fix: mcp bug when expanding task (#957)

* fix: mcp bug when expanding task

* chore: fix format

.changeset/better-seas-sit.md

@@ -1,15 +0,0 @@
----
-'task-master-ai': minor
----
-
-Added comprehensive Ollama model validation and interactive setup support
-
-- **Interactive Setup Enhancement**: Added "Custom Ollama model" option to `task-master models --setup`, matching the existing OpenRouter functionality
-- **Live Model Validation**: When setting Ollama models, Taskmaster now validates against the local Ollama instance by querying `/api/tags` endpoint
-- **Configurable Endpoints**: Uses the `ollamaBaseUrl` from `.taskmasterconfig` (with role-specific `baseUrl` overrides supported)
-- **Robust Error Handling**: 
-  - Detects when Ollama server is not running and provides clear error messages
-  - Validates model existence and lists available alternatives when model not found
-  - Graceful fallback behavior for connection issues
-- **Full Platform Support**: Both MCP server tools and CLI commands support the new validation
-- **Improved User Experience**: Clear feedback during model validation with informative success/error messages

.changeset/claude-code-json-truncation.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Recover from `@anthropic-ai/claude-code` JSON truncation bug that caused Task Master to crash when handling large (>8 kB) structured responses.  The CLI/SDK still truncates, but Task Master now detects the error, preserves buffered text, and returns a usable response instead of throwing. 

.changeset/cuddly-baboons-invent.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Updating dependency ai-sdk-provider-gemini-cli to 0.0.4 to address breaking change Google made to Gemini CLI and add better 'api-key' in addition to 'gemini-api-key' AI-SDK compatibility.

.changeset/cuddly-walls-clap.md

@@ -1,9 +0,0 @@
----
-'task-master-ai': minor
----
-
-Adds and updates supported AI models with costs:
-- Added new OpenRouter models: GPT-4.1 series, O3, Codex Mini, Llama 4 Maverick, Llama 4 Scout, Qwen3-235b
-- Added Mistral models: Devstral Small, Mistral Nemo
-- Updated Ollama models with latest variants: Devstral, Qwen3, Mistral-small3.1, Llama3.3
-- Updated Gemini model to latest 2.5 Flash preview version

.changeset/curly-melons-call.md

@@ -1,15 +0,0 @@
----
-'task-master-ai': minor
----
-
-Add `--research` flag to parse-prd command, enabling enhanced task generation from PRD files. When used, Taskmaster leverages the research model to:
-
-- Research current technologies and best practices relevant to the project
-- Identify technical challenges and security concerns not explicitly mentioned in the PRD
-- Include specific library recommendations with version numbers
-- Provide more detailed implementation guidance based on industry standards
-- Create more accurate dependency relationships between tasks
-
-This results in higher quality, more actionable tasks with minimal additional effort.
-
-*NOTE* That this is an experimental feature. Research models don't typically do great at structured output. You may find some failures when using research mode, so please share your feedback so we can improve this.

.changeset/dark-otters-sip.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Adjusts default main model model to Claude Sonnet 4. Adjusts default fallback to Claude Sonney 3.7"

.changeset/fuzzy-worlds-wish.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Adds llms-install.md to the root to enable AI agents to programmatically install the Taskmaster MCP server. This is specifically being introduced for the Cline MCP marketplace and will be adjusted over time for other MCP clients as needed.

.changeset/gentle-parents-film.md

@@ -1,9 +0,0 @@
----
-'task-master-ai': minor
----
-
-This change significantly enhances the `add-task` command's intelligence. When you add a new task, Taskmaster now automatically:
-    - Analyzes your existing tasks to find those most relevant to your new task's description.
-    - Provides the AI with detailed context from these relevant tasks.
-
-This results in newly created tasks being more accurately placed within your project's dependency structure, saving you time and any need to update tasks just for dependencies, all without significantly increasing AI costs. You'll get smarter, more connected tasks right from the start.

.changeset/grok-4-support.md

@@ -0,0 +1,9 @@
+---
+"task-master-ai": minor
+---
+
+Add support for xAI Grok 4 model
+
+- Add grok-4 model to xAI provider with $3/$15 per 1M token pricing
+- Enable main, fallback, and research roles for grok-4
+- Max tokens set to 131,072 (matching other xAI models)

.changeset/loud-bobcats-tap.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Adds AGENTS.md to power Claude Code integration more natively based on Anthropic's best practice and Claude-specific MCP client behaviours. Also adds in advanced workflows that tie Taskmaster commands together into one Claude workflow."

.changeset/metal-forks-yawn.md

@@ -1,7 +0,0 @@
----
-'task-master-ai': minor
----
-
-Enhance analyze-complexity to support analyzing specific task IDs. 
-    - You can now analyze individual tasks or selected task groups by using the new `--id` option with comma-separated IDs, or `--from` and `--to` options to specify a range of tasks. 
-    - The feature intelligently merges analysis results with existing reports, allowing incremental analysis while preserving previous results.

.changeset/modern-parks-fly.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Fixes issue with force/append flag combinations for parse-prd.

.changeset/petite-walls-learn.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-You can now add tasks to a newly initialized project without having to parse a prd. This will automatically create the missing tasks.json file and create the first task. Lets you vibe if you want to vibe."

.changeset/quick-laws-cover.md

@@ -0,0 +1,8 @@
+---
+"task-master-ai": minor
+---
+
+Add stricter validation and clearer feedback for task priority when adding new tasks
+
+- if a task priority is invalid, it will default to medium
+- made taks priority case-insensitive, essentially making HIGH and high the same value

.changeset/some-lies-grin.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": minor
+---
+
+Add support for MCP Sampling as AI provider, requires no API key, uses the client LLM provider

.changeset/spicy-badgers-fail.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Unify and streamline profile system architecture for improved maintainability

.changeset/tall-mails-sing.md

@@ -1,5 +0,0 @@
----
-'task-master-ai': patch
----
-
-Fixes an issue where the research fallback would attempt to make API calls without checking for a valid API key first. This ensures proper error handling when the main task generation and first fallback both fail. Closes #421 #519.

.changeset/tender-ads-joke.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": minor
+---
+
+Added Groq provider support

.changeset/wild-seas-read.md

@@ -1,29 +0,0 @@
----
-'task-master-ai': minor
----
-
-Add move command to enable moving tasks and subtasks within the task hierarchy. This new command supports moving standalone tasks to become subtasks, subtasks to become standalone tasks, and moving subtasks between different parents. The implementation handles circular dependencies, validation, and proper updating of parent-child relationships.
-
-**Usage:**
-- CLI command: `task-master move --from=<id> --to=<id>`
-- MCP tool: `move_task` with parameters:
-  - `from`: ID of task/subtask to move (e.g., "5" or "5.2")
-  - `to`: ID of destination (e.g., "7" or "7.3")
-  - `file` (optional): Custom path to tasks.json
-
-**Example scenarios:**
-- Move task to become subtask: `--from="5" --to="7"`
-- Move subtask to standalone task: `--from="5.2" --to="7"`
-- Move subtask to different parent: `--from="5.2" --to="7.3"`
-- Reorder subtask within same parent: `--from="5.2" --to="5.4"`
-- Move multiple tasks at once: `--from="10,11,12" --to="16,17,18"`
-- Move task to new ID: `--from="5" --to="25"` (creates a new task with ID 25)
-
-**Multiple Task Support:**
-The command supports moving multiple tasks simultaneously by providing comma-separated lists for both `--from` and `--to` parameters. The number of source and destination IDs must match. This is particularly useful for resolving merge conflicts in task files when multiple team members have created tasks on different branches.
-
-**Validation Features:**
-- Allows moving tasks to new, non-existent IDs (automatically creates placeholders)
-- Prevents moving to existing task IDs that already contain content (to avoid overwriting)
-- Validates source tasks exist before attempting to move them
-- Ensures proper parent-child relationships are maintained

.claude/TM_COMMANDS_GUIDE.md

@@ -0,0 +1,147 @@
+# Task Master Commands for Claude Code
+
+Complete guide to using Task Master through Claude Code's slash commands.
+
+## Overview
+
+All Task Master functionality is available through the `/project:tm/` namespace with natural language support and intelligent features.
+
+## Quick Start
+
+```bash
+# Install Task Master
+/project:tm/setup/quick-install
+
+# Initialize project
+/project:tm/init/quick
+
+# Parse requirements
+/project:tm/parse-prd requirements.md
+
+# Start working
+/project:tm/next
+```
+
+## Command Structure
+
+Commands are organized hierarchically to match Task Master's CLI:
+- Main commands at `/project:tm/[command]`
+- Subcommands for specific operations `/project:tm/[command]/[subcommand]`
+- Natural language arguments accepted throughout
+
+## Complete Command Reference
+
+### Setup & Configuration
+- `/project:tm/setup/install` - Full installation guide
+- `/project:tm/setup/quick-install` - One-line install
+- `/project:tm/init` - Initialize project
+- `/project:tm/init/quick` - Quick init with -y
+- `/project:tm/models` - View AI config
+- `/project:tm/models/setup` - Configure AI
+
+### Task Generation
+- `/project:tm/parse-prd` - Generate from PRD
+- `/project:tm/parse-prd/with-research` - Enhanced parsing
+- `/project:tm/generate` - Create task files
+
+### Task Management
+- `/project:tm/list` - List with natural language filters
+- `/project:tm/list/with-subtasks` - Hierarchical view
+- `/project:tm/list/by-status <status>` - Filter by status
+- `/project:tm/show <id>` - Task details
+- `/project:tm/add-task` - Create task
+- `/project:tm/update` - Update tasks
+- `/project:tm/remove-task` - Delete task
+
+### Status Management
+- `/project:tm/set-status/to-pending <id>`
+- `/project:tm/set-status/to-in-progress <id>`
+- `/project:tm/set-status/to-done <id>`
+- `/project:tm/set-status/to-review <id>`
+- `/project:tm/set-status/to-deferred <id>`
+- `/project:tm/set-status/to-cancelled <id>`
+
+### Task Analysis
+- `/project:tm/analyze-complexity` - AI analysis
+- `/project:tm/complexity-report` - View report
+- `/project:tm/expand <id>` - Break down task
+- `/project:tm/expand/all` - Expand all complex
+
+### Dependencies
+- `/project:tm/add-dependency` - Add dependency
+- `/project:tm/remove-dependency` - Remove dependency
+- `/project:tm/validate-dependencies` - Check issues
+- `/project:tm/fix-dependencies` - Auto-fix
+
+### Workflows
+- `/project:tm/workflows/smart-flow` - Adaptive workflows
+- `/project:tm/workflows/pipeline` - Chain commands
+- `/project:tm/workflows/auto-implement` - AI implementation
+
+### Utilities
+- `/project:tm/status` - Project dashboard
+- `/project:tm/next` - Next task recommendation
+- `/project:tm/utils/analyze` - Project analysis
+- `/project:tm/learn` - Interactive help
+
+## Key Features
+
+### Natural Language Support
+All commands understand natural language:
+```
+/project:tm/list pending high priority
+/project:tm/update mark 23 as done
+/project:tm/add-task implement OAuth login
+```
+
+### Smart Context
+Commands analyze project state and provide intelligent suggestions based on:
+- Current task status
+- Dependencies
+- Team patterns
+- Project phase
+
+### Visual Enhancements
+- Progress bars and indicators
+- Status badges
+- Organized displays
+- Clear hierarchies
+
+## Common Workflows
+
+### Daily Development
+```
+/project:tm/workflows/smart-flow morning
+/project:tm/next
+/project:tm/set-status/to-in-progress <id>
+/project:tm/set-status/to-done <id>
+```
+
+### Task Breakdown
+```
+/project:tm/show <id>
+/project:tm/expand <id>
+/project:tm/list/with-subtasks
+```
+
+### Sprint Planning
+```
+/project:tm/analyze-complexity
+/project:tm/workflows/pipeline init → expand/all → status
+```
+
+## Migration from Old Commands
+
+| Old | New |
+|-----|-----|
+| `/project:task-master:list` | `/project:tm/list` |
+| `/project:task-master:complete` | `/project:tm/set-status/to-done` |
+| `/project:workflows:auto-implement` | `/project:tm/workflows/auto-implement` |
+
+## Tips
+
+1. Use `/project:tm/` + Tab for command discovery
+2. Natural language is supported everywhere
+3. Commands provide smart defaults
+4. Chain commands for automation
+5. Check `/project:tm/learn` for interactive help

.claude/commands/tm/add-dependency/index.md

@@ -0,0 +1,55 @@
+Add a dependency between tasks.
+
+Arguments: $ARGUMENTS
+
+Parse the task IDs to establish dependency relationship.
+
+## Adding Dependencies
+
+Creates a dependency where one task must be completed before another can start.
+
+## Argument Parsing
+
+Parse natural language or IDs:
+- "make 5 depend on 3" → task 5 depends on task 3
+- "5 needs 3" → task 5 depends on task 3
+- "5 3" → task 5 depends on task 3
+- "5 after 3" → task 5 depends on task 3
+
+## Execution
+
+```bash
+task-master add-dependency --id=<task-id> --depends-on=<dependency-id>
+```
+
+## Validation
+
+Before adding:
+1. **Verify both tasks exist**
+2. **Check for circular dependencies**
+3. **Ensure dependency makes logical sense**
+4. **Warn if creating complex chains**
+
+## Smart Features
+
+- Detect if dependency already exists
+- Suggest related dependencies
+- Show impact on task flow
+- Update task priorities if needed
+
+## Post-Addition
+
+After adding dependency:
+1. Show updated dependency graph
+2. Identify any newly blocked tasks
+3. Suggest task order changes
+4. Update project timeline
+
+## Example Flows
+
+```
+/project:tm/add-dependency 5 needs 3
+→ Task #5 now depends on Task #3
+→ Task #5 is now blocked until #3 completes
+→ Suggested: Also consider if #5 needs #4
+```

.claude/commands/tm/add-subtask/from-task.md

@@ -0,0 +1,71 @@
+Convert an existing task into a subtask.
+
+Arguments: $ARGUMENTS
+
+Parse parent ID and task ID to convert.
+
+## Task Conversion
+
+Converts an existing standalone task into a subtask of another task.
+
+## Argument Parsing
+
+- "move task 8 under 5"
+- "make 8 a subtask of 5"
+- "nest 8 in 5"
+- "5 8" → make task 8 a subtask of task 5
+
+## Execution
+
+```bash
+task-master add-subtask --parent=<parent-id> --task-id=<task-to-convert>
+```
+
+## Pre-Conversion Checks
+
+1. **Validation**
+   - Both tasks exist and are valid
+   - No circular parent relationships
+   - Task isn't already a subtask
+   - Logical hierarchy makes sense
+
+2. **Impact Analysis**
+   - Dependencies that will be affected
+   - Tasks that depend on converting task
+   - Priority alignment needed
+   - Status compatibility
+
+## Conversion Process
+
+1. Change task ID from "8" to "5.1" (next available)
+2. Update all dependency references
+3. Inherit parent's context where appropriate
+4. Adjust priorities if needed
+5. Update time estimates
+
+## Smart Features
+
+- Preserve task history
+- Maintain dependencies
+- Update all references
+- Create conversion log
+
+## Example
+
+```
+/project:tm/add-subtask/from-task 5 8
+→ Converting: Task #8 becomes subtask #5.1
+→ Updated: 3 dependency references
+→ Parent task #5 now has 1 subtask
+→ Note: Subtask inherits parent's priority
+
+Before: #8 "Implement validation" (standalone)
+After:  #5.1 "Implement validation" (subtask of #5)
+```
+
+## Post-Conversion
+
+- Show new task hierarchy
+- List updated dependencies
+- Verify project integrity
+- Suggest related conversions

.claude/commands/tm/add-subtask/index.md

@@ -0,0 +1,76 @@
+Add a subtask to a parent task.
+
+Arguments: $ARGUMENTS
+
+Parse arguments to create a new subtask or convert existing task.
+
+## Adding Subtasks
+
+Creates subtasks to break down complex parent tasks into manageable pieces.
+
+## Argument Parsing
+
+Flexible natural language:
+- "add subtask to 5: implement login form"
+- "break down 5 with: setup, implement, test"
+- "subtask for 5: handle edge cases"
+- "5: validate user input" → adds subtask to task 5
+
+## Execution Modes
+
+### 1. Create New Subtask
+```bash
+task-master add-subtask --parent=<id> --title="<title>" --description="<desc>"
+```
+
+### 2. Convert Existing Task
+```bash
+task-master add-subtask --parent=<id> --task-id=<existing-id>
+```
+
+## Smart Features
+
+1. **Automatic Subtask Generation**
+   - If title contains "and" or commas, create multiple
+   - Suggest common subtask patterns
+   - Inherit parent's context
+
+2. **Intelligent Defaults**
+   - Priority based on parent
+   - Appropriate time estimates
+   - Logical dependencies between subtasks
+
+3. **Validation**
+   - Check parent task complexity
+   - Warn if too many subtasks
+   - Ensure subtask makes sense
+
+## Creation Process
+
+1. Parse parent task context
+2. Generate subtask with ID like "5.1"
+3. Set appropriate defaults
+4. Link to parent task
+5. Update parent's time estimate
+
+## Example Flows
+
+```
+/project:tm/add-subtask to 5: implement user authentication
+→ Created subtask #5.1: "implement user authentication"
+→ Parent task #5 now has 1 subtask
+→ Suggested next subtasks: tests, documentation
+
+/project:tm/add-subtask 5: setup, implement, test
+→ Created 3 subtasks:
+  #5.1: setup
+  #5.2: implement  
+  #5.3: test
+```
+
+## Post-Creation
+
+- Show updated task hierarchy
+- Suggest logical next subtasks
+- Update complexity estimates
+- Recommend subtask order

.claude/commands/tm/add-task/index.md

@@ -0,0 +1,78 @@
+Add new tasks with intelligent parsing and context awareness.
+
+Arguments: $ARGUMENTS
+
+## Smart Task Addition
+
+Parse natural language to create well-structured tasks.
+
+### 1. **Input Understanding**
+
+I'll intelligently parse your request:
+- Natural language → Structured task
+- Detect priority from keywords (urgent, ASAP, important)
+- Infer dependencies from context
+- Suggest complexity based on description
+- Determine task type (feature, bug, refactor, test, docs)
+
+### 2. **Smart Parsing Examples**
+
+**"Add urgent task to fix login bug"**
+→ Title: Fix login bug
+→ Priority: high
+→ Type: bug
+→ Suggested complexity: medium
+
+**"Create task for API documentation after task 23 is done"**
+→ Title: API documentation
+→ Dependencies: [23]
+→ Type: documentation
+→ Priority: medium
+
+**"Need to refactor auth module - depends on 12 and 15, high complexity"**
+→ Title: Refactor auth module
+→ Dependencies: [12, 15]
+→ Complexity: high
+→ Type: refactor
+
+### 3. **Context Enhancement**
+
+Based on current project state:
+- Suggest related existing tasks
+- Warn about potential conflicts
+- Recommend dependencies
+- Propose subtasks if complex
+
+### 4. **Interactive Refinement**
+
+```yaml
+Task Preview:
+─────────────
+Title: [Extracted title]
+Priority: [Inferred priority]
+Dependencies: [Detected dependencies]
+Complexity: [Estimated complexity]
+
+Suggestions:
+- Similar task #34 exists, consider as dependency?
+- This seems complex, break into subtasks?
+- Tasks #45-47 work on same module
+```
+
+### 5. **Validation & Creation**
+
+Before creating:
+- Validate dependencies exist
+- Check for duplicates
+- Ensure logical ordering
+- Verify task completeness
+
+### 6. **Smart Defaults**
+
+Intelligent defaults based on:
+- Task type patterns
+- Team conventions
+- Historical data
+- Current sprint/phase
+
+Result: High-quality tasks from minimal input.

