
+Your PR **must pass all CI checks**:
+
+- ✅ **Unit tests**: `npm test`
+- ✅ **Format check**: `npm run format-check`
+
+**Test your changes locally first** - this saves review time and shows you care about quality.
+
+## 📦 Changeset Guidelines
+
+We use [Changesets](https://github.com/changesets/changesets) to manage versioning and generate changelogs.
+
+### When to Create a Changeset
+
+**Always create a changeset for**:
+
+- ✅ New features
+- ✅ Bug fixes
+- ✅ Breaking changes
+- ✅ Performance improvements
+- ✅ User-facing documentation updates
+- ✅ Dependency updates that affect functionality
+
+**Skip changesets for**:
+
+- ❌ Internal documentation only
+- ❌ Test-only changes
+- ❌ Code formatting/linting
+- ❌ Development tooling that doesn't affect users
+
+### How to Create a Changeset
+
+1. **After making your changes**:
+
+   ```bash
+   npm run changeset
+   ```
+
+2. **Choose the bump type**:
+
+   - **Major**: Breaking changes
+   - **Minor**: New features
+   - **Patch**: Bug fixes, docs, performance improvements
+
+3. **Write a clear summary**:
+
+   ```
+   Add support for custom AI models in MCP configuration
+   ```
+
+4. **Commit the changeset file** with your changes:
+   ```bash
+   git add .changeset/*.md
+   git commit -m "feat: add custom AI model support"
+   ```
+
+### Changeset vs Git Commit Messages
+
+- **Changeset summary**: User-facing, goes in CHANGELOG.md
+- **Git commit**: Developer-facing, explains the technical change
+
+Example:
+
+```bash
+# Changeset summary (user-facing)
+"Add support for custom Ollama models"
+
+# Git commit message (developer-facing)
+"feat(models): implement custom Ollama model validation
+
+- Add model validation for custom Ollama endpoints
+- Update configuration schema to support custom models
+- Add tests for new validation logic"
+```
+
+## 🔧 Development Setup
+
+### Prerequisites
+
+- Node.js 18+
+- npm or yarn
+
+### Environment Setup
+
+1. **Copy environment template**:
+
+   ```bash
+   cp .env.example .env
+   ```
+
+2. **Add your API keys** (for testing AI features):
+   ```bash
+   ANTHROPIC_API_KEY=your_key_here
+   OPENAI_API_KEY=your_key_here
+   # Add others as needed
+   ```
+
+### Running Tests
+
+```bash
+# Run all tests
+npm test
+
+# Run tests in watch mode
+npm run test:watch
+
+# Run with coverage
+npm run test:coverage
+
+# Run E2E tests
+npm run test:e2e
+```
+
+### Code Formatting
+
+We use Prettier for consistent formatting:
+
+```bash
+# Check formatting
+npm run format-check
+
+# Fix formatting
+npm run format
+```
+
+## 📝 PR Guidelines
+
+### Before Submitting
+
+- [ ] **Target the `next` branch**
+- [ ] **Test everything locally**
+- [ ] **Run the full test suite**
+- [ ] **Check code formatting**
+- [ ] **Create a changeset** (if needed)
+- [ ] **Re-read your changes** - ensure they're clean and well-thought-out
+
+### PR Description Template
+
+```markdown
+## Description
+
+Brief description of what this PR does.
+
+## Type of Change
+
+- [ ] Bug fix
+- [ ] New feature
+- [ ] Breaking change
+- [ ] Documentation update
+
+## Testing
+
+- [ ] I have tested this locally
+- [ ] All existing tests pass
+- [ ] I have added tests for new functionality
+
+## Changeset
+
+- [ ] I have created a changeset (or this change doesn't need one)
+
+## Additional Notes
+
+Any additional context or notes for reviewers.
+```
+
+### What We Look For
+
+✅ **Good PRs**:
+
+- Clear, focused changes
+- Comprehensive testing
+- Good commit messages
+- Proper changeset (when needed)
+- Self-reviewed code
+
+❌ **Avoid**:
+
+- Massive PRs that change everything
+- Untested code
+- Formatting issues
+- Missing changesets for user-facing changes
+- AI-generated code that wasn't reviewed
+
+## 🏗️ Project Structure
+
+```
+claude-task-master/
+├── bin/                    # CLI executables
+├── mcp-server/            # MCP server implementation
+├── scripts/               # Core task management logic
+├── src/                   # Shared utilities and providers and well refactored code (we are slowly moving everything here)
+├── tests/                 # Test files
+├── docs/                  # Documentation
+└── .cursor/               # Cursor IDE rules and configuration
+└── assets/							   # Assets like rules and configuration for all IDEs
+```
+
+### Key Areas for Contribution
+
+- **CLI Commands**: `scripts/modules/commands.js`
+- **MCP Tools**: `mcp-server/src/tools/`
+- **Core Logic**: `scripts/modules/task-manager/`
+- **AI Providers**: `src/ai-providers/`
+- **Tests**: `tests/`
+
+## 🐛 Reporting Issues
+
+### Bug Reports
+
+Include:
+
+- Task Master version
+- Node.js version
+- Operating system
+- Steps to reproduce
+- Expected vs actual behavior
+- Error messages/logs
+
+### Feature Requests
+
+Include:
+
+- Clear description of the feature
+- Use case/motivation
+- Proposed implementation (if you have ideas)
+- Willingness to contribute
+
+## 💬 Getting Help
+
+- **Discord**: [Join our community](https://discord.gg/taskmasterai)
+- **Issues**: [GitHub Issues](https://github.com/eyaltoledano/claude-task-master/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/eyaltoledano/claude-task-master/discussions)
+
+## 📄 License
+
+By contributing, you agree that your contributions will be licensed under the same license as the project (MIT with Commons Clause).
+
+---
+
+**Thank you for contributing to Task Master!** 🎉
+
+Your contributions help make AI-driven development more accessible and efficient for everyone.