.claude/commands/tm/analyze-complexity/index.md

@@ -0,0 +1,121 @@
+Analyze task complexity and generate expansion recommendations.
+
+Arguments: $ARGUMENTS
+
+Perform deep analysis of task complexity across the project.
+
+## Complexity Analysis
+
+Uses AI to analyze tasks and recommend which ones need breakdown.
+
+## Execution Options
+
+```bash
+task-master analyze-complexity [--research] [--threshold=5]
+```
+
+## Analysis Parameters
+
+- `--research` → Use research AI for deeper analysis
+- `--threshold=5` → Only flag tasks above complexity 5
+- Default: Analyze all pending tasks
+
+## Analysis Process
+
+### 1. **Task Evaluation**
+For each task, AI evaluates:
+- Technical complexity
+- Time requirements
+- Dependency complexity
+- Risk factors
+- Knowledge requirements
+
+### 2. **Complexity Scoring**
+Assigns score 1-10 based on:
+- Implementation difficulty
+- Integration challenges
+- Testing requirements
+- Unknown factors
+- Technical debt risk
+
+### 3. **Recommendations**
+For complex tasks:
+- Suggest expansion approach
+- Recommend subtask breakdown
+- Identify risk areas
+- Propose mitigation strategies
+
+## Smart Analysis Features
+
+1. **Pattern Recognition**
+   - Similar task comparisons
+   - Historical complexity accuracy
+   - Team velocity consideration
+   - Technology stack factors
+
+2. **Contextual Factors**
+   - Team expertise
+   - Available resources
+   - Timeline constraints
+   - Business criticality
+
+3. **Risk Assessment**
+   - Technical risks
+   - Timeline risks
+   - Dependency risks
+   - Knowledge gaps
+
+## Output Format
+
+```
+Task Complexity Analysis Report
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+
+High Complexity Tasks (>7):
+📍 #5 "Implement real-time sync" - Score: 9/10
+   Factors: WebSocket complexity, state management, conflict resolution
+   Recommendation: Expand into 5-7 subtasks
+   Risks: Performance, data consistency
+
+📍 #12 "Migrate database schema" - Score: 8/10
+   Factors: Data migration, zero downtime, rollback strategy
+   Recommendation: Expand into 4-5 subtasks
+   Risks: Data loss, downtime
+
+Medium Complexity Tasks (5-7):
+📍 #23 "Add export functionality" - Score: 6/10
+   Consider expansion if timeline tight
+
+Low Complexity Tasks (<5):
+✅ 15 tasks - No expansion needed
+
+Summary:
+- Expand immediately: 2 tasks
+- Consider expanding: 5 tasks
+- Keep as-is: 15 tasks
+```
+
+## Actionable Output
+
+For each high-complexity task:
+1. Complexity score with reasoning
+2. Specific expansion suggestions
+3. Risk mitigation approaches
+4. Recommended subtask structure
+
+## Integration
+
+Results are:
+- Saved to `.taskmaster/reports/complexity-analysis.md`
+- Used by expand command
+- Inform sprint planning
+- Guide resource allocation
+
+## Next Steps
+
+After analysis:
+```
+/project:tm/expand 5    # Expand specific task
+/project:tm/expand/all  # Expand all recommended
+/project:tm/complexity-report  # View detailed report
+```

.claude/commands/tm/clear-subtasks/all.md

@@ -0,0 +1,93 @@
+Clear all subtasks from all tasks globally.
+
+## Global Subtask Clearing
+
+Remove all subtasks across the entire project. Use with extreme caution.
+
+## Execution
+
+```bash
+task-master clear-subtasks --all
+```
+
+## Pre-Clear Analysis
+
+1. **Project-Wide Summary**
+   ```
+   Global Subtask Summary
+   ━━━━━━━━━━━━━━━━━━━━
+   Total parent tasks: 12
+   Total subtasks: 47
+   - Completed: 15
+   - In-progress: 8
+   - Pending: 24
+   
+   Work at risk: ~120 hours
+   ```
+
+2. **Critical Warnings**
+   - In-progress subtasks that will lose work
+   - Completed subtasks with valuable history
+   - Complex dependency chains
+   - Integration test results
+
+## Double Confirmation
+
+```
+⚠️  DESTRUCTIVE OPERATION WARNING ⚠️
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+This will remove ALL 47 subtasks from your project
+Including 8 in-progress and 15 completed subtasks
+
+This action CANNOT be undone
+
+Type 'CLEAR ALL SUBTASKS' to confirm:
+```
+
+## Smart Safeguards
+
+- Require explicit confirmation phrase
+- Create automatic backup
+- Log all removed data
+- Option to export first
+
+## Use Cases
+
+Valid reasons for global clear:
+- Project restructuring
+- Major pivot in approach
+- Starting fresh breakdown
+- Switching to different task organization
+
+## Process
+
+1. Full project analysis
+2. Create backup file
+3. Show detailed impact
+4. Require confirmation
+5. Execute removal
+6. Generate summary report
+
+## Alternative Suggestions
+
+Before clearing all:
+- Export subtasks to file
+- Clear only pending subtasks
+- Clear by task category
+- Archive instead of delete
+
+## Post-Clear Report
+
+```
+Global Subtask Clear Complete
+━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Removed: 47 subtasks from 12 tasks
+Backup saved: .taskmaster/backup/subtasks-20240115.json
+Parent tasks updated: 12
+Time estimates adjusted: Yes
+
+Next steps:
+- Review updated task list
+- Re-expand complex tasks as needed
+- Check project timeline
+```

.claude/commands/tm/clear-subtasks/index.md

@@ -0,0 +1,86 @@
+Clear all subtasks from a specific task.
+
+Arguments: $ARGUMENTS (task ID)
+
+Remove all subtasks from a parent task at once.
+
+## Clearing Subtasks
+
+Bulk removal of all subtasks from a parent task.
+
+## Execution
+
+```bash
+task-master clear-subtasks --id=<task-id>
+```
+
+## Pre-Clear Analysis
+
+1. **Subtask Summary**
+   - Number of subtasks
+   - Completion status of each
+   - Work already done
+   - Dependencies affected
+
+2. **Impact Assessment**
+   - Data that will be lost
+   - Dependencies to be removed
+   - Effect on project timeline
+   - Parent task implications
+
+## Confirmation Required
+
+```
+Clear Subtasks Confirmation
+━━━━━━━━━━━━━━━━━━━━━━━━━
+Parent Task: #5 "Implement user authentication"
+Subtasks to remove: 4
+- #5.1 "Setup auth framework" (done)
+- #5.2 "Create login form" (in-progress)
+- #5.3 "Add validation" (pending)
+- #5.4 "Write tests" (pending)
+
+⚠️  This will permanently delete all subtask data
+Continue? (y/n)
+```
+
+## Smart Features
+
+- Option to convert to standalone tasks
+- Backup task data before clearing
+- Preserve completed work history
+- Update parent task appropriately
+
+## Process
+
+1. List all subtasks for confirmation
+2. Check for in-progress work
+3. Remove all subtasks
+4. Update parent task
+5. Clean up dependencies
+
+## Alternative Options
+
+Suggest alternatives:
+- Convert important subtasks to tasks
+- Keep completed subtasks
+- Archive instead of delete
+- Export subtask data first
+
+## Post-Clear
+
+- Show updated parent task
+- Recalculate time estimates
+- Update task complexity
+- Suggest next steps
+
+## Example
+
+```
+/project:tm/clear-subtasks 5
+→ Found 4 subtasks to remove
+→ Warning: Subtask #5.2 is in-progress
+→ Cleared all subtasks from task #5
+→ Updated parent task estimates
+→ Suggestion: Consider re-expanding with better breakdown
+```

.claude/commands/tm/complexity-report/index.md

@@ -0,0 +1,117 @@
+Display the task complexity analysis report.
+
+Arguments: $ARGUMENTS
+
+View the detailed complexity analysis generated by analyze-complexity command.
+
+## Viewing Complexity Report
+
+Shows comprehensive task complexity analysis with actionable insights.
+
+## Execution
+
+```bash
+task-master complexity-report [--file=<path>]
+```
+
+## Report Location
+
+Default: `.taskmaster/reports/complexity-analysis.md`
+Custom: Specify with --file parameter
+
+## Report Contents
+
+### 1. **Executive Summary**
+```
+Complexity Analysis Summary
+━━━━━━━━━━━━━━━━━━━━━━━━
+Analysis Date: 2024-01-15
+Tasks Analyzed: 32
+High Complexity: 5 (16%)
+Medium Complexity: 12 (37%)
+Low Complexity: 15 (47%)
+
+Critical Findings:
+- 5 tasks need immediate expansion
+- 3 tasks have high technical risk
+- 2 tasks block critical path
+```
+
+### 2. **Detailed Task Analysis**
+For each complex task:
+- Complexity score breakdown
+- Contributing factors
+- Specific risks identified
+- Expansion recommendations
+- Similar completed tasks
+
+### 3. **Risk Matrix**
+Visual representation:
+```
+Risk vs Complexity Matrix
+━━━━━━━━━━━━━━━━━━━━━━━
+High Risk  | #5(9) #12(8) | #23(6)
+Med Risk   | #34(7)       | #45(5) #67(5)
+Low Risk   | #78(8)       | [15 tasks]
+           | High Complex  | Med Complex
+```
+
+### 4. **Recommendations**
+
+**Immediate Actions:**
+1. Expand task #5 - Critical path + high complexity
+2. Expand task #12 - High risk + dependencies
+3. Review task #34 - Consider splitting
+
+**Sprint Planning:**
+- Don't schedule multiple high-complexity tasks together
+- Ensure expertise available for complex tasks
+- Build in buffer time for unknowns
+
+## Interactive Features
+
+When viewing report:
+1. **Quick Actions**
+   - Press 'e' to expand a task
+   - Press 'd' for task details
+   - Press 'r' to refresh analysis
+
+2. **Filtering**
+   - View by complexity level
+   - Filter by risk factors
+   - Show only actionable items
+
+3. **Export Options**
+   - Markdown format
+   - CSV for spreadsheets
+   - JSON for tools
+
+## Report Intelligence
+
+- Compares with historical data
+- Shows complexity trends
+- Identifies patterns
+- Suggests process improvements
+
+## Integration
+
+Use report for:
+- Sprint planning sessions
+- Resource allocation
+- Risk assessment
+- Team discussions
+- Client updates
+
+## Example Usage
+
+```
+/project:tm/complexity-report
+→ Opens latest analysis
+
+/project:tm/complexity-report --file=archived/2024-01-01.md
+→ View historical analysis
+
+After viewing:
+/project:tm/expand 5
+→ Expand high-complexity task
+```

.claude/commands/tm/expand/all.md

@@ -0,0 +1,51 @@
+Expand all pending tasks that need subtasks.
+
+## Bulk Task Expansion
+
+Intelligently expands all tasks that would benefit from breakdown.
+
+## Execution
+
+```bash
+task-master expand --all
+```
+
+## Smart Selection
+
+Only expands tasks that:
+- Are marked as pending
+- Have high complexity (>5)
+- Lack existing subtasks
+- Would benefit from breakdown
+
+## Expansion Process
+
+1. **Analysis Phase**
+   - Identify expansion candidates
+   - Group related tasks
+   - Plan expansion strategy
+
+2. **Batch Processing**
+   - Expand tasks in logical order
+   - Maintain consistency
+   - Preserve relationships
+   - Optimize for parallelism
+
+3. **Quality Control**
+   - Ensure subtask quality
+   - Avoid over-decomposition
+   - Maintain task coherence
+   - Update dependencies
+
+## Options
+
+- Add `force` to expand all regardless of complexity
+- Add `research` for enhanced AI analysis
+
+## Results
+
+After bulk expansion:
+- Summary of tasks expanded
+- New subtask count
+- Updated complexity metrics
+- Suggested task order

.claude/commands/tm/expand/index.md

@@ -0,0 +1,49 @@
+Break down a complex task into subtasks.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Intelligent Task Expansion
+
+Analyzes a task and creates detailed subtasks for better manageability.
+
+## Execution
+
+```bash
+task-master expand --id=$ARGUMENTS
+```
+
+## Expansion Process
+
+1. **Task Analysis**
+   - Review task complexity
+   - Identify components
+   - Detect technical challenges
+   - Estimate time requirements
+
+2. **Subtask Generation**
+   - Create 3-7 subtasks typically
+   - Each subtask 1-4 hours
+   - Logical implementation order
+   - Clear acceptance criteria
+
+3. **Smart Breakdown**
+   - Setup/configuration tasks
+   - Core implementation
+   - Testing components
+   - Integration steps
+   - Documentation updates
+
+## Enhanced Features
+
+Based on task type:
+- **Feature**: Setup → Implement → Test → Integrate
+- **Bug Fix**: Reproduce → Diagnose → Fix → Verify
+- **Refactor**: Analyze → Plan → Refactor → Validate
+
+## Post-Expansion
+
+After expansion:
+1. Show subtask hierarchy
+2. Update time estimates
+3. Suggest implementation order
+4. Highlight critical path

.claude/commands/tm/fix-dependencies/index.md

@@ -0,0 +1,81 @@
+Automatically fix dependency issues found during validation.
+
+## Automatic Dependency Repair
+
+Intelligently fixes common dependency problems while preserving project logic.
+
+## Execution
+
+```bash
+task-master fix-dependencies
+```
+
+## What Gets Fixed
+
+### 1. **Auto-Fixable Issues**
+- Remove references to deleted tasks
+- Break simple circular dependencies
+- Remove self-dependencies
+- Clean up duplicate dependencies
+
+### 2. **Smart Resolutions**
+- Reorder dependencies to maintain logic
+- Suggest task merging for over-dependent tasks
+- Flatten unnecessary dependency chains
+- Remove redundant transitive dependencies
+
+### 3. **Manual Review Required**
+- Complex circular dependencies
+- Critical path modifications
+- Business logic dependencies
+- High-impact changes
+
+## Fix Process
+
+1. **Analysis Phase**
+   - Run validation check
+   - Categorize issues by type
+   - Determine fix strategy
+
+2. **Execution Phase**
+   - Apply automatic fixes
+   - Log all changes made
+   - Preserve task relationships
+
+3. **Verification Phase**
+   - Re-validate after fixes
+   - Show before/after comparison
+   - Highlight manual fixes needed
+
+## Smart Features
+
+- Preserves intended task flow
+- Minimal disruption approach
+- Creates fix history/log
+- Suggests manual interventions
+
+## Output Example
+
+```
+Dependency Auto-Fix Report
+━━━━━━━━━━━━━━━━━━━━━━━━
+Fixed Automatically:
+✅ Removed 2 references to deleted tasks
+✅ Resolved 1 self-dependency
+✅ Cleaned 3 redundant dependencies
+
+Manual Review Needed:
+⚠️ Complex circular dependency: #12 → #15 → #18 → #12
+  Suggestion: Make #15 not depend on #12
+⚠️ Task #45 has 8 dependencies
+  Suggestion: Break into subtasks
+
+Run '/project:tm/validate-dependencies' to verify fixes
+```
+
+## Safety
+
+- Preview mode available
+- Rollback capability
+- Change logging
+- No data loss

.claude/commands/tm/generate/index.md

@@ -0,0 +1,121 @@
+Generate individual task files from tasks.json.
+
+## Task File Generation
+
+Creates separate markdown files for each task, perfect for AI agents or documentation.
+
+## Execution
+
+```bash
+task-master generate
+```
+
+## What It Creates
+
+For each task, generates a file like `task_001.txt`:
+
+```
+Task ID: 1
+Title: Implement user authentication
+Status: pending
+Priority: high
+Dependencies: []
+Created: 2024-01-15
+Complexity: 7
+
+## Description
+Create a secure user authentication system with login, logout, and session management.
+
+## Details
+- Use JWT tokens for session management
+- Implement secure password hashing
+- Add remember me functionality
+- Include password reset flow
+
+## Test Strategy
+- Unit tests for auth functions
+- Integration tests for login flow
+- Security testing for vulnerabilities
+- Performance tests for concurrent logins
+
+## Subtasks
+1.1 Setup authentication framework (pending)
+1.2 Create login endpoints (pending)
+1.3 Implement session management (pending)
+1.4 Add password reset (pending)
+```
+
+## File Organization
+
+Creates structure:
+```
+.taskmaster/
+└── tasks/
+    ├── task_001.txt
+    ├── task_002.txt
+    ├── task_003.txt
+    └── ...
+```
+
+## Smart Features
+
+1. **Consistent Formatting**
+   - Standardized structure
+   - Clear sections
+   - AI-readable format
+   - Markdown compatible
+
+2. **Contextual Information**
+   - Full task details
+   - Related task references
+   - Progress indicators
+   - Implementation notes
+
+3. **Incremental Updates**
+   - Only regenerate changed tasks
+   - Preserve custom additions
+   - Track generation timestamp
+   - Version control friendly
+
+## Use Cases
+
+- **AI Context**: Provide task context to AI assistants
+- **Documentation**: Standalone task documentation
+- **Archival**: Task history preservation
+- **Sharing**: Send specific tasks to team members
+- **Review**: Easier task review process
+
+## Generation Options
+
+Based on arguments:
+- Filter by status
+- Include/exclude completed
+- Custom templates
+- Different formats
+
+## Post-Generation
+
+```
+Task File Generation Complete
+━━━━━━━━━━━━━━━━━━━━━━━━━━
+Generated: 45 task files
+Location: .taskmaster/tasks/
+Total size: 156 KB
+
+New files: 5
+Updated files: 12
+Unchanged: 28
+
+Ready for:
+- AI agent consumption
+- Version control
+- Team distribution
+```
+
+## Integration Benefits
+
+- Git-trackable task history
+- Easy task sharing
+- AI tool compatibility
+- Offline task access
+- Backup redundancy

.claude/commands/tm/help.md

@@ -0,0 +1,81 @@
+Show help for Task Master commands.
+
+Arguments: $ARGUMENTS
+
+Display help for Task Master commands. If arguments provided, show specific command help.
+
+## Task Master Command Help
+
+### Quick Navigation
+
+Type `/project:tm/` and use tab completion to explore all commands.
+
+### Command Categories
+
+#### 🚀 Setup & Installation
+- `/project:tm/setup/install` - Comprehensive installation guide
+- `/project:tm/setup/quick-install` - One-line global install
+
+#### 📋 Project Setup
+- `/project:tm/init` - Initialize new project
+- `/project:tm/init/quick` - Quick setup with auto-confirm
+- `/project:tm/models` - View AI configuration
+- `/project:tm/models/setup` - Configure AI providers
+
+#### 🎯 Task Generation
+- `/project:tm/parse-prd` - Generate tasks from PRD
+- `/project:tm/parse-prd/with-research` - Enhanced parsing
+- `/project:tm/generate` - Create task files
+
+#### 📝 Task Management
+- `/project:tm/list` - List tasks (natural language filters)
+- `/project:tm/show <id>` - Display task details
+- `/project:tm/add-task` - Create new task
+- `/project:tm/update` - Update tasks naturally
+- `/project:tm/next` - Get next task recommendation
+
+#### 🔄 Status Management
+- `/project:tm/set-status/to-pending <id>`
+- `/project:tm/set-status/to-in-progress <id>`
+- `/project:tm/set-status/to-done <id>`
+- `/project:tm/set-status/to-review <id>`
+- `/project:tm/set-status/to-deferred <id>`
+- `/project:tm/set-status/to-cancelled <id>`
+
+#### 🔍 Analysis & Breakdown
+- `/project:tm/analyze-complexity` - Analyze task complexity
+- `/project:tm/expand <id>` - Break down complex task
+- `/project:tm/expand/all` - Expand all eligible tasks
+
+#### 🔗 Dependencies
+- `/project:tm/add-dependency` - Add task dependency
+- `/project:tm/remove-dependency` - Remove dependency
+- `/project:tm/validate-dependencies` - Check for issues
+
+#### 🤖 Workflows
+- `/project:tm/workflows/smart-flow` - Intelligent workflows
+- `/project:tm/workflows/pipeline` - Command chaining
+- `/project:tm/workflows/auto-implement` - Auto-implementation
+
+#### 📊 Utilities
+- `/project:tm/utils/analyze` - Project analysis
+- `/project:tm/status` - Project dashboard
+- `/project:tm/learn` - Interactive learning
+
+### Natural Language Examples
+
+```
+/project:tm/list pending high priority
+/project:tm/update mark all API tasks as done
+/project:tm/add-task create login system with OAuth
+/project:tm/show current
+```
+
+### Getting Started
+
+1. Install: `/project:tm/setup/quick-install`
+2. Initialize: `/project:tm/init/quick`
+3. Learn: `/project:tm/learn start`
+4. Work: `/project:tm/workflows/smart-flow`
+
+For detailed command info: `/project:tm/help <command-name>`

.claude/commands/tm/index.md

@@ -0,0 +1,130 @@
+# Task Master Command Reference
+
+Comprehensive command structure for Task Master integration with Claude Code.
+
+## Command Organization
+
+Commands are organized hierarchically to match Task Master's CLI structure while providing enhanced Claude Code integration.
+
+## Project Setup & Configuration
+
+### `/project:tm/init`
+- `index` - Initialize new project (handles PRD files intelligently)
+- `quick` - Quick setup with auto-confirmation (-y flag)
+
+### `/project:tm/models`
+- `index` - View current AI model configuration
+- `setup` - Interactive model configuration
+- `set-main` - Set primary generation model
+- `set-research` - Set research model
+- `set-fallback` - Set fallback model
+
+## Task Generation
+
+### `/project:tm/parse-prd`
+- `index` - Generate tasks from PRD document
+- `with-research` - Enhanced parsing with research mode
+
+### `/project:tm/generate`
+- Create individual task files from tasks.json
+
+## Task Management
+
+### `/project:tm/list`
+- `index` - Smart listing with natural language filters
+- `with-subtasks` - Include subtasks in hierarchical view
+- `by-status` - Filter by specific status
+
+### `/project:tm/set-status`
+- `to-pending` - Reset task to pending
+- `to-in-progress` - Start working on task
+- `to-done` - Mark task complete
+- `to-review` - Submit for review
+- `to-deferred` - Defer task
+- `to-cancelled` - Cancel task
+
+### `/project:tm/sync-readme`
+- Export tasks to README.md with formatting
+
+### `/project:tm/update`
+- `index` - Update tasks with natural language
+- `from-id` - Update multiple tasks from a starting point
+- `single` - Update specific task
+
+### `/project:tm/add-task`
+- `index` - Add new task with AI assistance
+
+### `/project:tm/remove-task`
+- `index` - Remove task with confirmation
+
+## Subtask Management
+
+### `/project:tm/add-subtask`
+- `index` - Add new subtask to parent
+- `from-task` - Convert existing task to subtask
+
+### `/project:tm/remove-subtask`
+- Remove subtask (with optional conversion)
+
+### `/project:tm/clear-subtasks`
+- `index` - Clear subtasks from specific task
+- `all` - Clear all subtasks globally
+
+## Task Analysis & Breakdown
+
+### `/project:tm/analyze-complexity`
+- Analyze and generate expansion recommendations
+
+### `/project:tm/complexity-report`
+- Display complexity analysis report
+
+### `/project:tm/expand`
+- `index` - Break down specific task
+- `all` - Expand all eligible tasks
+- `with-research` - Enhanced expansion
+
+## Task Navigation
+
+### `/project:tm/next`
+- Intelligent next task recommendation
+
+### `/project:tm/show`
+- Display detailed task information
+
+### `/project:tm/status`
+- Comprehensive project dashboard
+
+## Dependency Management
+
+### `/project:tm/add-dependency`
+- Add task dependency
+
+### `/project:tm/remove-dependency`
+- Remove task dependency
+
+### `/project:tm/validate-dependencies`
+- Check for dependency issues
+
+### `/project:tm/fix-dependencies`
+- Automatically fix dependency problems
+
+## Usage Patterns
+
+### Natural Language
+Most commands accept natural language arguments:
+```
+/project:tm/add-task create user authentication system
+/project:tm/update mark all API tasks as high priority
+/project:tm/list show blocked tasks
+```
+
+### ID-Based Commands
+Commands requiring IDs intelligently parse from $ARGUMENTS:
+```
+/project:tm/show 45
+/project:tm/expand 23
+/project:tm/set-status/to-done 67
+```
+
+### Smart Defaults
+Commands provide intelligent defaults and suggestions based on context.

.claude/commands/tm/init/index.md

@@ -0,0 +1,50 @@
+Initialize a new Task Master project.
+
+Arguments: $ARGUMENTS
+
+Parse arguments to determine initialization preferences.
+
+## Initialization Process
+
+1. **Parse Arguments**
+   - PRD file path (if provided)
+   - Project name
+   - Auto-confirm flag (-y)
+
+2. **Project Setup**
+   ```bash
+   task-master init
+   ```
+
+3. **Smart Initialization**
+   - Detect existing project files
+   - Suggest project name from directory
+   - Check for git repository
+   - Verify AI provider configuration
+
+## Configuration Options
+
+Based on arguments:
+- `quick` / `-y` → Skip confirmations
+- `<file.md>` → Use as PRD after init
+- `--name=<name>` → Set project name
+- `--description=<desc>` → Set description
+
+## Post-Initialization
+
+After successful init:
+1. Show project structure created
+2. Verify AI models configured
+3. Suggest next steps:
+   - Parse PRD if available
+   - Configure AI providers
+   - Set up git hooks
+   - Create first tasks
+
+## Integration
+
+If PRD file provided:
+```
+/project:tm/init my-prd.md
+→ Automatically runs parse-prd after init
+```

.claude/commands/tm/init/quick.md

@@ -0,0 +1,46 @@
+Quick initialization with auto-confirmation.
+
+Arguments: $ARGUMENTS
+
+Initialize a Task Master project without prompts, accepting all defaults.
+
+## Quick Setup
+
+```bash
+task-master init -y
+```
+
+## What It Does
+
+1. Creates `.taskmaster/` directory structure
+2. Initializes empty `tasks.json`
+3. Sets up default configuration
+4. Uses directory name as project name
+5. Skips all confirmation prompts
+
+## Smart Defaults
+
+- Project name: Current directory name
+- Description: "Task Master Project"
+- Model config: Existing environment vars
+- Task structure: Standard format
+
+## Next Steps
+
+After quick init:
+1. Configure AI models if needed:
+   ```
+   /project:tm/models/setup
+   ```
+
+2. Parse PRD if available:
+   ```
+   /project:tm/parse-prd <file>
+   ```
+
+3. Or create first task:
+   ```
+   /project:tm/add-task create initial setup
+   ```
+
+Perfect for rapid project setup!

.claude/commands/tm/learn.md

@@ -0,0 +1,103 @@
+Learn about Task Master capabilities through interactive exploration.
+
+Arguments: $ARGUMENTS
+
+## Interactive Task Master Learning
+
+Based on your input, I'll help you discover capabilities:
+
+### 1. **What are you trying to do?**
+
+If $ARGUMENTS contains:
+- "start" / "begin" → Show project initialization workflows
+- "manage" / "organize" → Show task management commands  
+- "automate" / "auto" → Show automation workflows
+- "analyze" / "report" → Show analysis tools
+- "fix" / "problem" → Show troubleshooting commands
+- "fast" / "quick" → Show efficiency shortcuts
+
+### 2. **Intelligent Suggestions**
+
+Based on your project state:
+
+**No tasks yet?**
+```
+You'll want to start with:
+1. /project:task-master:init <prd-file>
+   → Creates tasks from requirements
+   
+2. /project:task-master:parse-prd <file>
+   → Alternative task generation
+
+Try: /project:task-master:init demo-prd.md
+```
+
+**Have tasks?**
+Let me analyze what you might need...
+- Many pending tasks? → Learn sprint planning
+- Complex tasks? → Learn task expansion
+- Daily work? → Learn workflow automation
+
+### 3. **Command Discovery**
+
+**By Category:**
+- 📋 Task Management: list, show, add, update, complete
+- 🔄 Workflows: auto-implement, sprint-plan, daily-standup
+- 🛠️ Utilities: check-health, complexity-report, sync-memory
+- 🔍 Analysis: validate-deps, show dependencies
+
+**By Scenario:**
+- "I want to see what to work on" → `/project:task-master:next`
+- "I need to break this down" → `/project:task-master:expand <id>`
+- "Show me everything" → `/project:task-master:status`
+- "Just do it for me" → `/project:workflows:auto-implement`
+
+### 4. **Power User Patterns**
+
+**Command Chaining:**
+```
+/project:task-master:next
+/project:task-master:start <id>
+/project:workflows:auto-implement
+```
+
+**Smart Filters:**
+```
+/project:task-master:list pending high
+/project:task-master:list blocked
+/project:task-master:list 1-5 tree
+```
+
+**Automation:**
+```
+/project:workflows:pipeline init → expand-all → sprint-plan
+```
+
+### 5. **Learning Path**
+
+Based on your experience level:
+
+**Beginner Path:**
+1. init → Create project
+2. status → Understand state
+3. next → Find work
+4. complete → Finish task
+
+**Intermediate Path:**
+1. expand → Break down complex tasks
+2. sprint-plan → Organize work
+3. complexity-report → Understand difficulty
+4. validate-deps → Ensure consistency
+
+**Advanced Path:**
+1. pipeline → Chain operations
+2. smart-flow → Context-aware automation
+3. Custom commands → Extend the system
+
+### 6. **Try This Now**
+
+Based on what you asked about, try:
+[Specific command suggestion based on $ARGUMENTS]
+
+Want to learn more about a specific command?
+Type: /project:help <command-name>

.claude/commands/tm/list/by-status.md

@@ -0,0 +1,39 @@
+List tasks filtered by a specific status.
+
+Arguments: $ARGUMENTS
+
+Parse the status from arguments and list only tasks matching that status.
+
+## Status Options
+- `pending` - Not yet started
+- `in-progress` - Currently being worked on
+- `done` - Completed
+- `review` - Awaiting review
+- `deferred` - Postponed
+- `cancelled` - Cancelled
+
+## Execution
+
+Based on $ARGUMENTS, run:
+```bash
+task-master list --status=$ARGUMENTS
+```
+
+## Enhanced Display
+
+For the filtered results:
+- Group by priority within the status
+- Show time in current status
+- Highlight tasks approaching deadlines
+- Display blockers and dependencies
+- Suggest next actions for each status group
+
+## Intelligent Insights
+
+Based on the status filter:
+- **Pending**: Show recommended start order
+- **In-Progress**: Display idle time warnings
+- **Done**: Show newly unblocked tasks
+- **Review**: Indicate review duration
+- **Deferred**: Show reactivation criteria
+- **Cancelled**: Display impact analysis

.claude/commands/tm/list/index.md

@@ -0,0 +1,43 @@
+List tasks with intelligent argument parsing.
+
+Parse arguments to determine filters and display options:
+- Status: pending, in-progress, done, review, deferred, cancelled
+- Priority: high, medium, low (or priority:high)
+- Special: subtasks, tree, dependencies, blocked
+- IDs: Direct numbers (e.g., "1,3,5" or "1-5")
+- Complex: "pending high" = pending AND high priority
+
+Arguments: $ARGUMENTS
+
+Let me parse your request intelligently:
+
+1. **Detect Filter Intent**
+   - If arguments contain status keywords → filter by status
+   - If arguments contain priority → filter by priority
+   - If arguments contain "subtasks" → include subtasks
+   - If arguments contain "tree" → hierarchical view
+   - If arguments contain numbers → show specific tasks
+   - If arguments contain "blocked" → show blocked tasks only
+
+2. **Smart Combinations**
+   Examples of what I understand:
+   - "pending high" → pending tasks with high priority
+   - "done today" → tasks completed today
+   - "blocked" → tasks with unmet dependencies
+   - "1-5" → tasks 1 through 5
+   - "subtasks tree" → hierarchical view with subtasks
+
+3. **Execute Appropriate Query**
+   Based on parsed intent, run the most specific task-master command
+
+4. **Enhanced Display**
+   - Group by relevant criteria
+   - Show most important information first
+   - Use visual indicators for quick scanning
+   - Include relevant metrics
+
+5. **Intelligent Suggestions**
+   Based on what you're viewing, suggest next actions:
+   - Many pending? → Suggest priority order
+   - Many blocked? → Show dependency resolution
+   - Looking at specific tasks? → Show related tasks

.claude/commands/tm/list/with-subtasks.md

@@ -0,0 +1,29 @@
+List all tasks including their subtasks in a hierarchical view.
+
+This command shows all tasks with their nested subtasks, providing a complete project overview.
+
+## Execution
+
+Run the Task Master list command with subtasks flag:
+```bash
+task-master list --with-subtasks
+```
+
+## Enhanced Display
+
+I'll organize the output to show:
+- Parent tasks with clear indicators
+- Nested subtasks with proper indentation
+- Status badges for quick scanning
+- Dependencies and blockers highlighted
+- Progress indicators for tasks with subtasks
+
+## Smart Filtering
+
+Based on the task hierarchy:
+- Show completion percentage for parent tasks
+- Highlight blocked subtask chains
+- Group by functional areas
+- Indicate critical path items
+
+This gives you a complete tree view of your project structure.

.claude/commands/tm/models/index.md

@@ -0,0 +1,51 @@
+View current AI model configuration.
+
+## Model Configuration Display
+
+Shows the currently configured AI providers and models for Task Master.
+
+## Execution
+
+```bash
+task-master models
+```
+
+## Information Displayed
+
+1. **Main Provider**
+   - Model ID and name
+   - API key status (configured/missing)
+   - Usage: Primary task generation
+
+2. **Research Provider**
+   - Model ID and name  
+   - API key status
+   - Usage: Enhanced research mode
+
+3. **Fallback Provider**
+   - Model ID and name
+   - API key status
+   - Usage: Backup when main fails
+
+## Visual Status
+
+```
+Task Master AI Model Configuration
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Main:     ✅ claude-3-5-sonnet (configured)
+Research: ✅ perplexity-sonar (configured)  
+Fallback: ⚠️  Not configured (optional)
+
+Available Models:
+- claude-3-5-sonnet
+- gpt-4-turbo
+- gpt-3.5-turbo
+- perplexity-sonar
+```
+
+## Next Actions
+
+Based on configuration:
+- If missing API keys → Suggest setup
+- If no research model → Explain benefits
+- If all configured → Show usage tips

.claude/commands/tm/models/setup.md

@@ -0,0 +1,51 @@
+Run interactive setup to configure AI models.
+
+## Interactive Model Configuration
+
+Guides you through setting up AI providers for Task Master.
+
+## Execution
+
+```bash
+task-master models --setup
+```
+
+## Setup Process
+
+1. **Environment Check**
+   - Detect existing API keys
+   - Show current configuration
+   - Identify missing providers
+
+2. **Provider Selection**
+   - Choose main provider (required)
+   - Select research provider (recommended)
+   - Configure fallback (optional)
+
+3. **API Key Configuration**
+   - Prompt for missing keys
+   - Validate key format
+   - Test connectivity
+   - Save configuration
+
+## Smart Recommendations
+
+Based on your needs:
+- **For best results**: Claude + Perplexity
+- **Budget conscious**: GPT-3.5 + Perplexity
+- **Maximum capability**: GPT-4 + Perplexity + Claude fallback
+
+## Configuration Storage
+
+Keys can be stored in:
+1. Environment variables (recommended)
+2. `.env` file in project
+3. Global `.taskmaster/config`
+
+## Post-Setup
+
+After configuration:
+- Test each provider
+- Show usage examples
+- Suggest next steps
+- Verify parse-prd works

.claude/commands/tm/next/index.md

@@ -0,0 +1,66 @@
+Intelligently determine and prepare the next action based on comprehensive context.
+
+This enhanced version of 'next' considers:
+- Current task states
+- Recent activity
+- Time constraints
+- Dependencies
+- Your working patterns
+
+Arguments: $ARGUMENTS
+
+## Intelligent Next Action
+
+### 1. **Context Gathering**
+Let me analyze the current situation:
+- Active tasks (in-progress)
+- Recently completed tasks
+- Blocked tasks
+- Time since last activity
+- Arguments provided: $ARGUMENTS
+
+### 2. **Smart Decision Tree**
+
+**If you have an in-progress task:**
+- Has it been idle > 2 hours? → Suggest resuming or switching
+- Near completion? → Show remaining steps
+- Blocked? → Find alternative task
+
+**If no in-progress tasks:**
+- Unblocked high-priority tasks? → Start highest
+- Complex tasks need breakdown? → Suggest expansion
+- All tasks blocked? → Show dependency resolution
+
+**Special arguments handling:**
+- "quick" → Find task < 2 hours
+- "easy" → Find low complexity task
+- "important" → Find high priority regardless of complexity
+- "continue" → Resume last worked task
+
+### 3. **Preparation Workflow**
+
+Based on selected task:
+1. Show full context and history
+2. Set up development environment
+3. Run relevant tests
+4. Open related files
+5. Show similar completed tasks
+6. Estimate completion time
+
+### 4. **Alternative Suggestions**
+
+Always provide options:
+- Primary recommendation
+- Quick alternative (< 1 hour)
+- Strategic option (unblocks most tasks)
+- Learning option (new technology/skill)
+
+### 5. **Workflow Integration**
+
+Seamlessly connect to:
+- `/project:task-master:start [selected]` 
+- `/project:workflows:auto-implement`
+- `/project:task-master:expand` (if complex)
+- `/project:utils:complexity-report` (if unsure)
+
+The goal: Zero friction from decision to implementation.

.claude/commands/tm/parse-prd/index.md

@@ -0,0 +1,49 @@
+Parse a PRD document to generate tasks.
+
+Arguments: $ARGUMENTS (PRD file path)
+
+## Intelligent PRD Parsing
+
+Analyzes your requirements document and generates a complete task breakdown.
+
+## Execution
+
+```bash
+task-master parse-prd --input=$ARGUMENTS
+```
+
+## Parsing Process
+
+1. **Document Analysis**
+   - Extract key requirements
+   - Identify technical components
+   - Detect dependencies
+   - Estimate complexity
+
+2. **Task Generation**
+   - Create 10-15 tasks by default
+   - Include implementation tasks
+   - Add testing tasks
+   - Include documentation tasks
+   - Set logical dependencies
+
+3. **Smart Enhancements**
+   - Group related functionality
+   - Set appropriate priorities
+   - Add acceptance criteria
+   - Include test strategies
+
+## Options
+
+Parse arguments for modifiers:
+- Number after filename → `--num-tasks`
+- `research` → Use research mode
+- `comprehensive` → Generate more tasks
+
+## Post-Generation
+
+After parsing:
+1. Display task summary
+2. Show dependency graph
+3. Suggest task expansion for complex items
+4. Recommend sprint planning

.claude/commands/tm/parse-prd/with-research.md

@@ -0,0 +1,48 @@
+Parse PRD with enhanced research mode for better task generation.
+
+Arguments: $ARGUMENTS (PRD file path)
+
+## Research-Enhanced Parsing
+
+Uses the research AI provider (typically Perplexity) for more comprehensive task generation with current best practices.
+
+## Execution
+
+```bash
+task-master parse-prd --input=$ARGUMENTS --research
+```
+
+## Research Benefits
+
+1. **Current Best Practices**
+   - Latest framework patterns
+   - Security considerations
+   - Performance optimizations
+   - Accessibility requirements
+
+2. **Technical Deep Dive**
+   - Implementation approaches
+   - Library recommendations
+   - Architecture patterns
+   - Testing strategies
+
+3. **Comprehensive Coverage**
+   - Edge cases consideration
+   - Error handling tasks
+   - Monitoring setup
+   - Deployment tasks
+
+## Enhanced Output
+
+Research mode typically:
+- Generates more detailed tasks
+- Includes industry standards
+- Adds compliance considerations
+- Suggests modern tooling
+
+## When to Use
+
+- New technology domains
+- Complex requirements
+- Regulatory compliance needed
+- Best practices crucial

.claude/commands/tm/remove-dependency/index.md

@@ -0,0 +1,62 @@
+Remove a dependency between tasks.
+
+Arguments: $ARGUMENTS
+
+Parse the task IDs to remove dependency relationship.
+
+## Removing Dependencies
+
+Removes a dependency relationship, potentially unblocking tasks.
+
+## Argument Parsing
+
+Parse natural language or IDs:
+- "remove dependency between 5 and 3"
+- "5 no longer needs 3"
+- "unblock 5 from 3"
+- "5 3" → remove dependency of 5 on 3
+
+## Execution
+
+```bash
+task-master remove-dependency --id=<task-id> --depends-on=<dependency-id>
+```
+
+## Pre-Removal Checks
+
+1. **Verify dependency exists**
+2. **Check impact on task flow**
+3. **Warn if it breaks logical sequence**
+4. **Show what will be unblocked**
+
+## Smart Analysis
+
+Before removing:
+- Show why dependency might have existed
+- Check if removal makes tasks executable
+- Verify no critical path disruption
+- Suggest alternative dependencies
+
+## Post-Removal
+
+After removing:
+1. Show updated task status
+2. List newly unblocked tasks
+3. Update project timeline
+4. Suggest next actions
+
+## Safety Features
+
+- Confirm if removing critical dependency
+- Show tasks that become immediately actionable
+- Warn about potential issues
+- Keep removal history
+
+## Example
+
+```
+/project:tm/remove-dependency 5 from 3
+→ Removed: Task #5 no longer depends on #3
+→ Task #5 is now UNBLOCKED and ready to start
+→ Warning: Consider if #5 still needs #2 completed first
+```