apps/docs/getting-started/faq.mdx

@@ -0,0 +1,12 @@
+---
+title: FAQ
+sidebarTitle: "FAQ"
+---
+
+Coming soon. 
+
+## 💬 Getting Help
+
+- **Discord**: [Join our community](https://discord.gg/taskmasterai)
+- **Issues**: [GitHub Issues](https://github.com/eyaltoledano/claude-task-master/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/eyaltoledano/claude-task-master/discussions)

apps/docs/getting-started/quick-start/configuration-quick.mdx

@@ -0,0 +1,112 @@
+---
+title: Configuration
+sidebarTitle: "Configuration"
+
+---
+
+Before getting started with Task Master, you'll need to set up your API keys. There are a couple of ways to do this depending on whether you're using the CLI or working inside MCP. It's also a good time to start getting familiar with the other configuration options available — even if you don’t need to adjust them yet, knowing what’s possible will help down the line.
+
+## API Key Setup
+
+Task Master uses environment variables to securely store provider API keys and optional endpoint URLs.
+
+### MCP Usage: mcp.json file
+
+For MCP/Cursor usage: Configure keys in the env section of your .cursor/mcp.json file.
+
+```java .env lines icon="java"
+{
+	"mcpServers": {
+		"task-master-ai": {
+			"command": "node",
+			"args": ["./mcp-server/server.js"],
+			"env": {
+				"ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY_HERE",
+				"PERPLEXITY_API_KEY": "PERPLEXITY_API_KEY_HERE",
+				"OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
+				"GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
+				"XAI_API_KEY": "XAI_API_KEY_HERE",
+				"OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
+				"MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
+				"AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
+				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE",
+				"GITHUB_API_KEY": "GITHUB_API_KEY_HERE"
+			}
+		}
+	}
+}
+```
+
+### CLI Usage: `.env` File
+
+Create a `.env` file in your project root and include the keys for the providers you plan to use:
+
+
+
+```java .env lines icon="java"
+# Required API keys for providers configured in .taskmaster/config.json
+ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
+PERPLEXITY_API_KEY=pplx-your-key-here
+# OPENAI_API_KEY=sk-your-key-here
+# GOOGLE_API_KEY=AIzaSy...
+# AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
+# etc.
+
+# Optional Endpoint Overrides
+# Use a specific provider's base URL, e.g., for an OpenAI-compatible API
+# OPENAI_BASE_URL=https://api.third-party.com/v1
+#
+# Azure OpenAI Configuration
+# AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/ or https://your-endpoint-name.cognitiveservices.azure.com/openai/deployments
+# OLLAMA_BASE_URL=http://custom-ollama-host:11434/api
+
+# Google Vertex AI Configuration (Required if using 'vertex' provider)
+# VERTEX_PROJECT_ID=your-gcp-project-id
+```
+
+## What Else Can Be Configured?
+
+The main configuration file (`.taskmaster/config.json`) allows you to control nearly every aspect of Task Master’s behavior. Here’s a high-level look at what you can customize:
+
+<Tip>
+You don’t need to configure everything up front. Most settings can be left as defaults or updated later as your workflow evolves.
+</Tip>
+