.claude/commands/tm/remove-subtask/index.md

@@ -0,0 +1,84 @@
+Remove a subtask from its parent task.
+
+Arguments: $ARGUMENTS
+
+Parse subtask ID to remove, with option to convert to standalone task.
+
+## Removing Subtasks
+
+Remove a subtask and optionally convert it back to a standalone task.
+
+## Argument Parsing
+
+- "remove subtask 5.1"
+- "delete 5.1"
+- "convert 5.1 to task" → remove and convert
+- "5.1 standalone" → convert to standalone
+
+## Execution Options
+
+### 1. Delete Subtask
+```bash
+task-master remove-subtask --id=<parentId.subtaskId>
+```
+
+### 2. Convert to Standalone
+```bash
+task-master remove-subtask --id=<parentId.subtaskId> --convert
+```
+
+## Pre-Removal Checks
+
+1. **Validate Subtask**
+   - Verify subtask exists
+   - Check completion status
+   - Review dependencies
+
+2. **Impact Analysis**
+   - Other subtasks that depend on it
+   - Parent task implications
+   - Data that will be lost
+
+## Removal Process
+
+### For Deletion:
+1. Confirm if subtask has work done
+2. Update parent task estimates
+3. Remove subtask and its data
+4. Clean up dependencies
+
+### For Conversion:
+1. Assign new standalone task ID
+2. Preserve all task data
+3. Update dependency references
+4. Maintain task history
+
+## Smart Features
+
+- Warn if subtask is in-progress
+- Show impact on parent task
+- Preserve important data
+- Update related estimates
+
+## Example Flows
+
+```
+/project:tm/remove-subtask 5.1
+→ Warning: Subtask #5.1 is in-progress
+→ This will delete all subtask data
+→ Parent task #5 will be updated
+Confirm deletion? (y/n)
+
+/project:tm/remove-subtask 5.1 convert
+→ Converting subtask #5.1 to standalone task #89
+→ Preserved: All task data and history
+→ Updated: 2 dependency references
+→ New task #89 is now independent
+```
+
+## Post-Removal
+
+- Update parent task status
+- Recalculate estimates
+- Show updated hierarchy
+- Suggest next actions

.claude/commands/tm/remove-task/index.md

@@ -0,0 +1,107 @@
+Remove a task permanently from the project.
+
+Arguments: $ARGUMENTS (task ID)
+
+Delete a task and handle all its relationships properly.
+
+## Task Removal
+
+Permanently removes a task while maintaining project integrity.
+
+## Argument Parsing
+
+- "remove task 5"
+- "delete 5"
+- "5" → remove task 5
+- Can include "-y" for auto-confirm
+
+## Execution
+
+```bash
+task-master remove-task --id=<id> [-y]
+```
+
+## Pre-Removal Analysis
+
+1. **Task Details**
+   - Current status
+   - Work completed
+   - Time invested
+   - Associated data
+
+2. **Relationship Check**
+   - Tasks that depend on this
+   - Dependencies this task has
+   - Subtasks that will be removed
+   - Blocking implications
+
+3. **Impact Assessment**
+   ```
+   Task Removal Impact
+   ━━━━━━━━━━━━━━━━━━
+   Task: #5 "Implement authentication" (in-progress)
+   Status: 60% complete (~8 hours work)
+   
+   Will affect:
+   - 3 tasks depend on this (will be blocked)
+   - Has 4 subtasks (will be deleted)
+   - Part of critical path
+   
+   ⚠️  This action cannot be undone
+   ```
+
+## Smart Warnings
+
+- Warn if task is in-progress
+- Show dependent tasks that will be blocked
+- Highlight if part of critical path
+- Note any completed work being lost
+
+## Removal Process
+
+1. Show comprehensive impact
+2. Require confirmation (unless -y)
+3. Update dependent task references
+4. Remove task and subtasks
+5. Clean up orphaned dependencies
+6. Log removal with timestamp
+
+## Alternative Actions
+
+Suggest before deletion:
+- Mark as cancelled instead
+- Convert to documentation
+- Archive task data
+- Transfer work to another task
+
+## Post-Removal
+
+- List affected tasks
+- Show broken dependencies
+- Update project statistics
+- Suggest dependency fixes
+- Recalculate timeline
+
+## Example Flows
+
+```
+/project:tm/remove-task 5
+→ Task #5 is in-progress with 8 hours logged
+→ 3 other tasks depend on this
+→ Suggestion: Mark as cancelled instead?
+Remove anyway? (y/n)
+
+/project:tm/remove-task 5 -y
+→ Removed: Task #5 and 4 subtasks
+→ Updated: 3 task dependencies
+→ Warning: Tasks #7, #8, #9 now have missing dependency
+→ Run /project:tm/fix-dependencies to resolve
+```
+
+## Safety Features
+
+- Confirmation required
+- Impact preview
+- Removal logging
+- Suggest alternatives
+- No cascade delete of dependents

.claude/commands/tm/set-status/to-cancelled.md

@@ -0,0 +1,55 @@
+Cancel a task permanently.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Cancelling a Task
+
+This status indicates a task is no longer needed and won't be completed.
+
+## Valid Reasons for Cancellation
+
+- Requirements changed
+- Feature deprecated
+- Duplicate of another task
+- Strategic pivot
+- Technical approach invalidated
+
+## Pre-Cancellation Checks
+
+1. Confirm no critical dependencies
+2. Check for partial implementation
+3. Verify cancellation rationale
+4. Document lessons learned
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=cancelled
+```
+
+## Cancellation Impact
+
+When cancelling:
+1. **Dependency Updates**
+   - Notify dependent tasks
+   - Update project scope
+   - Recalculate timelines
+
+2. **Clean-up Actions**
+   - Remove related branches
+   - Archive any work done
+   - Update documentation
+   - Close related issues
+
+3. **Learning Capture**
+   - Document why cancelled
+   - Note what was learned
+   - Update estimation models
+   - Prevent future duplicates
+
+## Historical Preservation
+
+- Keep for reference
+- Tag with cancellation reason
+- Link to replacement if any
+- Maintain audit trail

.claude/commands/tm/set-status/to-deferred.md

@@ -0,0 +1,47 @@
+Defer a task for later consideration.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Deferring a Task
+
+This status indicates a task is valid but not currently actionable or prioritized.
+
+## Valid Reasons for Deferral
+
+- Waiting for external dependencies
+- Reprioritized for future sprint
+- Blocked by technical limitations
+- Resource constraints
+- Strategic timing considerations
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=deferred
+```
+
+## Deferral Management
+
+When deferring:
+1. **Document Reason**
+   - Capture why it's being deferred
+   - Set reactivation criteria
+   - Note any partial work completed
+
+2. **Impact Analysis**
+   - Check dependent tasks
+   - Update project timeline
+   - Notify affected stakeholders
+
+3. **Future Planning**
+   - Set review reminders
+   - Tag for specific milestone
+   - Preserve context for reactivation
+   - Link to blocking issues
+
+## Smart Tracking
+
+- Monitor deferral duration
+- Alert when criteria met
+- Prevent scope creep
+- Regular review cycles

.claude/commands/tm/set-status/to-done.md

@@ -0,0 +1,44 @@
+Mark a task as completed.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Completing a Task
+
+This command validates task completion and updates project state intelligently.
+
+## Pre-Completion Checks
+
+1. Verify test strategy was followed
+2. Check if all subtasks are complete
+3. Validate acceptance criteria met
+4. Ensure code is committed
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=done
+```
+
+## Post-Completion Actions
+
+1. **Update Dependencies**
+   - Identify newly unblocked tasks
+   - Update sprint progress
+   - Recalculate project timeline
+
+2. **Documentation**
+   - Generate completion summary
+   - Update CLAUDE.md with learnings
+   - Log implementation approach
+
+3. **Next Steps**
+   - Show newly available tasks
+   - Suggest logical next task
+   - Update velocity metrics
+
+## Celebration & Learning
+
+- Show impact of completion
+- Display unblocked work
+- Recognize achievement
+- Capture lessons learned

.claude/commands/tm/set-status/to-in-progress.md

@@ -0,0 +1,36 @@
+Start working on a task by setting its status to in-progress.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Starting Work on Task
+
+This command does more than just change status - it prepares your environment for productive work.
+
+## Pre-Start Checks
+
+1. Verify dependencies are met
+2. Check if another task is already in-progress
+3. Ensure task details are complete
+4. Validate test strategy exists
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=in-progress
+```
+
+## Environment Setup
+
+After setting to in-progress:
+1. Create/checkout appropriate git branch
+2. Open relevant documentation
+3. Set up test watchers if applicable
+4. Display task details and acceptance criteria
+5. Show similar completed tasks for reference
+
+## Smart Suggestions
+
+- Estimated completion time based on complexity
+- Related files from similar tasks
+- Potential blockers to watch for
+- Recommended first steps

.claude/commands/tm/set-status/to-pending.md

@@ -0,0 +1,32 @@
+Set a task's status to pending.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Setting Task to Pending
+
+This moves a task back to the pending state, useful for:
+- Resetting erroneously started tasks
+- Deferring work that was prematurely begun
+- Reorganizing sprint priorities
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=pending
+```
+
+## Validation
+
+Before setting to pending:
+- Warn if task is currently in-progress
+- Check if this will block other tasks
+- Suggest documenting why it's being reset
+- Preserve any work already done
+
+## Smart Actions
+
+After setting to pending:
+- Update sprint planning if needed
+- Notify about freed resources
+- Suggest priority reassessment
+- Log the status change with context

.claude/commands/tm/set-status/to-review.md

@@ -0,0 +1,40 @@
+Set a task's status to review.
+
+Arguments: $ARGUMENTS (task ID)
+
+## Marking Task for Review
+
+This status indicates work is complete but needs verification before final approval.
+
+## When to Use Review Status
+
+- Code complete but needs peer review
+- Implementation done but needs testing
+- Documentation written but needs proofreading
+- Design complete but needs stakeholder approval
+
+## Execution
+
+```bash
+task-master set-status --id=$ARGUMENTS --status=review
+```
+
+## Review Preparation
+
+When setting to review:
+1. **Generate Review Checklist**
+   - Link to PR/MR if applicable
+   - Highlight key changes
+   - Note areas needing attention
+   - Include test results
+
+2. **Documentation**
+   - Update task with review notes
+   - Link relevant artifacts
+   - Specify reviewers if known
+
+3. **Smart Actions**
+   - Create review reminders
+   - Track review duration
+   - Suggest reviewers based on expertise
+   - Prepare rollback plan if needed

.claude/commands/tm/setup/install.md

@@ -0,0 +1,117 @@
+Check if Task Master is installed and install it if needed.
+
+This command helps you get Task Master set up globally on your system.
+
+## Detection and Installation Process
+
+1. **Check Current Installation**
+   ```bash
+   # Check if task-master command exists
+   which task-master || echo "Task Master not found"
+   
+   # Check npm global packages
+   npm list -g task-master-ai
+   ```
+
+2. **System Requirements Check**
+   ```bash
+   # Verify Node.js is installed
+   node --version
+   
+   # Verify npm is installed  
+   npm --version
+   
+   # Check Node version (need 16+)
+   ```
+
+3. **Install Task Master Globally**
+   If not installed, run:
+   ```bash
+   npm install -g task-master-ai
+   ```
+
+4. **Verify Installation**
+   ```bash
+   # Check version
+   task-master --version
+   
+   # Verify command is available
+   which task-master
+   ```
+
+5. **Initial Setup**
+   ```bash
+   # Initialize in current directory
+   task-master init
+   ```
+
+6. **Configure AI Provider**
+   Ensure you have at least one AI provider API key set:
+   ```bash
+   # Check current configuration
+   task-master models --status
+   
+   # If no API keys found, guide setup
+   echo "You'll need at least one API key:"
+   echo "- ANTHROPIC_API_KEY for Claude"
+   echo "- OPENAI_API_KEY for GPT models"
+   echo "- PERPLEXITY_API_KEY for research"
+   echo ""
+   echo "Set them in your shell profile or .env file"
+   ```
+
+7. **Quick Test**
+   ```bash
+   # Create a test PRD
+   echo "Build a simple hello world API" > test-prd.txt
+   
+   # Try parsing it
+   task-master parse-prd test-prd.txt -n 3
+   ```
+
+## Troubleshooting
+
+If installation fails:
+
+**Permission Errors:**
+```bash
+# Try with sudo (macOS/Linux)
+sudo npm install -g task-master-ai
+
+# Or fix npm permissions
+npm config set prefix ~/.npm-global
+export PATH=~/.npm-global/bin:$PATH
+```
+
+**Network Issues:**
+```bash
+# Use different registry
+npm install -g task-master-ai --registry https://registry.npmjs.org/
+```
+
+**Node Version Issues:**
+```bash
+# Install Node 18+ via nvm
+curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.0/install.sh | bash
+nvm install 18
+nvm use 18
+```
+
+## Success Confirmation
+
+Once installed, you should see:
+```
+✅ Task Master v0.16.2 (or higher) installed
+✅ Command 'task-master' available globally
+✅ AI provider configured
+✅ Ready to use slash commands!
+
+Try: /project:task-master:init your-prd.md
+```
+
+## Next Steps
+
+After installation:
+1. Run `/project:utils:check-health` to verify setup
+2. Configure AI providers with `/project:task-master:models`
+3. Start using Task Master commands!

.claude/commands/tm/setup/quick-install.md

@@ -0,0 +1,22 @@
+Quick install Task Master globally if not already installed.
+
+Execute this streamlined installation:
+
+```bash
+# Check and install in one command
+task-master --version 2>/dev/null || npm install -g task-master-ai
+
+# Verify installation
+task-master --version
+
+# Quick setup check
+task-master models --status || echo "Note: You'll need to set up an AI provider API key"
+```
+
+If you see "command not found" after installation, you may need to:
+1. Restart your terminal
+2. Or add npm global bin to PATH: `export PATH=$(npm bin -g):$PATH`
+
+Once installed, you can use all the Task Master commands!
+
+Quick test: Run `/project:help` to see all available commands.

.claude/commands/tm/show/index.md

@@ -0,0 +1,82 @@
+Show detailed task information with rich context and insights.
+
+Arguments: $ARGUMENTS
+
+## Enhanced Task Display
+
+Parse arguments to determine what to show and how.
+
+### 1. **Smart Task Selection**
+
+Based on $ARGUMENTS:
+- Number → Show specific task with full context
+- "current" → Show active in-progress task(s)
+- "next" → Show recommended next task
+- "blocked" → Show all blocked tasks with reasons
+- "critical" → Show critical path tasks
+- Multiple IDs → Comparative view
+
+### 2. **Contextual Information**
+
+For each task, intelligently include:
+
+**Core Details**
+- Full task information (id, title, description, details)
+- Current status with history
+- Test strategy and acceptance criteria
+- Priority and complexity analysis
+
+**Relationships**
+- Dependencies (what it needs)
+- Dependents (what needs it)
+- Parent/subtask hierarchy
+- Related tasks (similar work)
+
+**Time Intelligence**
+- Created/updated timestamps
+- Time in current status
+- Estimated vs actual time
+- Historical completion patterns
+
+### 3. **Visual Enhancements**
+
+```
+📋 Task #45: Implement User Authentication
+━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
+Status: 🟡 in-progress (2 hours)
+Priority: 🔴 High | Complexity: 73/100
+
+Dependencies: ✅ #41, ✅ #42, ⏳ #43 (blocked)
+Blocks: #46, #47, #52
+
+Progress: ████████░░ 80% complete
+
+Recent Activity:
+- 2h ago: Status changed to in-progress
+- 4h ago: Dependency #42 completed
+- Yesterday: Task expanded with 3 subtasks
+```
+
+### 4. **Intelligent Insights**
+
+Based on task analysis:
+- **Risk Assessment**: Complexity vs time remaining
+- **Bottleneck Analysis**: Is this blocking critical work?
+- **Recommendation**: Suggested approach or concerns
+- **Similar Tasks**: How others completed similar work
+
+### 5. **Action Suggestions**
+
+Context-aware next steps:
+- If blocked → Show how to unblock
+- If complex → Suggest expansion
+- If in-progress → Show completion checklist
+- If done → Show dependent tasks ready to start
+
+### 6. **Multi-Task View**
+
+When showing multiple tasks:
+- Common dependencies
+- Optimal completion order
+- Parallel work opportunities
+- Combined complexity analysis

.claude/commands/tm/status/index.md

@@ -0,0 +1,64 @@
+Enhanced status command with comprehensive project insights.
+
+Arguments: $ARGUMENTS
+
+## Intelligent Status Overview
+
+### 1. **Executive Summary**
+Quick dashboard view:
+- 🏃 Active work (in-progress tasks)
+- 📊 Progress metrics (% complete, velocity)
+- 🚧 Blockers and risks
+- ⏱️ Time analysis (estimated vs actual)
+- 🎯 Sprint/milestone progress
+
+### 2. **Contextual Analysis**
+
+Based on $ARGUMENTS, focus on:
+- "sprint" → Current sprint progress and burndown
+- "blocked" → Dependency chains and resolution paths
+- "team" → Task distribution and workload
+- "timeline" → Schedule adherence and projections
+- "risk" → High complexity or overdue items
+
+### 3. **Smart Insights**
+
+**Workflow Health:**
+- Idle tasks (in-progress > 24h without updates)
+- Bottlenecks (multiple tasks waiting on same dependency)
+- Quick wins (low complexity, high impact)
+
+**Predictive Analytics:**
+- Completion projections based on velocity
+- Risk of missing deadlines
+- Recommended task order for optimal flow
+
+### 4. **Visual Intelligence**
+
+Dynamic visualization based on data:
+```
+Sprint Progress: ████████░░ 80% (16/20 tasks)
+Velocity Trend: ↗️ +15% this week
+Blocked Tasks:  🔴 3 critical path items
+
+Priority Distribution:
+High:   ████████ 8 tasks (2 blocked)
+Medium: ████░░░░ 4 tasks
+Low:    ██░░░░░░ 2 tasks
+```
+
+### 5. **Actionable Recommendations**
+
+Based on analysis:
+1. **Immediate actions** (unblock critical path)
+2. **Today's focus** (optimal task sequence)
+3. **Process improvements** (recurring patterns)
+4. **Resource needs** (skills, time, dependencies)
+
+### 6. **Historical Context**
+
+Compare to previous periods:
+- Velocity changes
+- Pattern recognition
+- Improvement areas
+- Success patterns to repeat

.claude/commands/tm/sync-readme/index.md

@@ -0,0 +1,117 @@
+Export tasks to README.md with professional formatting.
+
+Arguments: $ARGUMENTS
+
+Generate a well-formatted README with current task information.
+
+## README Synchronization
+
+Creates or updates README.md with beautifully formatted task information.
+
+## Argument Parsing
+
+Optional filters:
+- "pending" → Only pending tasks
+- "with-subtasks" → Include subtask details
+- "by-priority" → Group by priority
+- "sprint" → Current sprint only
+
+## Execution
+
+```bash
+task-master sync-readme [--with-subtasks] [--status=<status>]
+```
+
+## README Generation
+
+### 1. **Project Header**
+```markdown
+# Project Name
+
+## 📋 Task Progress
+
+Last Updated: 2024-01-15 10:30 AM
+
+### Summary
+- Total Tasks: 45
+- Completed: 15 (33%)
+- In Progress: 5 (11%)
+- Pending: 25 (56%)
+```
+
+### 2. **Task Sections**
+Organized by status or priority:
+- Progress indicators
+- Task descriptions
+- Dependencies noted
+- Time estimates
+
+### 3. **Visual Elements**
+- Progress bars
+- Status badges
+- Priority indicators
+- Completion checkmarks
+
+## Smart Features
+
+1. **Intelligent Grouping**
+   - By feature area
+   - By sprint/milestone
+   - By assigned developer
+   - By priority
+
+2. **Progress Tracking**
+   - Overall completion
+   - Sprint velocity
+   - Burndown indication
+   - Time tracking
+
+3. **Formatting Options**
+   - GitHub-flavored markdown
+   - Task checkboxes
+   - Collapsible sections
+   - Table format available
+
+## Example Output
+
+```markdown
+## 🚀 Current Sprint
+
+### In Progress
+- [ ] 🔄 #5 **Implement user authentication** (60% complete)
+  - Dependencies: API design (#3 ✅)
+  - Subtasks: 4 (2 completed)
+  - Est: 8h / Spent: 5h
+
+### Pending (High Priority)
+- [ ] ⚡ #8 **Create dashboard UI**
+  - Blocked by: #5
+  - Complexity: High
+  - Est: 12h
+```
+
+## Customization
+
+Based on arguments:
+- Include/exclude sections
+- Detail level control
+- Custom grouping
+- Filter by criteria
+
+## Post-Sync
+
+After generation:
+1. Show diff preview
+2. Backup existing README
+3. Write new content
+4. Commit reminder
+5. Update timestamp
+
+## Integration
+
+Works well with:
+- Git workflows
+- CI/CD pipelines
+- Project documentation
+- Team updates
+- Client reports

.claude/commands/tm/update/from-id.md

@@ -0,0 +1,108 @@
+Update multiple tasks starting from a specific ID.
+
+Arguments: $ARGUMENTS
+
+Parse starting task ID and update context.
+
+## Bulk Task Updates
+
+Update multiple related tasks based on new requirements or context changes.
+
+## Argument Parsing
+
+- "from 5: add security requirements"
+- "5 onwards: update API endpoints"
+- "starting at 5: change to use new framework"
+
+## Execution
+
+```bash
+task-master update --from=<id> --prompt="<context>"
+```
+
+## Update Process
+
+### 1. **Task Selection**
+Starting from specified ID:
+- Include the task itself
+- Include all dependent tasks
+- Include related subtasks
+- Smart boundary detection
+
+### 2. **Context Application**
+AI analyzes the update context and:
+- Identifies what needs changing
+- Maintains consistency
+- Preserves completed work
+- Updates related information
+
+### 3. **Intelligent Updates**
+- Modify descriptions appropriately
+- Update test strategies
+- Adjust time estimates
+- Revise dependencies if needed
+
+## Smart Features
+
+1. **Scope Detection**
+   - Find natural task groupings
+   - Identify related features
+   - Stop at logical boundaries
+   - Avoid over-updating
+
+2. **Consistency Maintenance**
+   - Keep naming conventions
+   - Preserve relationships
+   - Update cross-references
+   - Maintain task flow
+
+3. **Change Preview**
+   ```
+   Bulk Update Preview
+   ━━━━━━━━━━━━━━━━━━
+   Starting from: Task #5
+   Tasks to update: 8 tasks + 12 subtasks
+   
+   Context: "add security requirements"
+   
+   Changes will include:
+   - Add security sections to descriptions
+   - Update test strategies for security
+   - Add security-related subtasks where needed
+   - Adjust time estimates (+20% average)
+   
+   Continue? (y/n)
+   ```
+
+## Example Updates
+
+```
+/project:tm/update/from-id 5: change database to PostgreSQL
+→ Analyzing impact starting from task #5
+→ Found 6 related tasks to update
+→ Updates will maintain consistency
+→ Preview changes? (y/n)
+
+Applied updates:
+✓ Task #5: Updated connection logic references
+✓ Task #6: Changed migration approach
+✓ Task #7: Updated query syntax notes
+✓ Task #8: Revised testing strategy
+✓ Task #9: Updated deployment steps
+✓ Task #12: Changed backup procedures
+```
+
+## Safety Features
+
+- Preview all changes
+- Selective confirmation
+- Rollback capability
+- Change logging
+- Validation checks
+
+## Post-Update
+
+- Summary of changes
+- Consistency verification
+- Suggest review tasks
+- Update timeline if needed

.claude/commands/tm/update/index.md

@@ -0,0 +1,72 @@
+Update tasks with intelligent field detection and bulk operations.
+
+Arguments: $ARGUMENTS
+
+## Intelligent Task Updates
+
+Parse arguments to determine update intent and execute smartly.
+
+### 1. **Natural Language Processing**
+
+Understand update requests like:
+- "mark 23 as done" → Update status to done
+- "increase priority of 45" → Set priority to high
+- "add dependency on 12 to task 34" → Add dependency
+- "tasks 20-25 need review" → Bulk status update
+- "all API tasks high priority" → Pattern-based update
+
+### 2. **Smart Field Detection**
+
+Automatically detect what to update:
+- Status keywords: done, complete, start, pause, review
+- Priority changes: urgent, high, low, deprioritize
+- Dependency updates: depends on, blocks, after
+- Assignment: assign to, owner, responsible
+- Time: estimate, spent, deadline
+
+### 3. **Bulk Operations**
+
+Support for multiple task updates:
+```
+Examples:
+- "complete tasks 12, 15, 18"
+- "all pending auth tasks to in-progress"
+- "increase priority for tasks blocking 45"
+- "defer all documentation tasks"
+```
+
+### 4. **Contextual Validation**
+
+Before updating, check:
+- Status transitions are valid
+- Dependencies don't create cycles
+- Priority changes make sense
+- Bulk updates won't break project flow
+
+Show preview:
+```
+Update Preview:
+─────────────────
+Tasks to update: #23, #24, #25
+Change: status → in-progress
+Impact: Will unblock tasks #30, #31
+Warning: Task #24 has unmet dependencies
+```
+
+### 5. **Smart Suggestions**
+
+Based on update:
+- Completing task? → Show newly unblocked tasks
+- Changing priority? → Show impact on sprint
+- Adding dependency? → Check for conflicts
+- Bulk update? → Show summary of changes
+
+### 6. **Workflow Integration**
+
+After updates:
+- Auto-update dependent task states
+- Trigger status recalculation
+- Update sprint/milestone progress
+- Log changes with context
+
+Result: Flexible, intelligent task updates with safety checks.

.claude/commands/tm/update/single.md

@@ -0,0 +1,119 @@
+Update a single specific task with new information.
+
+Arguments: $ARGUMENTS
+
+Parse task ID and update details.
+
+## Single Task Update
+
+Precisely update one task with AI assistance to maintain consistency.
+
+## Argument Parsing
+
+Natural language updates:
+- "5: add caching requirement"
+- "update 5 to include error handling"
+- "task 5 needs rate limiting"
+- "5 change priority to high"
+
+## Execution
+
+```bash
+task-master update-task --id=<id> --prompt="<context>"
+```
+
+## Update Types
+
+### 1. **Content Updates**
+- Enhance description
+- Add requirements
+- Clarify details
+- Update acceptance criteria
+
+### 2. **Metadata Updates**
+- Change priority
+- Adjust time estimates
+- Update complexity
+- Modify dependencies
+
+### 3. **Strategic Updates**
+- Revise approach
+- Change test strategy
+- Update implementation notes
+- Adjust subtask needs
+
+## AI-Powered Updates
+
+The AI:
+1. **Understands Context**
+   - Reads current task state
+   - Identifies update intent
+   - Maintains consistency
+   - Preserves important info
+
+2. **Applies Changes**
+   - Updates relevant fields
+   - Keeps style consistent
+   - Adds without removing
+   - Enhances clarity
+
+3. **Validates Results**
+   - Checks coherence
+   - Verifies completeness
+   - Maintains relationships
+   - Suggests related updates
+
+## Example Updates
+
+```
+/project:tm/update/single 5: add rate limiting
+→ Updating Task #5: "Implement API endpoints"
+
+Current: Basic CRUD endpoints
+Adding: Rate limiting requirements
+
+Updated sections:
+✓ Description: Added rate limiting mention
+✓ Details: Added specific limits (100/min)
+✓ Test Strategy: Added rate limit tests
+✓ Complexity: Increased from 5 to 6
+✓ Time Estimate: Increased by 2 hours
+
+Suggestion: Also update task #6 (API Gateway) for consistency?
+```
+
+## Smart Features
+
+1. **Incremental Updates**
+   - Adds without overwriting
+   - Preserves work history
+   - Tracks what changed
+   - Shows diff view
+
+2. **Consistency Checks**
+   - Related task alignment
+   - Subtask compatibility
+   - Dependency validity
+   - Timeline impact
+
+3. **Update History**
+   - Timestamp changes
+   - Track who/what updated
+   - Reason for update
+   - Previous versions
+
+## Field-Specific Updates
+
+Quick syntax for specific fields:
+- "5 priority:high" → Update priority only
+- "5 add-time:4h" → Add to time estimate
+- "5 status:review" → Change status
+- "5 depends:3,4" → Add dependencies
+
+## Post-Update
+
+- Show updated task
+- Highlight changes
+- Check related tasks
+- Update suggestions
+- Timeline adjustments

.claude/commands/tm/utils/analyze.md

@@ -0,0 +1,97 @@
+Advanced project analysis with actionable insights and recommendations.
+
+Arguments: $ARGUMENTS
+
+## Comprehensive Project Analysis
+
+Multi-dimensional analysis based on requested focus area.
+
+### 1. **Analysis Modes**
+
+Based on $ARGUMENTS:
+- "velocity" → Sprint velocity and trends
+- "quality" → Code quality metrics
+- "risk" → Risk assessment and mitigation
+- "dependencies" → Dependency graph analysis
+- "team" → Workload and skill distribution
+- "architecture" → System design coherence
+- Default → Full spectrum analysis
+
+### 2. **Velocity Analytics**
+
+```
+📊 Velocity Analysis
+━━━━━━━━━━━━━━━━━━━
+Current Sprint: 24 points/week ↗️ +20%
+Rolling Average: 20 points/week
+Efficiency: 85% (17/20 tasks on time)
+
+Bottlenecks Detected:
+- Code review delays (avg 4h wait)
+- Test environment availability
+- Dependency on external team
+
+Recommendations:
+1. Implement parallel review process
+2. Add staging environment
+3. Mock external dependencies
+```
+
+### 3. **Risk Assessment**
+
+**Technical Risks**
+- High complexity tasks without backup assignee
+- Single points of failure in architecture
+- Insufficient test coverage in critical paths
+- Technical debt accumulation rate
+
+**Project Risks**
+- Critical path dependencies
+- Resource availability gaps
+- Deadline feasibility analysis
+- Scope creep indicators
+
+### 4. **Dependency Intelligence**
+
+Visual dependency analysis:
+```
+Critical Path: 
+#12 → #15 → #23 → #45 → #50 (20 days)
+         ↘ #24 → #46 ↗
+
+Optimization: Parallelize #15 and #24
+Time Saved: 3 days
+```
+
+### 5. **Quality Metrics**
+
+**Code Quality**
+- Test coverage trends
+- Complexity scores
+- Technical debt ratio
+- Review feedback patterns
+
+**Process Quality**
+- Rework frequency
+- Bug introduction rate
+- Time to resolution
+- Knowledge distribution
+
+### 6. **Predictive Insights**
+
+Based on patterns:
+- Completion probability by deadline
+- Resource needs projection
+- Risk materialization likelihood
+- Suggested interventions
+
+### 7. **Executive Dashboard**
+
+High-level summary with:
+- Health score (0-100)
+- Top 3 risks
+- Top 3 opportunities
+- Recommended actions
+- Success probability
+
+Result: Data-driven decisions with clear action paths.

.claude/commands/tm/validate-dependencies/index.md

@@ -0,0 +1,71 @@
+Validate all task dependencies for issues.
+
+## Dependency Validation
+
+Comprehensive check for dependency problems across the entire project.
+
+## Execution
+
+```bash
+task-master validate-dependencies
+```
+
+## Validation Checks
+
+1. **Circular Dependencies**
+   - A depends on B, B depends on A
+   - Complex circular chains
+   - Self-dependencies
+
+2. **Missing Dependencies**
+   - References to non-existent tasks
+   - Deleted task references
+   - Invalid task IDs
+
+3. **Logical Issues**
+   - Completed tasks depending on pending
+   - Cancelled tasks in dependency chains
+   - Impossible sequences
+
+4. **Complexity Warnings**
+   - Over-complex dependency chains
+   - Too many dependencies per task
+   - Bottleneck tasks
+
+## Smart Analysis
+
+The validation provides:
+- Visual dependency graph
+- Critical path analysis
+- Bottleneck identification
+- Suggested optimizations
+
+## Report Format
+
+```
+Dependency Validation Report
+━━━━━━━━━━━━━━━━━━━━━━━━━━
+✅ No circular dependencies found
+⚠️  2 warnings found:
+   - Task #23 has 7 dependencies (consider breaking down)
+   - Task #45 blocks 5 other tasks (potential bottleneck)
+❌ 1 error found:
+   - Task #67 depends on deleted task #66
+
+Critical Path: #1 → #5 → #23 → #45 → #50 (15 days)
+```
+
+## Actionable Output
+
+For each issue found:
+- Clear description
+- Impact assessment
+- Suggested fix
+- Command to resolve
+
+## Next Steps
+
+After validation:
+- Run `/project:tm/fix-dependencies` to auto-fix
+- Manually adjust problematic dependencies
+- Rerun to verify fixes

.claude/commands/tm/workflows/auto-implement.md

@@ -0,0 +1,97 @@
+Enhanced auto-implementation with intelligent code generation and testing.
+
+Arguments: $ARGUMENTS
+
+## Intelligent Auto-Implementation
+
+Advanced implementation with context awareness and quality checks.
+
+### 1. **Pre-Implementation Analysis**
+
+Before starting:
+- Analyze task complexity and requirements
+- Check codebase patterns and conventions
+- Identify similar completed tasks
+- Assess test coverage needs
+- Detect potential risks
+
+### 2. **Smart Implementation Strategy**
+
+Based on task type and context:
+
+**Feature Tasks**
+1. Research existing patterns
+2. Design component architecture
+3. Implement with tests
+4. Integrate with system
+5. Update documentation
+
+**Bug Fix Tasks**
+1. Reproduce issue
+2. Identify root cause
+3. Implement minimal fix
+4. Add regression tests
+5. Verify side effects
+
+**Refactoring Tasks**
+1. Analyze current structure
+2. Plan incremental changes
+3. Maintain test coverage
+4. Refactor step-by-step
+5. Verify behavior unchanged
+
+### 3. **Code Intelligence**
+
+**Pattern Recognition**
+- Learn from existing code
+- Follow team conventions
+- Use preferred libraries
+- Match style guidelines
+
+**Test-Driven Approach**
+- Write tests first when possible
+- Ensure comprehensive coverage
+- Include edge cases
+- Performance considerations
+
+### 4. **Progressive Implementation**
+
+Step-by-step with validation:
+```
+Step 1/5: Setting up component structure ✓
+Step 2/5: Implementing core logic ✓
+Step 3/5: Adding error handling ⚡ (in progress)
+Step 4/5: Writing tests ⏳
+Step 5/5: Integration testing ⏳
+
+Current: Adding try-catch blocks and validation...
+```
+
+### 5. **Quality Assurance**
+
+Automated checks:
+- Linting and formatting
+- Test execution
+- Type checking
+- Dependency validation
+- Performance analysis
+
+### 6. **Smart Recovery**
+
+If issues arise:
+- Diagnostic analysis
+- Suggestion generation
+- Fallback strategies
+- Manual intervention points
+- Learning from failures
+
+### 7. **Post-Implementation**
+
+After completion:
+- Generate PR description
+- Update documentation
+- Log lessons learned
+- Suggest follow-up tasks
+- Update task relationships
+
+Result: High-quality, production-ready implementations.

.claude/commands/tm/workflows/pipeline.md

@@ -0,0 +1,77 @@
+Execute a pipeline of commands based on a specification.
+
+Arguments: $ARGUMENTS
+
+## Command Pipeline Execution
+
+Parse pipeline specification from arguments. Supported formats:
+
+### Simple Pipeline
+`init → expand-all → sprint-plan`
+
+### Conditional Pipeline  
+`status → if:pending>10 → sprint-plan → else → next`
+
+### Iterative Pipeline
+`for:pending-tasks → expand → complexity-check`
+
+### Smart Pipeline Patterns
+
+**1. Project Setup Pipeline**
+```
+init [prd] → 
+expand-all → 
+complexity-report → 
+sprint-plan → 
+show first-sprint
+```
+
+**2. Daily Work Pipeline**
+```
+standup →
+if:in-progress → continue →
+else → next → start
+```
+
+**3. Task Completion Pipeline**
+```
+complete [id] →
+git-commit →
+if:blocked-tasks-freed → show-freed →
+next
+```
+
+**4. Quality Check Pipeline**
+```
+list in-progress →
+for:each → check-idle-time →
+if:idle>1day → prompt-update
+```
+
+### Pipeline Features
+
+**Variables**
+- Store results: `status → $count=pending-count`
+- Use in conditions: `if:$count>10`
+- Pass between commands: `expand $high-priority-tasks`
+
+**Error Handling**
+- On failure: `try:complete → catch:show-blockers`
+- Skip on error: `optional:test-run`
+- Retry logic: `retry:3:commit`
+
+**Parallel Execution**
+- Parallel branches: `[analyze | test | lint]`
+- Join results: `parallel → join:report`
+
+### Execution Flow
+
+1. Parse pipeline specification
+2. Validate command sequence
+3. Execute with state passing
+4. Handle conditions and loops
+5. Aggregate results
+6. Show summary
+
+This enables complex workflows like:
+`parse-prd → expand-all → filter:complex>70 → assign:senior → sprint-plan:weighted`

.claude/commands/tm/workflows/smart-flow.md

@@ -0,0 +1,55 @@
+Execute an intelligent workflow based on current project state and recent commands.
+
+This command analyzes:
+1. Recent commands you've run
+2. Current project state
+3. Time of day / day of week
+4. Your working patterns
+
+Arguments: $ARGUMENTS
+
+## Intelligent Workflow Selection
+
+Based on context, I'll determine the best workflow:
+
+### Context Analysis
+- Previous command executed
+- Current task states
+- Unfinished work from last session
+- Your typical patterns
+
+### Smart Execution
+
+If last command was:
+- `status` → Likely starting work → Run daily standup
+- `complete` → Task finished → Find next task
+- `list pending` → Planning → Suggest sprint planning
+- `expand` → Breaking down work → Show complexity analysis
+- `init` → New project → Show onboarding workflow
+
+If no recent commands:
+- Morning? → Daily standup workflow
+- Many pending tasks? → Sprint planning
+- Tasks blocked? → Dependency resolution
+- Friday? → Weekly review
+
+### Workflow Composition
+
+I'll chain appropriate commands:
+1. Analyze current state
+2. Execute primary workflow
+3. Suggest follow-up actions
+4. Prepare environment for coding
+
+### Learning Mode
+
+This command learns from your patterns:
+- Track command sequences
+- Note time preferences
+- Remember common workflows
+- Adapt to your style
+
+Example flows detected:
+- Morning: standup → next → start
+- After lunch: status → continue task
+- End of day: complete → commit → status

.cursor/mcp.json

@@ -8,11 +8,13 @@
 				"PERPLEXITY_API_KEY": "PERPLEXITY_API_KEY_HERE",
 				"OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
 				"GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
+				"GROQ_API_KEY": "GROQ_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"
+				"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE",
+				"GITHUB_API_KEY": "GITHUB_API_KEY_HERE"
 			}
 		}
 	}

.cursor/rules/architecture.mdc

@@ -20,19 +20,21 @@ alwaysApply: false
   - **[`task-manager.js`](mdc:scripts/modules/task-manager.js) & `task-manager/` directory: Task Data & Core Logic**
     - **Purpose**: Contains core functions for task data manipulation (CRUD), AI interactions, and related logic.
     - **Responsibilities**:
-      - Reading/writing `tasks.json`.
+      - Reading/writing `tasks.json` with tagged task lists support.
       - Implementing functions for task CRUD, parsing PRDs, expanding tasks, updating status, etc.
+      - **Tagged Task Lists**: Handles task organization across multiple contexts (tags) like "master", branch names, or project phases.
+      - **Tag Resolution**: Provides backward compatibility by resolving tagged format to legacy format transparently.
       - **Delegating AI interactions** to the `ai-services-unified.js` layer.
       - Accessing non-AI configuration via `config-manager.js` getters.
     - **Key Files**: Individual files within `scripts/modules/task-manager/` handle specific actions (e.g., `add-task.js`, `expand-task.js`).
 
   - **[`dependency-manager.js`](mdc:scripts/modules/dependency-manager.js): Dependency Management**
     - **Purpose**: Manages task dependencies.
-    - **Responsibilities**: Add/remove/validate/fix dependencies.
+    - **Responsibilities**: Add/remove/validate/fix dependencies across tagged task contexts.
 
   - **[`ui.js`](mdc:scripts/modules/ui.js): User Interface Components**
     - **Purpose**: Handles CLI output formatting (tables, colors, boxes, spinners).
-    - **Responsibilities**: Displaying tasks, reports, progress, suggestions.
+    - **Responsibilities**: Displaying tasks, reports, progress, suggestions, and migration notices for tagged systems.
 
   - **[`ai-services-unified.js`](mdc:scripts/modules/ai-services-unified.js): Unified AI Service Layer**
     - **Purpose**: Centralized interface for all LLM interactions using Vercel AI SDK.
@@ -53,6 +55,7 @@ alwaysApply: false
     - **Responsibilities** (See also: [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)):
       - Reads and merges `.taskmasterconfig` with defaults.
       - Provides getters (e.g., `getMainProvider`, `getLogLevel`, `getDefaultSubtasks`) for accessing settings.
+      - **Tag Configuration**: Manages `global.defaultTag` and `tags` section for tag system settings.
       - **Note**: Does **not** store or directly handle API keys (keys are in `.env` or MCP `session.env`).
 