+<Accordion title="View Configuration Options">
+
+### Models and Providers
+- Role-based model setup: `main`, `research`, `fallback`
+- Provider selection (Anthropic, OpenAI, Perplexity, etc.)
+- Model IDs per role
+- Temperature, max tokens, and other generation settings
+- Custom base URLs for OpenAI-compatible APIs
+
+### Global Settings
+- `logLevel`: Logging verbosity
+- `debug`: Enable/disable debug mode
+- `projectName`: Optional name for your project
+- `defaultTag`: Default tag for task grouping
+- `defaultSubtasks`: Number of subtasks to auto-generate
+- `defaultPriority`: Priority level for new tasks
+
+### API Endpoint Overrides
+- `ollamaBaseURL`: Custom Ollama server URL
+- `azureBaseURL`: Global Azure endpoint
+- `vertexProjectId`: Google Vertex AI project ID
+- `vertexLocation`: Region for Vertex AI models
+
+### Tag and Git Integration
+- Default tag context per project
+- Support for task isolation by tag
+- Manual tag creation from Git branches
+
+### State Management
+- Active tag tracking
+- Migration state
+- Last tag switch timestamp
+
+</Accordion>
+
+<Note>
+For advanced configuration options and detailed customization, see our [Advanced Configuration Guide](/docs/best-practices/configuration-advanced) page.
+</Note>

apps/docs/getting-started/quick-start/execute-quick.mdx

@@ -0,0 +1,59 @@
+---
+title: Executing Tasks
+sidebarTitle: "Executing Tasks"
+---
+
+Now that your tasks are generated and reviewed you are ready to begin executing.
+
+## Select the Task to Work on: Next Task
+
+Task Master has the "next" command to find the next task to work on. You can access it with the following request:
+```
+What's the next task I should work on? Please consider dependencies and priorities.
+```
+Alternatively you can use the CLI to show the next task
+```bash
+task-master next
+```
+
+## Discuss Task
+When you know what task to work on next you can then start chatting with the agent to make sure it understands the plan of action.
+
+You can tag relevant files and folders so it knows what context to pull up as it generates its plan. For example:
+```
+Please review Task 5 and confirm you understand how to execute before beginning. Refer to @models @api and @schema 
+```
+The agent will begin analyzing the task and files and respond with the steps to complete the task. 
+
+## Agent Task execution
+
+If you agree with the plan of action, tell the agent to get started.
+```
+You may begin. I believe in you.
+```
+
+## Review and Test
+
+Once the agent is finished with the task you can refer to the task testing strategy to make sure it was completed correctly.
+
+## Update Task Status
+
+If the task was completed correctly you can update the status to done
+
+```
+Please mark Task 5 as done
+```
+The agent will execute
+```bash
+task-master set-status --id=5 --status=done
+```
+
+## Rules and Context
+
+If you ran into problems and had to debug errors you can create new rules as you go. This helps build context on your codebase that helps the creation and execution of future tasks.
+
+## On to the Next Task!
+
+By now you have all you need to get started executing code faster and smarter with Task Master.
+
+If you have any questions please check out [Frequently Asked Questions](/docs/getting-started/faq)