   - **[`utils.js`](mdc:scripts/modules/utils.js): Core Utility Functions**
@@ -62,6 +65,8 @@ alwaysApply: false
       - Task utils (`findTaskById`), Dependency utils (`findCycles`).
       - API Key Resolution (`resolveEnvVariable`).
       - Silent Mode Control (`enableSilentMode`, `disableSilentMode`).
+      - **Tagged Task Lists**: Silent migration system, tag resolution, current tag management.
+      - **Migration System**: `performCompleteTagMigration`, `migrateConfigJson`, `createStateJson`.
 
   - **[`mcp-server/`](mdc:mcp-server/): MCP Server Integration**
     - **Purpose**: Provides MCP interface using FastMCP.
@@ -71,16 +76,42 @@ alwaysApply: false
       - Tool `execute` methods call **direct function wrappers** (`mcp-server/src/core/direct-functions/*.js`), passing the normalized `projectRoot` and other args.
       - Direct functions use path utilities (`mcp-server/src/core/utils/`) to resolve paths based on `projectRoot` from session.
       - Direct functions implement silent mode, logger wrappers, and call core logic functions from `scripts/modules/`.
+      - **Tagged Task Lists**: MCP tools fully support the tagged format with complete tag management capabilities.
       - Manages MCP caching and response formatting.
 
   - **[`init.js`](mdc:scripts/init.js): Project Initialization Logic**
     - **Purpose**: Sets up new Task Master project structure.
-    - **Responsibilities**: Creates directories, copies templates, manages `package.json`, sets up `.cursor/mcp.json`.
+    - **Responsibilities**: Creates directories, copies templates, manages `package.json`, sets up `.cursor/mcp.json`, initializes state.json for tagged system.
+
+## Tagged Task Lists System Architecture
+
+**Data Structure**: Task Master now uses a tagged task lists system where the `tasks.json` file contains multiple named task lists as top-level keys:
+
+```json
+{
+  "master": {
+    "tasks": [/* standard task objects */]
+  },
+  "feature-branch": {
+    "tasks": [/* separate task context */]
+  }
+}
+```
+
+**Key Components:**
+
+- **Silent Migration**: Automatically transforms legacy `{"tasks": [...]}` format to tagged format `{"master": {"tasks": [...]}}` on first read
+- **Tag Resolution Layer**: Provides 100% backward compatibility by intercepting tagged format and returning legacy format to existing code
+- **Configuration Integration**: `global.defaultTag` and `tags` section in config.json manage tag system settings
+- **State Management**: `.taskmaster/state.json` tracks current tag, migration status, and tag-branch mappings
+- **Migration Notice**: User-friendly notification system for seamless migration experience
+
+**Backward Compatibility**: All existing CLI commands and MCP tools continue to work unchanged. The tag resolution layer ensures that existing code receives the expected legacy format while the underlying storage uses the new tagged structure.
 
 - **Data Flow and Module Dependencies (Updated)**:
 
-  - **CLI**: `bin/task-master.js` -> `scripts/dev.js` (loads `.env`) -> `scripts/modules/commands.js` -> Core Logic (`scripts/modules/*`) -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
-  - **MCP**: External Tool -> `mcp-server/server.js` -> Tool (`mcp-server/src/tools/*`) -> Direct Function (`mcp-server/src/core/direct-functions/*`) -> Core Logic (`scripts/modules/*`) -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
+  - **CLI**: `bin/task-master.js` -> `scripts/dev.js` (loads `.env`) -> `scripts/modules/commands.js` -> Core Logic (`scripts/modules/*`) -> **Tag Resolution Layer** -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
+  - **MCP**: External Tool -> `mcp-server/server.js` -> Tool (`mcp-server/src/tools/*`) -> Direct Function (`mcp-server/src/core/direct-functions/*`) -> Core Logic (`scripts/modules/*`) -> **Tag Resolution Layer** -> Unified AI Service (`ai-services-unified.js`) -> Provider Adapters -> LLM API.
   - **Configuration**: Core logic needing non-AI settings calls `config-manager.js` getters (passing `session.env` via `explicitRoot` if from MCP). Unified AI Service internally calls `config-manager.js` getters (using `role`) for AI params and `utils.js` (`resolveEnvVariable` with `session.env`) for API keys.
 
 ## Silent Mode Implementation Pattern in MCP Direct Functions
@@ -197,6 +228,7 @@ By following these patterns consistently, direct functions will properly manage
     - **Integration Tests**: Located in `tests/integration/`, test interactions between modules
     - **End-to-End Tests**: Located in `tests/e2e/`, test complete workflows from a user perspective
     - **Test Fixtures**: Located in `tests/fixtures/`, provide reusable test data
+    - **Tagged System Tests**: Test migration, tag resolution, and multi-context functionality
 
   - **Module Design for Testability**:
     - **Explicit Dependencies**: Functions accept their dependencies as parameters rather than using globals
@@ -205,12 +237,14 @@ By following these patterns consistently, direct functions will properly manage
     - **Clear Module Interfaces**: Each module has well-defined exports that can be mocked in tests
     - **Callback Isolation**: Callbacks are defined as separate functions for easier testing
     - **Stateless Design**: Modules avoid maintaining internal state where possible
+    - **Tag Resolution Testing**: Test both tagged and legacy format handling
 
   - **Mock Integration Patterns**:
     - **External Libraries**: Libraries like `fs`, `commander`, and `@anthropic-ai/sdk` are mocked at module level
     - **Internal Modules**: Application modules are mocked with appropriate spy functions
     - **Testing Function Callbacks**: Callbacks are extracted from mock call arguments and tested in isolation
     - **UI Elements**: Output functions from `ui.js` are mocked to verify display calls
+    - **Tagged Data Mocking**: Test both legacy and tagged task data structures
 
   - **Testing Flow**:
     - Module dependencies are mocked (following Jest's hoisting behavior)
@@ -218,6 +252,7 @@ By following these patterns consistently, direct functions will properly manage
     - Spy functions are set up on module methods
     - Tests call the functions under test and verify behavior
     - Mocks are reset between test cases to maintain isolation
+    - Tagged system behavior is tested for both migration and normal operation
 
 - **Benefits of this Architecture**:
 
@@ -226,8 +261,11 @@ By following these patterns consistently, direct functions will properly manage
     - **Mocking Support**: The clear dependency boundaries make mocking straightforward
     - **Test Isolation**: Each component can be tested without affecting others
     - **Callback Testing**: Function callbacks can be extracted and tested independently
+    - **Multi-Context Testing**: Tagged system enables testing different task contexts independently
   - **Reusability**: Utility functions and UI components can be reused across different parts of the application.
   - **Scalability**:  New features can be added as new modules or by extending existing ones without significantly impacting other parts of the application.
+  - **Multi-Context Support**: Tagged task lists enable working across different contexts (branches, environments, phases) without conflicts.
+  - **Backward Compatibility**: Seamless migration and tag resolution ensure existing workflows continue unchanged.
   - **Clarity**: The modular structure provides a clear separation of concerns, making the codebase easier to navigate and understand for developers.
 
 This architectural overview should help AI models understand the structure and organization of the Task Master CLI codebase, enabling them to more effectively assist with code generation, modification, and understanding.
@@ -249,6 +287,7 @@ Follow these steps to add MCP support for an existing Task Master command (see [
         - Call core logic.
         - Return `{ success: true/false, data/error, fromCache: boolean }`.
     - Export the wrapper function.
+    - **Note**: Tag-aware MCP tools are fully implemented with complete tag management support.
 
 3.  **Update `task-master-core.js` with Import/Export**: Add imports/exports for the new `*Direct` function.
 
@@ -275,12 +314,8 @@ The `initialize_project` command provides a way to set up a new Task Master proj
 - **MCP Tool**: `initialize_project`
 - **Functionality**:
   - Creates necessary directories and files for a new project
-  - Sets up `tasks.json` and initial task files
-  - Configures project metadata (name, description, version)
-  - Handles shell alias creation if requested
-  - Works in both interactive and non-interactive modes
-  - Creates necessary directories and files for a new project
-  - Sets up `tasks.json` and initial task files
+  - Sets up `tasks.json` with tagged structure and initial task files
   - Configures project metadata (name, description, version)
+  - Initializes state.json for tag system
   - Handles shell alias creation if requested
   - Works in both interactive and non-interactive modes