apps/docs/getting-started/quick-start/installation.mdx

@@ -0,0 +1,159 @@
+---
+title: Installation
+sidebarTitle: "Installation"
+---
+
+Now that you have Node.js and your first API Key, you are ready to begin installing Task Master in one of three ways. 
+
+<Note>Cursor Users Can Use the One Click Install Below</Note>
+<Accordion title="Quick Install for Cursor 1.0+ (One-Click)">
+
+<a href="cursor://anysphere.cursor-deeplink/mcp/install?name=task-master-ai&config=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%3D">
+  <img 
+    className="block dark:hidden" 
+    src="https://cursor.com/deeplink/mcp-install-light.png" 
+    alt="Add Task Master MCP server to Cursor" 
+    noZoom
+  />
+  <img 
+    className="hidden dark:block" 
+    src="https://cursor.com/deeplink/mcp-install-dark.png" 
+    alt="Add Task Master MCP server to Cursor" 
+    noZoom
+  />
+</a>
+
+Or click the copy button (top-right of code block) then paste into your browser:
+
+```text
+cursor://anysphere.cursor-deeplink/mcp/install?name=taskmaster-ai&config=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
+```
+
+> **Note:** After clicking the link, you'll still need to add your API keys to the configuration. The link installs the MCP server with placeholder keys that you'll need to replace with your actual API keys.
+</Accordion>
+## Installation Options
+
+
+<Accordion title="Option 1: MCP (Recommended)">
+
+MCP (Model Control Protocol) lets you run Task Master directly from your editor.
+
+## 1. Add your MCP config at the following path depending on your editor
+
+| Editor       | Scope   | Linux/macOS Path                      | Windows Path                                      | Key          |
+| ------------ | ------- | ------------------------------------- | ------------------------------------------------- | ------------ |
+| **Cursor**   | Global  | `~/.cursor/mcp.json`                  | `%USERPROFILE%\.cursor\mcp.json`                  | `mcpServers` |
+|              | Project | `<project_folder>/.cursor/mcp.json`   | `<project_folder>\.cursor\mcp.json`               | `mcpServers` |
+| **Windsurf** | Global  | `~/.codeium/windsurf/mcp_config.json` | `%USERPROFILE%\.codeium\windsurf\mcp_config.json` | `mcpServers` |
+| **VS Code**  | Project | `<project_folder>/.vscode/mcp.json`   | `<project_folder>\.vscode\mcp.json`               | `servers`    |
+
+## Manual Configuration
+
+### Cursor & Windsurf (`mcpServers`)
+
+```json
+{
+  "mcpServers": {
+    "taskmaster-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
+        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE",
+        "OLLAMA_API_KEY": "YOUR_OLLAMA_API_KEY_HERE"
+      }
+    }
+  }
+}
+```
+
+> 🔑 Replace `YOUR_…_KEY_HERE` with your real API keys. You can remove keys you don't use.
+
+> **Note**: If you see `0 tools enabled` in the MCP settings, try removing the `--package=task-master-ai` flag from `args`.
+
+### VS Code (`servers` + `type`)
+
+```json
+{
+  "servers": {
+    "taskmaster-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
+        "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
+        "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
+        "GOOGLE_API_KEY": "YOUR_GOOGLE_KEY_HERE",
+        "MISTRAL_API_KEY": "YOUR_MISTRAL_KEY_HERE",
+        "OPENROUTER_API_KEY": "YOUR_OPENROUTER_KEY_HERE",
+        "XAI_API_KEY": "YOUR_XAI_KEY_HERE",
+        "AZURE_OPENAI_API_KEY": "YOUR_AZURE_KEY_HERE"
+      },
+      "type": "stdio"
+    }
+  }
+}
+```
+
+> 🔑 Replace `YOUR_…_KEY_HERE` with your real API keys. You can remove keys you don't use.
+
+#### 2. (Cursor-only) Enable Taskmaster MCP
+
+Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab on the left ➡ Enable task-master-ai with the toggle
+
+#### 3. (Optional) Configure the models you want to use
+
+In your editor's AI chat pane, say:
+
+```txt
+Change the main, research and fallback models to <model_name>, <model_name> and <model_name> respectively.
+```
+
+For example, to use Claude Code (no API key required):
+```txt
+Change the main model to claude-code/sonnet
+```
+
+#### 4. Initialize Task Master
+
+In your editor's AI chat pane, say:
+
+```txt
+Initialize taskmaster-ai in my project
+```
+
+</Accordion>
+
+<Accordion title="Option 2: Using Command Line">
+
+## CLI Installation
+
+```bash
+# Install globally
+npm install -g task-master-ai
+
+# OR install locally within your project
+npm install task-master-ai
+```
+
+## Initialize a new project
+
+```bash
+# If installed globally
+task-master init
+
+# If installed locally
+npx task-master init
+
+# Initialize project with specific rules
+task-master init --rules cursor,windsurf,vscode
+```
+
+This will prompt you for project details and set up a new project with the necessary files and structure.
+</Accordion>

apps/docs/getting-started/quick-start/moving-forward.mdx

@@ -0,0 +1,4 @@
+---
+title: Moving Forward
+sidebarTitle: "Moving Forward"
+---

apps/docs/getting-started/quick-start/prd-quick.mdx

@@ -0,0 +1,81 @@
+---
+title: PRD Creation and Parsing
+sidebarTitle: "PRD Creation and Parsing"
+---
+
+# Writing a PRD
+
+A PRD (Product Requirements Document) is the starting point of every task flow in Task Master. It defines what you're building and why. A clear PRD dramatically improves the quality of your tasks, your model outputs, and your final product — so it’s worth taking the time to get it right.
+
+<Tip>
+You don’t need to define your whole app up front. You can write a focused PRD just for the next feature or module you’re working on.
+</Tip>
+
+<Tip>
+You can start with an empty project or you can start with a feature PRD on an existing project.
+</Tip>
+
+<Tip>
+You can add and parse multiple PRDs per project using the --append flag
+</Tip>
+
+## What Makes a Good PRD?
+
+- Clear objective — what’s the outcome or feature?
+- Context — what’s already in place or assumed?
+- Constraints — what limits or requirements need to be respected?
+- Reasoning — why are you building it this way?
+
+The more context you give the model, the better the breakdown and results.
+
+---
+
+## Writing a PRD for Task Master
+
+<Note>An example PRD can be found in .taskmaster/templates/example_prd.txt</Note>
+
+
+You can co-write your PRD with an LLM model using the following workflow:
+
+1. **Chat about requirements** — explain what you want to build.
+2. **Show an example PRD** — share the example PRD so the model understands the expected format. The example uses formatting that work well with Task Master's code. Following the example will yield better results.
+3. **Iterate and refine** — work with the model to shape the draft into a clear and well-structured PRD.
+
+This approach works great in Cursor, or anywhere you use a chat-based LLM.
+
+---
+
+## Where to Save Your PRD
+
+Place your PRD file in the `.taskmaster/docs` folder in your project.
+
+- You can have **multiple PRDs** per project.
+- Name your PRDs clearly so they’re easy to reference later.
+  - Examples: `dashboard_redesign.txt`, `user_onboarding.txt`
+
+---
+
+# Parse your PRD into Tasks
+
+This is where the Task Master magic begins.
+
+In Cursor's AI chat, instruct the agent to generate tasks from your PRD:
+
+```
+Please use the task-master parse-prd command to generate tasks from my PRD. The PRD is located at .taskmaster/docs/<prd-name>.txt.
+```
+
+The agent will execute the following command which you can alternatively paste into the CLI:
+
+```bash
+task-master parse-prd .taskmaster/docs/<prd-name>.txt
+```
+
+This will:
+
+- Parse your PRD document
+- Generate a structured `tasks.json` file with tasks, dependencies, priorities, and test strategies
+
+Now that you have written and parsed a PRD, you are ready to start setting up your tasks.
+
+

apps/docs/getting-started/quick-start/quick-start.mdx

@@ -0,0 +1,19 @@
+---
+title: Quick Start
+sidebarTitle: "Quick Start"
+---
+
+This guide is for new users who want to start using Task Master with minimal setup time.
+
+It covers:
+- [Requirements](/docs/getting-started/quick-start/requirements): You will need Node.js and an AI model API Key.
+- [Installation](/docs/getting-started/quick-start/installation): How to Install Task Master.
+- [Configuration](/docs/getting-started/quick-start/configuration-quick): Setting up your API Key, MCP, and more.
+- [PRD](/docs/getting-started/quick-start/prd-quick): Writing and parsing your first PRD.
+- [Task Setup](/docs/getting-started/quick-start/tasks-quick): Preparing your tasks for execution.
+- [Executing Tasks](/docs/getting-started/quick-start/execute-quick): Using Task Master to execute tasks.
+- [Rules & Context](/docs/getting-started/quick-start/rules-quick): Learn how and why to build context in your project over time.
+
+<Tip>
+By the end of this guide, you'll have everything you need to begin working productively with Task Master.
+</Tip>

apps/docs/getting-started/quick-start/requirements.mdx

@@ -0,0 +1,50 @@
+---
+title: Requirements
+sidebarTitle: "Requirements"
+---
+Before you can start using TaskMaster AI, you'll need to install Node.js and set up at least one model API Key.
+
+## 1. Node.js
+
+TaskMaster AI is built with Node.js and requires it to run. npm (Node Package Manager) comes bundled with Node.js.
+
+<Accordion title="Install Node.js">
+
+### Installation
+
+**Option 1: Download from official website**
+1. Visit [nodejs.org](https://nodejs.org)
+2. Download the **LTS (Long Term Support)** version for your operating system
+3. Run the installer and follow the setup wizard
+
+**Option 2: Use a package manager**
+
+<CodeGroup>
+
+```bash Windows (Chocolatey)
+choco install nodejs
+```
+
+```bash Windows (winget)
+winget install OpenJS.NodeJS
+```
+
+</CodeGroup>
+
+</Accordion>
+
+## 2. Model API Key
+
+Taskmaster utilizes AI across several commands, and those require a separate API key. For the purpose of a Quick Start we recommend setting up an API Key with Anthropic for your main model and Perplexity for your research model (optional but recommended).
+
+<Tip>Task Master shows API costs per command used. Most users load $5-10 on their keys and don't have to top it off for a few months.</Tip>
+
+At least one (1) of the following is required:
+
+1. Anthropic API key (Claude API) - **recommended for Quick Start**
+2. OpenAI API key
+3. Google Gemini API key
+4. Perplexity API key (for research model)
+5. xAI API Key (for research or main model)
+6. OpenRouter API Key (for research or main model)
+7. Claude Code (no API key required - requires Claude Code CLI)

apps/docs/getting-started/quick-start/rules-quick.mdx

@@ -0,0 +1,4 @@
+---
+title: Rules and Context
+sidebarTitle: "Rules and Context"
+---

apps/docs/getting-started/quick-start/tasks-quick.mdx

@@ -0,0 +1,69 @@
+---
+title: Tasks Setup
+sidebarTitle: "Tasks Setup"
+---
+Now that your tasks are generated you can review the plan and prepare for execution.
+
+<Tip>
+Not all of the setup steps are required but they are recommended in order to ensure your coding agents work on accurate tasks.
+</Tip>
+
+## Expand Tasks
+Used to add detail to tasks and create subtasks. We recommend expanding all tasks using the MCP request below:
+```
+Expand all tasks into subtasks.
+```
+The agent will execute
+```bash
+task-master expand --all
+```
+## List/Show Tasks
+
+Used to view task details. It is important to review the plan and ensure it makes sense in your project. Check for correct folder structures, dependencies, out of scope subtasks, etc.
+
+To see a list of tasks and descriptions use the following command:
+
+```
+List all pending tasks so I can review.
+```
+To see all tasks in the CLI you can use:
+```bash
+task-master list
+```
+
+To see all implementation details of an individual task, including subtasks and testing strategy, you can use Show Task:
+
+```
+Show task 2 so I can review.
+```
+
+```bash
+task-master show --id=<##>
+```
+
+## Update Tasks
+
+If the task details need to be edited you can update the task using this request: 
+
+```
+Update Task 2 to use Postgres instead of MongoDB and remove the sharding subtask
+```
+Or this CLI command:
+
+```bash
+task-master update-task --id=2 --prompt="use Postgres instead of MongoDB and remove the sharding subtask"
+```
+## Analyze complexity
+
+Task Master can provide a complexity report which can be helpful to read before you begin. If you didn't already expand all your tasks, it could help identify which could be broken down further with subtasks.
+
+```
+Can you analyze the complexity of our tasks to help me understand which ones need to be broken down further?
+```
+
+You can view the report in a friendly table using:
+```
+Can you show me the complexity report in a more readable format?
+```
+
+<Check>Now you are ready to begin [executing tasks](/docs/getting-started/quick-start/execute-quick)</Check>