.cursor/rules/commands.mdc

@@ -329,6 +329,60 @@ When implementing commands that delete or remove data (like `remove-task` or `re
   };
   ```
 
+## Context-Aware Command Pattern
+
+For AI-powered commands that benefit from project context, follow the research command pattern:
+
+- **Context Integration**:
+  - ✅ DO: Use `ContextGatherer` utility for multi-source context extraction
+  - ✅ DO: Support task IDs, file paths, custom context, and project tree
+  - ✅ DO: Implement fuzzy search for automatic task discovery
+  - ✅ DO: Display detailed token breakdown for transparency
+
+  ```javascript
+  // ✅ DO: Follow this pattern for context-aware commands
+  programInstance
+    .command('research')
+    .description('Perform AI-powered research queries with project context')
+    .argument('<prompt>', 'Research prompt to investigate')
+    .option('-i, --id <ids>', 'Comma-separated task/subtask IDs to include as context')
+    .option('-f, --files <paths>', 'Comma-separated file paths to include as context')
+    .option('-c, --context <text>', 'Additional custom context')
+    .option('--tree', 'Include project file tree structure')
+    .option('-d, --detail <level>', 'Output detail level: low, medium, high', 'medium')
+    .action(async (prompt, options) => {
+      // 1. Parameter validation and parsing
+      const taskIds = options.id ? parseTaskIds(options.id) : [];
+      const filePaths = options.files ? parseFilePaths(options.files) : [];
+      
+      // 2. Initialize context gatherer
+      const projectRoot = findProjectRoot() || '.';
+      const gatherer = new ContextGatherer(projectRoot, tasksPath);
+      
+      // 3. Auto-discover relevant tasks if none specified
+      if (taskIds.length === 0) {
+        const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+        const discoveredIds = fuzzySearch.getTaskIds(
+          fuzzySearch.findRelevantTasks(prompt)
+        );
+        taskIds.push(...discoveredIds);
+      }
+      
+      // 4. Gather context with token breakdown
+      const contextResult = await gatherer.gather({
+        tasks: taskIds,
+        files: filePaths,
+        customContext: options.context,
+        includeProjectTree: options.projectTree,
+        format: 'research',
+        includeTokenCounts: true
+      });
+      
+      // 5. Display token breakdown and execute AI call
+      // Implementation continues...
+    });
+  ```
+
 ## Error Handling
 
 - **Exception Management**:

.cursor/rules/context_gathering.mdc

@@ -0,0 +1,268 @@
+---
+description: Standardized patterns for gathering and processing context from multiple sources in Task Master commands, particularly for AI-powered features.
+globs: 
+alwaysApply: false
+---
+# Context Gathering Patterns and Utilities
+
+This document outlines the standardized patterns for gathering and processing context from multiple sources in Task Master commands, particularly for AI-powered features.
+
+## Core Context Gathering Utility
+
+The `ContextGatherer` class (`scripts/modules/utils/contextGatherer.js`) provides a centralized, reusable utility for extracting context from multiple sources:
+
+### **Key Features**
+- **Multi-source Context**: Tasks, files, custom text, project file tree
+- **Token Counting**: Detailed breakdown using `gpt-tokens` library
+- **Format Support**: Different output formats (research, chat, system-prompt)
+- **Error Handling**: Graceful handling of missing files, invalid task IDs
+- **Performance**: File size limits, depth limits for tree generation
+
+### **Usage Pattern**
+```javascript
+import { ContextGatherer } from '../utils/contextGatherer.js';
+
+// Initialize with project paths
+const gatherer = new ContextGatherer(projectRoot, tasksPath);
+
+// Gather context with detailed token breakdown
+const result = await gatherer.gather({
+    tasks: ['15', '16.2'],           // Task and subtask IDs
+    files: ['src/api.js', 'README.md'], // File paths
+    customContext: 'Additional context text',
+    includeProjectTree: true,        // Include file tree
+    format: 'research',              // Output format
+    includeTokenCounts: true         // Get detailed token breakdown
+});
+
+// Access results
+const contextString = result.context;
+const tokenBreakdown = result.tokenBreakdown;
+```
+
+### **Token Breakdown Structure**
+```javascript
+{
+    customContext: { tokens: 150, characters: 800 },
+    tasks: [
+        { id: '15', type: 'task', title: 'Task Title', tokens: 245, characters: 1200 },
+        { id: '16.2', type: 'subtask', title: 'Subtask Title', tokens: 180, characters: 900 }
+    ],
+    files: [
+        { path: 'src/api.js', tokens: 890, characters: 4500, size: '4.5 KB' }
+    ],
+    projectTree: { tokens: 320, characters: 1600 },
+    total: { tokens: 1785, characters: 8000 }
+}
+```
+
+## Fuzzy Search Integration
+
+The `FuzzyTaskSearch` class (`scripts/modules/utils/fuzzyTaskSearch.js`) provides intelligent task discovery:
+
+### **Key Features**
+- **Semantic Matching**: Uses Fuse.js for similarity scoring
+- **Purpose Categories**: Pattern-based task categorization
+- **Relevance Scoring**: High/medium/low relevance thresholds
+- **Context-Aware**: Different search configurations for different use cases
+
+### **Usage Pattern**
+```javascript
+import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
+
+// Initialize with tasks data and context
+const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+
+// Find relevant tasks
+const searchResults = fuzzySearch.findRelevantTasks(query, {
+    maxResults: 8,
+    includeRecent: true,
+    includeCategoryMatches: true
+});
+
+// Get task IDs for context gathering
+const taskIds = fuzzySearch.getTaskIds(searchResults);
+```
+
+## Implementation Patterns for Commands
+
+### **1. Context-Aware Command Structure**
+```javascript
+// In command action handler
+async function commandAction(prompt, options) {
+    // 1. Parameter validation and parsing
+    const taskIds = options.id ? parseTaskIds(options.id) : [];
+    const filePaths = options.files ? parseFilePaths(options.files) : [];
+    
+    // 2. Initialize context gatherer
+    const projectRoot = findProjectRoot() || '.';
+    const tasksPath = path.join(projectRoot, 'tasks', 'tasks.json');
+    const gatherer = new ContextGatherer(projectRoot, tasksPath);
+    
+    // 3. Auto-discover relevant tasks if none specified
+    if (taskIds.length === 0) {
+        const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+        const discoveredIds = fuzzySearch.getTaskIds(
+            fuzzySearch.findRelevantTasks(prompt)
+        );
+        taskIds.push(...discoveredIds);
+    }
+    
+    // 4. Gather context with token breakdown
+    const contextResult = await gatherer.gather({
+        tasks: taskIds,
+        files: filePaths,
+        customContext: options.context,
+        includeProjectTree: options.projectTree,
+        format: 'research',
+        includeTokenCounts: true
+    });
+    
+    // 5. Display token breakdown (for CLI)
+    if (outputFormat === 'text') {
+        displayDetailedTokenBreakdown(contextResult.tokenBreakdown);
+    }
+    
+    // 6. Use context in AI call
+    const aiResult = await generateTextService(role, session, systemPrompt, userPrompt);
+    
+    // 7. Display results with enhanced formatting
+    displayResults(aiResult, contextResult.tokenBreakdown);
+}
+```
+
+### **2. Token Display Pattern**
+```javascript
+function displayDetailedTokenBreakdown(tokenBreakdown, systemTokens, userTokens) {
+    const sections = [];
+    
+    // Build context breakdown
+    if (tokenBreakdown.tasks?.length > 0) {
+        const taskDetails = tokenBreakdown.tasks.map(task => 
+            `${task.type === 'subtask' ? '  ' : ''}${task.id}: ${task.tokens.toLocaleString()}`
+        ).join('\n');
+        sections.push(`Tasks (${tokenBreakdown.tasks.reduce((sum, t) => sum + t.tokens, 0).toLocaleString()}):\n${taskDetails}`);
+    }
+    
+    if (tokenBreakdown.files?.length > 0) {
+        const fileDetails = tokenBreakdown.files.map(file =>
+            `  ${file.path}: ${file.tokens.toLocaleString()} (${file.size})`
+        ).join('\n');
+        sections.push(`Files (${tokenBreakdown.files.reduce((sum, f) => sum + f.tokens, 0).toLocaleString()}):\n${fileDetails}`);
+    }
+    
+    // Add prompts breakdown
+    sections.push(`Prompts: system ${systemTokens.toLocaleString()}, user ${userTokens.toLocaleString()}`);
+    
+    // Display in clean box
+    const content = sections.join('\n\n');
+    console.log(boxen(content, {
+        title: chalk.cyan('Token Usage'),
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        borderStyle: 'round',
+        borderColor: 'cyan'
+    }));
+}
+```
+
+### **3. Enhanced Result Display Pattern**
+```javascript
+function displayResults(result, query, detailLevel, tokenBreakdown) {
+    // Header with query info
+    const header = boxen(
+        chalk.green.bold('Research Results') + '\n\n' +
+        chalk.gray('Query: ') + chalk.white(query) + '\n' +
+        chalk.gray('Detail Level: ') + chalk.cyan(detailLevel),
+        {
+            padding: { top: 1, bottom: 1, left: 2, right: 2 },
+            margin: { top: 1, bottom: 0 },
+            borderStyle: 'round',
+            borderColor: 'green'
+        }
+    );
+    console.log(header);
+    
+    // Process and highlight code blocks
+    const processedResult = processCodeBlocks(result);
+    
+    // Main content in clean box
+    const contentBox = boxen(processedResult, {
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        margin: { top: 0, bottom: 1 },
+        borderStyle: 'single',
+        borderColor: 'gray'
+    });
+    console.log(contentBox);
+    
+    console.log(chalk.green('✓ Research complete'));
+}
+```
+
+## Code Block Enhancement
+
+### **Syntax Highlighting Pattern**
+```javascript
+import { highlight } from 'cli-highlight';
+
+function processCodeBlocks(text) {
+    return text.replace(/```(\w+)?\n([\s\S]*?)```/g, (match, language, code) => {
+        try {
+            const highlighted = highlight(code.trim(), { 
+                language: language || 'javascript',
+                theme: 'default'
+            });
+            return `\n${highlighted}\n`;
+        } catch (error) {
+            return `\n${code.trim()}\n`;
+        }
+    });
+}
+```
+
+## Integration Guidelines
+
+### **When to Use Context Gathering**
+- ✅ **DO**: Use for AI-powered commands that benefit from project context
+- ✅ **DO**: Use when users might want to reference specific tasks or files
+- ✅ **DO**: Use for research, analysis, or generation commands
+- ❌ **DON'T**: Use for simple CRUD operations that don't need AI context
+
+### **Performance Considerations**
+- ✅ **DO**: Set reasonable file size limits (50KB default)
+- ✅ **DO**: Limit project tree depth (3-5 levels)
+- ✅ **DO**: Provide token counts to help users understand context size
+- ✅ **DO**: Allow users to control what context is included
+
+### **Error Handling**
+- ✅ **DO**: Gracefully handle missing files with warnings
+- ✅ **DO**: Validate task IDs and provide helpful error messages
+- ✅ **DO**: Continue processing even if some context sources fail
+- ✅ **DO**: Provide fallback behavior when context gathering fails
+
+### **Future Command Integration**
+Commands that should consider adopting this pattern:
+- `analyze-complexity` - Could benefit from file context
+- `expand-task` - Could use related task context
+- `update-task` - Could reference similar tasks for consistency
+- `add-task` - Could use project context for better task generation
+
+## Export Patterns
+
+### **Context Gatherer Module**
+```javascript
+export {
+    ContextGatherer,
+    createContextGatherer  // Factory function
+};
+```
+
+### **Fuzzy Search Module**
+```javascript
+export {
+    FuzzyTaskSearch,
+    PURPOSE_CATEGORIES,
+    RELEVANCE_THRESHOLDS
+};
+```
+
+This context gathering system provides a foundation for building more intelligent, context-aware commands that can leverage project knowledge to provide better AI-powered assistance.

.cursor/rules/dev_workflow.mdc

@@ -1,23 +1,205 @@
 ---
-description: Guide for using Task Master to manage task-driven development workflows
+description: Guide for using Taskmaster to manage task-driven development workflows
 globs: **/*
 alwaysApply: true
 ---
-# Task Master Development Workflow
 
-This guide outlines the typical process for using Task Master to manage software development projects.
+# 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.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to generate initial tasks.json with tagged structure
+-   Configure rule sets during initialization with `--rules` flag (e.g., `task-master init --rules cursor,windsurf`) or manage them later with `task-master rules add/remove` commands  
+-   Begin coding sessions with `get_tasks` / `task-master list` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to see current tasks, status, and IDs
+-   Determine the next task to work on using `next_task` / `task-master next` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before breaking down tasks
+-   Review complexity report using `complexity_report` / `task-master complexity-report` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   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.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to understand implementation requirements
+-   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) 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.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+-   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.mdc`](mdc:.cursor/rules/taskmaster.mdc))
+
+---
+
+## 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
 
-Task Master offers two primary ways to interact:
+Taskmaster offers two primary ways to interact:
 
 1.  **MCP Server (Recommended for Integrated Tools)**:
     - For AI agents and integrated development environments (like Cursor), interacting via the **MCP server is the preferred method**.
-    - The MCP server exposes Task Master functionality through a set of tools (e.g., `get_tasks`, `add_subtask`).
+    - 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.mdc`](mdc:.cursor/rules/mcp.mdc) 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.mdc`](mdc:.cursor/rules/taskmaster.mdc).
     - **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.
@@ -25,31 +207,17 @@ Task Master offers two primary ways to interact:
     - 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.mdc`](mdc:.cursor/rules/taskmaster.mdc) for a detailed command reference.
+    - **Tagged Task Lists**: CLI fully supports the new tagged system with seamless migration.
 
-## Standard Development Workflow Process
+## How the Tag System Works (For Your Reference)
 
--   Start new projects by running `initialize_project` tool / `task-master init` or `parse_prd` / `task-master parse-prd --input='<prd-file.txt>'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to generate initial tasks.json
--   Begin coding sessions with `get_tasks` / `task-master list` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to see current tasks, status, and IDs
--   Determine the next task to work on using `next_task` / `task-master next` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Analyze task complexity with `analyze_project_complexity` / `task-master analyze-complexity --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before breaking down tasks
--   Review complexity report using `complexity_report` / `task-master complexity-report` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Select tasks based on dependencies (all marked 'done'), priority level, and ID order
--   Clarify tasks by checking task files in tasks/ directory or asking for user input
--   View specific task details using `get_task` / `task-master show <id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to understand implementation requirements
--   Break down complex tasks using `expand_task` / `task-master expand --id=<id> --force --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) with appropriate flags like `--force` (to replace existing subtasks) and `--research`.
--   Clear existing subtasks if needed using `clear_subtasks` / `task-master clear-subtasks --id=<id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) before regenerating
--   Implement code following task details, dependencies, and project standards
--   Verify tasks according to test strategies before marking as complete (See [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
--   Mark completed tasks with `set_task_status` / `task-master set-status --id=<id> --status=done` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc))
--   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.mdc`](mdc:.cursor/rules/taskmaster.mdc))
--   Add new tasks discovered during implementation using `add_task` / `task-master add-task --prompt="..." --research` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Add new subtasks as needed using `add_subtask` / `task-master add-subtask --parent=<id> --title="..."` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Append notes or details to subtasks using `update_subtask` / `task-master update-subtask --id=<subtaskId> --prompt='Add implementation notes here...\nMore details...'` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)).
--   Generate task files with `generate` / `task-master generate` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) after updating tasks.json
--   Maintain valid dependency structure with `add_dependency`/`remove_dependency` tools or `task-master add-dependency`/`remove-dependency` commands, `validate_dependencies` / `task-master validate-dependencies`, and `fix_dependencies` / `task-master fix-dependencies` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) when needed
--   Respect dependency chains and task priorities when selecting work
--   Report progress regularly using `get_tasks` / `task-master list`
--   Reorganize tasks as needed using `move_task` / `task-master move --from=<id> --to=<id>` (see [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)) to change task hierarchy or ordering
+- **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.mdc`](mdc:.cursor/rules/taskmaster.mdc) for a full command list.
+
+---
 
 ## Task Complexity Analysis
 
@@ -104,12 +272,13 @@ Task Master offers two primary ways to interact:
 
 Taskmaster configuration is managed through two main mechanisms:
 
-1.  **`.taskmasterconfig` File (Primary):**
+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.
+    *   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.
@@ -117,10 +286,26 @@ Taskmaster configuration is managed through two main mechanisms:
     *   For MCP/Cursor integration, configure these keys in the `env` section of `.cursor/mcp.json`.
     *   Available keys/variables: See `assets/env.example` or the Configuration section in the command reference (previously linked to `taskmaster.mdc`).
 
+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 `.cursor/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, Cursor, Roo Code, Trae, Windsurf (claude, cline, codex, cursor, roo, trae, windsurf)
+- **During Initialization**: Use `task-master init --rules cursor,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., `.cursor/rules`, `.roo/rules`) with appropriate configuration files
+
 ## Determining the Next Task
 
 - Run `next_task` / `task-master next` to show the next task to work on.

.cursor/rules/git_workflow.mdc

@@ -0,0 +1,404 @@
+---
+description: Git workflow integrated with Task Master for feature development and collaboration
+globs: "**/*"
+alwaysApply: true
+---
+# Git Workflow with Task Master Integration
+
+## **Branch Strategy**
+
+### **Main Branch Protection**
+- **main** branch contains production-ready code
+- All feature development happens on task-specific branches
+- Direct commits to main are prohibited
+- All changes merge via Pull Requests
+
+### **Task Branch Naming**
+```bash
+# ✅ DO: Use consistent task branch naming
+task-001  # For Task 1
+task-004  # For Task 4
+task-015  # For Task 15
+
+# ❌ DON'T: Use inconsistent naming
+feature/user-auth
+fix-database-issue
+random-branch-name
+```
+
+## **Tagged Task Lists Integration**
+
+Task Master's **tagged task lists system** provides significant benefits for Git workflows:
+
+### **Multi-Context Development**
+- **Branch-Specific Tasks**: Each branch can have its own task context using tags
+- **Merge Conflict Prevention**: Tasks in different tags are completely isolated
+- **Context Switching**: Seamlessly switch between different development contexts
+- **Parallel Development**: Multiple team members can work on separate task contexts
+
+### **Migration and Compatibility**
+- **Seamless Migration**: Existing projects automatically migrate to use a "master" tag
+- **Zero Disruption**: All existing Git workflows continue unchanged
+- **Backward Compatibility**: Legacy projects work exactly as before
+
+### **Manual Git Integration**
+- **Manual Tag Creation**: Use `--from-branch` option to create tags from current git branch
+- **Manual Context Switching**: Explicitly switch tag contexts as needed for different branches
+- **Simplified Integration**: Focused on manual control rather than automatic workflows
+
+## **Workflow Overview**
+
+```mermaid
+flowchart TD
+    A[Start: On main branch] --> B[Pull latest changes]
+    B --> C[Create task branch<br/>git checkout -b task-XXX]
+    C --> D[Set task status: in-progress]
+    D --> E[Get task context & expand if needed<br/>Tasks automatically use current tag]
+    E --> F[Identify next subtask]
+    
+    F --> G[Set subtask: in-progress]
+    G --> H[Research & collect context<br/>update_subtask with findings]
+    H --> I[Implement subtask]
+    I --> J[Update subtask with completion]
+    J --> K[Set subtask: done]
+    K --> L[Git commit subtask]
+    
+    L --> M{More subtasks?}
+    M -->|Yes| F
+    M -->|No| N[Run final tests]
+    
+    N --> O[Commit tests if added]
+    O --> P[Push task branch]
+    P --> Q[Create Pull Request]
+    Q --> R[Human review & merge]
+    R --> S[Switch to main & pull]
+    S --> T[Delete task branch]
+    T --> U[Ready for next task]
+    
+    style A fill:#e1f5fe
+    style C fill:#f3e5f5
+    style G fill:#fff3e0
+    style L fill:#e8f5e8
+    style Q fill:#fce4ec
+    style R fill:#f1f8e9
+    style U fill:#e1f5fe
+```
+
+## **Complete Task Development Workflow**
+
+### **Phase 1: Task Preparation**
+```bash
+# 1. Ensure you're on main branch and pull latest
+git checkout main
+git pull origin main
+
+# 2. Check current branch status
+git branch  # Verify you're on main
+
+# 3. Create task-specific branch
+git checkout -b task-004  # For Task 4
+
+# 4. Set task status in Task Master (tasks automatically use current tag context)
+# Use: set_task_status tool or `task-master set-status --id=4 --status=in-progress`
+```
+
+### **Phase 2: Task Analysis & Planning**
+```bash
+# 5. Get task context and expand if needed (uses current tag automatically)
+# Use: get_task tool or `task-master show 4`
+# Use: expand_task tool or `task-master expand --id=4 --research --force` (if complex)
+
+# 6. Identify next subtask to work on
+# Use: next_task tool or `task-master next`
+```
+
+### **Phase 3: Subtask Implementation Loop**
+For each subtask, follow this pattern:
+
+```bash
+# 7. Mark subtask as in-progress
+# Use: set_task_status tool or `task-master set-status --id=4.1 --status=in-progress`
+
+# 8. Gather context and research (if needed)
+# Use: update_subtask tool with research flag or:
+# `task-master update-subtask --id=4.1 --prompt="Research findings..." --research`
+
+# 9. Collect code context through AI exploration
+# Document findings in subtask using update_subtask
+
+# 10. Implement the subtask
+# Write code, tests, documentation
+
+# 11. Update subtask with completion details
+# Use: update_subtask tool or:
+# `task-master update-subtask --id=4.1 --prompt="Implementation complete..."`
+
+# 12. Mark subtask as done
+# Use: set_task_status tool or `task-master set-status --id=4.1 --status=done`
+
+# 13. Commit the subtask implementation
+git add .
+git commit -m "feat(task-4): Complete subtask 4.1 - [Subtask Title]
+
+- Implementation details
+- Key changes made
+- Any important notes
+
+Subtask 4.1: [Brief description of what was accomplished]
+Relates to Task 4: [Main task title]"
+```
+
+### **Phase 4: Task Completion**
+```bash
+# 14. When all subtasks are complete, run final testing
+# Create test file if needed, ensure all tests pass
+npm test  # or jest, or manual testing
+
+# 15. If tests were added/modified, commit them
+git add .
+git commit -m "test(task-4): Add comprehensive tests for Task 4
+
+- Unit tests for core functionality
+- Integration tests for API endpoints
+- All tests passing
+
+Task 4: [Main task title] - Testing complete"
+
+# 16. Push the task branch
+git push origin task-004
+
+# 17. Create Pull Request
+# Title: "Task 4: [Task Title]"
+# Description should include:
+# - Task overview
+# - Subtasks completed
+# - Testing approach
+# - Any breaking changes or considerations
+```
+
+### **Phase 5: PR Merge & Cleanup**
+```bash
+# 18. Human reviews and merges PR into main
+
+# 19. Switch back to main and pull merged changes
+git checkout main
+git pull origin main
+
+# 20. Delete the feature branch (optional cleanup)
+git branch -d task-004
+git push origin --delete task-004
+```
+
+## **Commit Message Standards**
+
+### **Subtask Commits**
+```bash
+# ✅ DO: Consistent subtask commit format
+git commit -m "feat(task-4): Complete subtask 4.1 - Initialize Express server
+
+- Set up Express.js with TypeScript configuration
+- Added CORS and body parsing middleware
+- Implemented health check endpoints
+- Basic error handling middleware
+
+Subtask 4.1: Initialize project with npm and install dependencies
+Relates to Task 4: Setup Express.js Server Project"
+
+# ❌ DON'T: Vague or inconsistent commits
+git commit -m "fixed stuff"
+git commit -m "working on task"
+```
+
+### **Test Commits**
+```bash
+# ✅ DO: Separate test commits when substantial
+git commit -m "test(task-4): Add comprehensive tests for Express server setup
+
+- Unit tests for middleware configuration
+- Integration tests for health check endpoints
+- Mock tests for database connection
+- All tests passing with 95% coverage
+
+Task 4: Setup Express.js Server Project - Testing complete"
+```
+
+### **Commit Type Prefixes**
+- `feat(task-X):` - New feature implementation
+- `fix(task-X):` - Bug fixes
+- `test(task-X):` - Test additions/modifications
+- `docs(task-X):` - Documentation updates
+- `refactor(task-X):` - Code refactoring
+- `chore(task-X):` - Build/tooling changes
+
+## **Task Master Commands Integration**
+
+### **Essential Commands for Git Workflow**
+```bash
+# Task management (uses current tag context automatically)
+task-master show <id>           # Get task/subtask details
+task-master next                # Find next task to work on
+task-master set-status --id=<id> --status=<status>
+task-master update-subtask --id=<id> --prompt="..." --research
+
+# Task expansion (for complex tasks)
+task-master expand --id=<id> --research --force
+
+# Progress tracking
+task-master list                # View all tasks and status
+task-master list --status=in-progress  # View active tasks
+```
+
+### **MCP Tool Equivalents**
+When using Cursor or other MCP-integrated tools:
+- `get_task` instead of `task-master show`
+- `next_task` instead of `task-master next`
+- `set_task_status` instead of `task-master set-status`
+- `update_subtask` instead of `task-master update-subtask`
+
+## **Branch Management Rules**
+
+### **Branch Protection**
+```bash
+# ✅ DO: Always work on task branches
+git checkout -b task-005
+# Make changes
+git commit -m "..."
+git push origin task-005
+
+# ❌ DON'T: Commit directly to main
+git checkout main
+git commit -m "..."  # NEVER do this
+```
+
+### **Keeping Branches Updated**
+```bash
+# ✅ DO: Regularly sync with main (for long-running tasks)
+git checkout task-005
+git fetch origin
+git rebase origin/main  # or merge if preferred
+
+# Resolve any conflicts and continue
+```
+
+## **Pull Request Guidelines**
+
+### **PR Title Format**
+```
+Task <ID>: <Task Title>
+
+Examples:
+Task 4: Setup Express.js Server Project
+Task 7: Implement User Authentication
+Task 12: Add Stripe Payment Integration
+```
+
+### **PR Description Template**
+```markdown
+## Task Overview
+Brief description of the main task objective.
+
+## Subtasks Completed
+- [x] 4.1: Initialize project with npm and install dependencies
+- [x] 4.2: Configure TypeScript, ESLint and Prettier  
+- [x] 4.3: Create basic Express app with middleware and health check route
+
+## Implementation Details
+- Key architectural decisions made
+- Important code changes
+- Any deviations from original plan
+
+## Testing
+- [ ] Unit tests added/updated
+- [ ] Integration tests passing
+- [ ] Manual testing completed
+
+## Breaking Changes
+List any breaking changes or migration requirements.
+
+## Related Tasks
+Mention any dependent tasks or follow-up work needed.
+```
+
+## **Conflict Resolution**
+
+### **Task Conflicts with Tagged System**
+```bash
+# With tagged task lists, merge conflicts are significantly reduced:
+# 1. Different branches can use different tag contexts
+# 2. Tasks in separate tags are completely isolated
+# 3. Use Task Master's move functionality to reorganize if needed
+
+# Manual git integration available:
+# - Use `task-master add-tag --from-branch` to create tags from current branch
+# - Manually switch contexts with `task-master use-tag <name>`
+# - Simple, predictable workflow without automatic behavior
+```
+
+### **Code Conflicts**
+```bash
+# Standard Git conflict resolution
+git fetch origin
+git rebase origin/main
+# Resolve conflicts in files
+git add .
+git rebase --continue
+```
+
+## **Emergency Procedures**
+
+### **Hotfixes**
+```bash
+# For urgent production fixes:
+git checkout main
+git pull origin main
+git checkout -b hotfix-urgent-issue
+
+# Make minimal fix
+git commit -m "hotfix: Fix critical production issue
+
+- Specific fix description
+- Minimal impact change
+- Requires immediate deployment"
+
+git push origin hotfix-urgent-issue
+# Create emergency PR for immediate review
+```
+
+### **Task Abandonment**
+```bash
+# If task needs to be abandoned or significantly changed:
+# 1. Update task status
+task-master set-status --id=<id> --status=cancelled
+
+# 2. Clean up branch
+git checkout main
+git branch -D task-<id>
+git push origin --delete task-<id>
+
+# 3. Document reasoning in task
+task-master update-task --id=<id> --prompt="Task cancelled due to..."
+```
+
+## **Tagged System Benefits for Git Workflows**
+
+### **Multi-Team Development**
+- **Isolated Contexts**: Different teams can work on separate tag contexts without conflicts
+- **Feature Branches**: Each feature branch can have its own task context
+- **Release Management**: Separate tags for different release versions or environments
+
+### **Merge Conflict Prevention**
+- **Context Separation**: Tasks in different tags don't interfere with each other
+- **Clean Merges**: Reduced likelihood of task-related merge conflicts
+- **Parallel Development**: Multiple developers can work simultaneously without task conflicts
+
+### **Manual Git Integration**
+- **Branch-Based Tag Creation**: Use `--from-branch` option to create tags from current git branch
+- **Manual Context Management**: Explicitly switch tag contexts as needed
+- **Predictable Workflow**: Simple, manual control without automatic behavior
+
+---
+
+**References:**
+- [Task Master Workflow](mdc:.cursor/rules/dev_workflow.mdc)
+- [Architecture Guidelines](mdc:.cursor/rules/architecture.mdc)
+- [Task Master Commands](mdc:.cursor/rules/taskmaster.mdc)

.cursor/rules/glossary.mdc

@@ -7,20 +7,20 @@ alwaysApply: true
 
 This file provides a quick reference to the purpose of each rule file located in the `.cursor/rules` directory.
 
-- **[`architecture.mdc`](mdc:.cursor/rules/architecture.mdc)**: Describes the high-level architecture of the Task Master CLI application.
+- **[`architecture.mdc`](mdc:.cursor/rules/architecture.mdc)**: Describes the high-level architecture of the Task Master CLI application, including the new tagged task lists system.
 - **[`changeset.mdc`](mdc:.cursor/rules/changeset.mdc)**: Guidelines for using Changesets (npm run changeset) to manage versioning and changelogs.
 - **[`commands.mdc`](mdc:.cursor/rules/commands.mdc)**: Guidelines for implementing CLI commands using Commander.js.
 - **[`cursor_rules.mdc`](mdc:.cursor/rules/cursor_rules.mdc)**: Guidelines for creating and maintaining Cursor rules to ensure consistency and effectiveness.
-- **[`dependencies.mdc`](mdc:.cursor/rules/dependencies.mdc)**: Guidelines for managing task dependencies and relationships.
-- **[`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc)**: Guide for using Task Master to manage task-driven development workflows.
+- **[`dependencies.mdc`](mdc:.cursor/rules/dependencies.mdc)**: Guidelines for managing task dependencies and relationships across tagged task contexts.
+- **[`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc)**: Guide for using Task Master to manage task-driven development workflows with tagged task lists support.
 - **[`glossary.mdc`](mdc:.cursor/rules/glossary.mdc)**: This file; provides a glossary of other Cursor rules.
 - **[`mcp.mdc`](mdc:.cursor/rules/mcp.mdc)**: Guidelines for implementing and interacting with the Task Master MCP Server.
-- **[`new_features.mdc`](mdc:.cursor/rules/new_features.mdc)**: Guidelines for integrating new features into the Task Master CLI.
+- **[`new_features.mdc`](mdc:.cursor/rules/new_features.mdc)**: Guidelines for integrating new features into the Task Master CLI with tagged system considerations.
 - **[`self_improve.mdc`](mdc:.cursor/rules/self_improve.mdc)**: Guidelines for continuously improving Cursor rules based on emerging code patterns and best practices.
-- **[`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)**: Comprehensive reference for Taskmaster MCP tools and CLI commands.
-- **[`tasks.mdc`](mdc:.cursor/rules/tasks.mdc)**: Guidelines for implementing task management operations.
+- **[`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc)**: Comprehensive reference for Taskmaster MCP tools and CLI commands with tagged task lists information.
+- **[`tasks.mdc`](mdc:.cursor/rules/tasks.mdc)**: Guidelines for implementing task management operations with tagged task lists system support.
 - **[`tests.mdc`](mdc:.cursor/rules/tests.mdc)**: Guidelines for implementing and maintaining tests for Task Master CLI.
 - **[`ui.mdc`](mdc:.cursor/rules/ui.mdc)**: Guidelines for implementing and maintaining user interface components.
-- **[`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)**: Guidelines for implementing utility functions.
+- **[`utilities.mdc`](mdc:.cursor/rules/utilities.mdc)**: Guidelines for implementing utility functions including tagged task lists utilities.
 - **[`telemetry.mdc`](mdc:.cursor/rules/telemetry.mdc)**: Guidelines for integrating AI usage telemetry across Task Master.
 

.cursor/rules/new_features.mdc

@@ -24,17 +24,22 @@ alwaysApply: false
 The standard pattern for adding a feature follows this workflow:
 
 1. **Core Logic**: Implement the business logic in the appropriate module (e.g., [`task-manager.js`](mdc:scripts/modules/task-manager.js)).
-2. **AI Integration (If Applicable)**: 
+2. **Context Gathering (If Applicable)**: 
+   - For AI-powered commands that benefit from project context, use the standardized context gathering patterns from [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc).
+   - Import `ContextGatherer` and `FuzzyTaskSearch` utilities for reusable context extraction.
+   - Support multiple context types: tasks, files, custom text, project tree.
+   - Implement detailed token breakdown display for transparency.
+3. **AI Integration (If Applicable)**: 
    - Import necessary service functions (e.g., `generateTextService`, `streamTextService`) from [`ai-services-unified.js`](mdc:scripts/modules/ai-services-unified.js).
    - Prepare parameters (`role`, `session`, `systemPrompt`, `prompt`).
    - Call the service function.
    - Handle the response (direct text or stream object).
    - **Important**: Prefer `generateTextService` for calls sending large context (like stringified JSON) where incremental display is not needed. See [`ai_services.mdc`](mdc:.cursor/rules/ai_services.mdc) for detailed usage patterns and cautions.
-3. **UI Components**: Add any display functions to [`ui.js`](mdc:scripts/modules/ui.js) following [`ui.mdc`](mdc:.cursor/rules/ui.mdc).
-4. **Command Integration**: Add the CLI command to [`commands.js`](mdc:scripts/modules/commands.js) following [`commands.mdc`](mdc:.cursor/rules/commands.mdc).
-5. **Testing**: Write tests for all components of the feature (following [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
-6. **Configuration**: Update configuration settings or add new ones in [`config-manager.js`](mdc:scripts/modules/config-manager.js) and ensure getters/setters are appropriate. Update documentation in [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc). Update the `.taskmasterconfig` structure if needed.
-7. **Documentation**: Update help text and documentation in [`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc).
+4. **UI Components**: Add any display functions to [`ui.js`](mdc:scripts/modules/ui.js) following [`ui.mdc`](mdc:.cursor/rules/ui.mdc). Consider enhanced formatting with syntax highlighting for code blocks.
+5. **Command Integration**: Add the CLI command to [`commands.js`](mdc:scripts/modules/commands.js) following [`commands.mdc`](mdc:.cursor/rules/commands.mdc).
+6. **Testing**: Write tests for all components of the feature (following [`tests.mdc`](mdc:.cursor/rules/tests.mdc))
+7. **Configuration**: Update configuration settings or add new ones in [`config-manager.js`](mdc:scripts/modules/config-manager.js) and ensure getters/setters are appropriate. Update documentation in [`utilities.mdc`](mdc:.cursor/rules/utilities.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc). Update the `.taskmasterconfig` structure if needed.
+8. **Documentation**: Update help text and documentation in [`dev_workflow.mdc`](mdc:.cursor/rules/dev_workflow.mdc) and [`taskmaster.mdc`](mdc:.cursor/rules/taskmaster.mdc).
 
 ## Critical Checklist for New Features
 
@@ -629,3 +634,287 @@ When implementing project initialization commands:
      });
    }
    ```
+
+## Feature Planning
+
+- **Core Logic First**:
+  - ✅ DO: Implement core logic in `scripts/modules/` before CLI or MCP interfaces
+  - ✅ DO: Consider tagged task lists system compatibility from the start
+  - ✅ DO: Design functions to work with both legacy and tagged data formats
+  - ✅ DO: Use tag resolution functions (`getTasksForTag`, `setTasksForTag`) for task data access
+  - ❌ DON'T: Directly manipulate tagged data structure in new features
+
+  ```javascript
+  // ✅ DO: Design tagged-aware core functions
+  async function newFeatureCore(tasksPath, featureParams, options = {}) {
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
+    
+    // Perform feature logic on tasks array
+    const result = performFeatureLogic(tasks, featureParams);
+    
+    // Save back using tag resolution
+    setTasksForTag(tasksData, currentTag, tasks);
+    writeJSON(tasksPath, tasksData);
+    
+    return result;
+  }
+  ```
+
+- **Backward Compatibility**:
+  - ✅ DO: Ensure new features work with existing projects seamlessly
+  - ✅ DO: Test with both legacy and tagged task data formats
+  - ✅ DO: Support silent migration during feature usage
+  - ❌ DON'T: Break existing workflows when adding tagged system features
+
+## CLI Command Implementation
+
+- **Command Structure**:
+  - ✅ DO: Follow the established pattern in [`commands.js`](mdc:scripts/modules/commands.js)
+  - ✅ DO: Use Commander.js for argument parsing
+  - ✅ DO: Include comprehensive help text and examples
+  - ✅ DO: Support tagged task context awareness
+
+  ```javascript
+  // ✅ DO: Implement CLI commands with tagged system awareness
+  program
+    .command('new-feature')
+    .description('Description of the new feature with tagged task lists support')
+    .option('-t, --tag <tag>', 'Specify tag context (defaults to current tag)')
+    .option('-p, --param <value>', 'Feature-specific parameter')
+    .option('--force', 'Force operation without confirmation')
+    .action(async (options) => {
+      try {
+        const projectRoot = findProjectRoot();
+        if (!projectRoot) {
+          console.error('Not in a Task Master project directory');
+          process.exit(1);
+        }
+        
+        // Use specified tag or current tag
+        const targetTag = options.tag || getCurrentTag() || 'master';
+        
+        const result = await newFeatureCore(
+          path.join(projectRoot, '.taskmaster', 'tasks', 'tasks.json'),
+          { param: options.param },
+          { 
+            force: options.force,
+            targetTag: targetTag,
+            outputFormat: 'text'
+          }
+        );
+        
+        console.log('Feature executed successfully');
+      } catch (error) {
+        console.error(`Error: ${error.message}`);
+        process.exit(1);
+      }
+    });
+  ```
+
+- **Error Handling**:
+  - ✅ DO: Provide clear error messages for common failures
+  - ✅ DO: Handle tagged system migration errors gracefully
+  - ✅ DO: Include suggestion for resolution when possible
+  - ✅ DO: Exit with appropriate codes for scripting
+
+## MCP Tool Implementation
+
+- **Direct Function Pattern**:
+  - ✅ DO: Create direct function wrappers in `mcp-server/src/core/direct-functions/`
+  - ✅ DO: Follow silent mode patterns to prevent console output interference
+  - ✅ DO: Use `findTasksJsonPath` for consistent path resolution
+  - ✅ DO: Ensure tagged system compatibility
+
+  ```javascript
+  // ✅ DO: Implement MCP direct functions with tagged awareness
+  export async function newFeatureDirect(args, log, context = {}) {
+    try {
+      const tasksPath = findTasksJsonPath(args, log);
+      
+      // Enable silent mode for clean MCP responses
+      enableSilentMode();
+      
+      try {
+        const result = await newFeatureCore(
+          tasksPath,
+          { param: args.param },
+          { 
+            force: args.force,
+            targetTag: args.tag || 'master', // Support tag specification
+            mcpLog: log,
+            session: context.session,
+            outputFormat: 'json'
+          }
+        );
+        
+        return {
+          success: true,
+          data: result,
+          fromCache: false
+        };
+      } finally {
+        disableSilentMode();
+      }
+    } catch (error) {
+      log.error(`Error in newFeatureDirect: ${error.message}`);
+      return {
+        success: false,
+        error: { code: 'FEATURE_ERROR', message: error.message },
+        fromCache: false
+      };
+    }
+  }
+  ```
+
+- **Tool Registration**:
+  - ✅ DO: Create tool definitions in `mcp-server/src/tools/`
+  - ✅ DO: Use Zod for parameter validation
+  - ✅ DO: Include optional tag parameter for multi-context support
+  - ✅ DO: Follow established naming conventions
+
+  ```javascript
+  // ✅ DO: Register MCP tools with tagged system support
+  export function registerNewFeatureTool(server) {
+    server.addTool({
+      name: "new_feature",
+      description: "Description of the new feature with tagged task lists support",
+      inputSchema: z.object({
+        param: z.string().describe("Feature-specific parameter"),
+        tag: z.string().optional().describe("Target tag context (defaults to current tag)"),
+        force: z.boolean().optional().describe("Force operation without confirmation"),
+        projectRoot: z.string().optional().describe("Project root directory")
+      }),
+      execute: withNormalizedProjectRoot(async (args, { log, session }) => {
+        try {
+          const result = await newFeatureDirect(
+            { ...args, projectRoot: args.projectRoot },
+            log,
+            { session }
+          );
+          return handleApiResult(result, log);
+        } catch (error) {
+          return handleApiResult({
+            success: false,
+            error: { code: 'EXECUTION_ERROR', message: error.message }
+          }, log);
+        }
+      })
+    });
+  }
+  ```
+
+## Testing Strategy
+
+- **Unit Tests**:
+  - ✅ DO: Test core logic independently with both data formats
+  - ✅ DO: Mock file system operations appropriately
+  - ✅ DO: Test tag resolution behavior
+  - ✅ DO: Verify migration compatibility
+
+  ```javascript
+  // ✅ DO: Test new features with tagged system awareness
+  describe('newFeature', () => {
+    beforeEach(() => {
+      jest.clearAllMocks();
+    });
+    
+    it('should work with legacy task format', async () => {
+      const legacyData = { tasks: [/* test data */] };
+      fs.readFileSync.mockReturnValue(JSON.stringify(legacyData));
+      
+      const result = await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      expect(result).toBeDefined();
+      // Test legacy format handling
+    });
+    
+    it('should work with tagged task format', async () => {
+      const taggedData = { 
+        master: { tasks: [/* test data */] },
+        feature: { tasks: [/* test data */] }
+      };
+      fs.readFileSync.mockReturnValue(JSON.stringify(taggedData));
+      
+      const result = await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      expect(result).toBeDefined();
+      // Test tagged format handling
+    });
+    
+    it('should handle tag migration during feature usage', async () => {
+      const legacyData = { tasks: [/* test data */] };
+      fs.readFileSync.mockReturnValue(JSON.stringify(legacyData));
+      
+      await newFeatureCore('/test/tasks.json', { param: 'test' });
+      
+      // Verify migration occurred
+      expect(fs.writeFileSync).toHaveBeenCalledWith(
+        '/test/tasks.json',
+        expect.stringContaining('"master"')
+      );
+    });
+  });
+  ```
+
+- **Integration Tests**:
+  - ✅ DO: Test CLI and MCP interfaces with real task data
+  - ✅ DO: Verify end-to-end workflows across tag contexts
+  - ✅ DO: Test error scenarios and recovery
+
+## Documentation Updates
+
+- **Rule Updates**:
+  - ✅ DO: Update relevant `.cursor/rules/*.mdc` files
+  - ✅ DO: Include tagged system considerations in architecture docs
+  - ✅ DO: Add examples showing multi-context usage
+  - ✅ DO: Update workflow documentation as needed
+
+- **User Documentation**:
+  - ✅ DO: Add feature documentation to `/docs` folder
+  - ✅ DO: Include tagged system usage examples
+  - ✅ DO: Update command reference documentation
+  - ✅ DO: Provide migration notes if relevant
+
+## Migration Considerations
+
+- **Silent Migration Support**:
+  - ✅ DO: Ensure new features trigger migration when needed
+  - ✅ DO: Handle migration errors gracefully in feature code
+  - ✅ DO: Test feature behavior with pre-migration projects
+  - ❌ DON'T: Assume projects are already migrated
+
+- **Tag Context Handling**:
+  - ✅ DO: Default to current tag when not specified
+  - ✅ DO: Support explicit tag selection in advanced features
+  - ✅ DO: Validate tag existence before operations
+  - ✅ DO: Provide clear messaging about tag context
+
+## Performance Considerations
+
+- **Efficient Tag Operations**:
+  - ✅ DO: Minimize file I/O operations per feature execution
+  - ✅ DO: Cache tag resolution results when appropriate
+  - ✅ DO: Use streaming for large task datasets
+  - ❌ DON'T: Load all tags when only one is needed
+
+- **Memory Management**:
+  - ✅ DO: Process large task lists efficiently
+  - ✅ DO: Clean up temporary data structures
+  - ✅ DO: Avoid keeping all tag data in memory simultaneously
+
+## Deployment and Versioning
+
+- **Changesets**:
+  - ✅ DO: Create appropriate changesets for new features
+  - ✅ DO: Use semantic versioning (minor for new features)
+  - ✅ DO: Include tagged system information in release notes
+  - ✅ DO: Document breaking changes if any
+
+- **Feature Flags**:
+  - ✅ DO: Consider feature flags for experimental functionality
+  - ✅ DO: Ensure tagged system features work with flags
+  - ✅ DO: Provide clear documentation about flag usage
+
+By following these guidelines, new features will integrate smoothly with the Task Master ecosystem while supporting the enhanced tagged task lists system for multi-context development workflows.

.cursor/rules/tags.mdc

@@ -0,0 +1,229 @@
+---
+description: 
+globs: scripts/modules/*
+alwaysApply: false
+---
+# Tagged Task Lists Command Patterns
+
+This document outlines the standardized patterns that **ALL** Task Master commands must follow to properly support the tagged task lists system.
+
+## Core Principles
+
+- **Every command** that reads or writes tasks.json must be tag-aware
+- **Consistent tag resolution** across all commands using `getCurrentTag(projectRoot)`
+- **Proper context passing** to core functions with `{ projectRoot, tag }`
+- **Standardized CLI options** with `--tag <tag>` flag
+
+## Required Imports
+
+All command files must import `getCurrentTag`:
+
+```javascript
+// ✅ DO: Import getCurrentTag in commands.js
+import { 
+  log, 
+  readJSON, 
+  writeJSON, 
+  findProjectRoot, 
+  getCurrentTag 
+} from './utils.js';
+
+// ✅ DO: Import getCurrentTag in task-manager files
+import { 
+  readJSON, 
+  writeJSON, 
+  getCurrentTag 
+} from '../utils.js';
+```
+
+## CLI Command Pattern
+
+Every CLI command that operates on tasks must follow this exact pattern:
+
+```javascript
+// ✅ DO: Standard tag-aware CLI command pattern
+programInstance
+  .command('command-name')
+  .description('Command description')
+  .option('-f, --file <file>', 'Path to the tasks file', TASKMASTER_TASKS_FILE)
+  .option('--tag <tag>', 'Specify tag context for task operations') // REQUIRED
+  .action(async (options) => {
+    // 1. Find project root
+    const projectRoot = findProjectRoot();
+    if (!projectRoot) {
+      console.error(chalk.red('Error: Could not find project root.'));
+      process.exit(1);
+    }
+
+    // 2. Resolve tag using standard pattern
+    const tag = options.tag || getCurrentTag(projectRoot) || 'master';
+
+    // 3. Call core function with proper context
+    await coreFunction(
+      tasksPath,
+      // ... other parameters ...
+      { projectRoot, tag } // REQUIRED context object
+    );
+  });
+```
+
+## Core Function Pattern
+
+All core functions in `scripts/modules/task-manager/` must follow this pattern:
+
+```javascript
+// ✅ DO: Standard tag-aware core function pattern
+async function coreFunction(
+  tasksPath,
+  // ... other parameters ...
+  context = {} // REQUIRED context parameter
+) {
+  const { projectRoot, tag } = context;
+  
+  // Use tag-aware readJSON/writeJSON
+  const data = readJSON(tasksPath, projectRoot, tag);
+  
+  // ... function logic ...
+  
+  writeJSON(tasksPath, data, projectRoot, tag);
+}
+```
+
+## Tag Resolution Priority
+
+The tag resolution follows this exact priority order:
+
+1. **Explicit `--tag` flag**: `options.tag`
+2. **Current active tag**: `getCurrentTag(projectRoot)`  
+3. **Default fallback**: `'master'`
+
+```javascript
+// ✅ DO: Standard tag resolution pattern
+const tag = options.tag || getCurrentTag(projectRoot) || 'master';
+```
+
+## Commands Requiring Updates
+
+### High Priority (Core Task Operations)
+- [x] `add-task` - ✅ Fixed
+- [x] `list` - ✅ Fixed  
+- [x] `update-task` - ✅ Fixed
+- [x] `update-subtask` - ✅ Fixed
+- [x] `set-status` - ✅ Already correct
+- [x] `remove-task` - ✅ Already correct
+- [x] `remove-subtask` - ✅ Fixed
+- [x] `add-subtask` - ✅ Already correct
+- [x] `clear-subtasks` - ✅ Fixed
+- [x] `move-task` - ✅ Already correct
+
+### Medium Priority (Analysis & Expansion)
+- [x] `expand` - ✅ Fixed
+- [ ] `next` - ✅ Fixed
+- [ ] `show` (get-task) - Needs checking
+- [ ] `analyze-complexity` - Needs checking
+- [ ] `generate` - ✅ Fixed
+
+### Lower Priority (Utilities)
+- [ ] `research` - Needs checking
+- [ ] `complexity-report` - Needs checking
+- [ ] `validate-dependencies` - ✅ Fixed
+- [ ] `fix-dependencies` - ✅ Fixed
+- [ ] `add-dependency` - ✅ Fixed
+- [ ] `remove-dependency` - ✅ Fixed
+
+## MCP Integration Pattern
+
+MCP direct functions must also follow the tag-aware pattern:
+
+```javascript
+// ✅ DO: Tag-aware MCP direct function
+export async function coreActionDirect(args, log, context = {}) {
+  const { session } = context;
+  const { projectRoot, tag } = args; // MCP passes these in args
+  
+  try {
+    const result = await coreAction(
+      tasksPath,
+      // ... other parameters ...
+      { projectRoot, tag, session, mcpLog: logWrapper }
+    );
+    
+    return { success: true, data: result };
+  } catch (error) {
+    return { success: false, error: { code: 'ERROR_CODE', message: error.message } };
+  }
+}
+```
+
+## File Generation Tag-Aware Naming
+
+The `generate` command must use tag-aware file naming:
+
+```javascript
+// ✅ DO: Tag-aware file naming
+const taskFileName = targetTag === 'master' 
+  ? `task_${task.id.toString().padStart(3, '0')}.txt`
+  : `task_${task.id.toString().padStart(3, '0')}_${targetTag}.txt`;
+```
+
+**Examples:**
+- Master tag: `task_001.txt`, `task_002.txt`
+- Other tags: `task_001_feature.txt`, `task_002_feature.txt`
+
+## Common Anti-Patterns
+
+```javascript
+// ❌ DON'T: Missing getCurrentTag import
+import { readJSON, writeJSON } from '../utils.js'; // Missing getCurrentTag
+
+// ❌ DON'T: Hard-coded tag resolution
+const tag = options.tag || 'master'; // Missing getCurrentTag
+
+// ❌ DON'T: Missing --tag option
+.option('-f, --file <file>', 'Path to tasks file') // Missing --tag option
+
+// ❌ DON'T: Missing context parameter
+await coreFunction(tasksPath, param1, param2); // Missing { projectRoot, tag }
+
+// ❌ DON'T: Incorrect readJSON/writeJSON calls
+const data = readJSON(tasksPath); // Missing projectRoot and tag
+writeJSON(tasksPath, data); // Missing projectRoot and tag
+```
+
+## Validation Checklist
+
+For each command, verify:
+
+- [ ] Imports `getCurrentTag` from utils.js
+- [ ] Has `--tag <tag>` CLI option
+- [ ] Uses standard tag resolution: `options.tag || getCurrentTag(projectRoot) || 'master'`
+- [ ] Finds `projectRoot` with error handling
+- [ ] Passes `{ projectRoot, tag }` context to core functions
+- [ ] Core functions accept and use context parameter
+- [ ] Uses `readJSON(tasksPath, projectRoot, tag)` and `writeJSON(tasksPath, data, projectRoot, tag)`
+
+## Testing Tag Resolution
+
+Test each command with:
+
+```bash
+# Test with explicit tag
+node bin/task-master command-name --tag test-tag
+
+# Test with active tag (should use current active tag)
+node bin/task-master use-tag test-tag
+node bin/task-master command-name
+
+# Test with master tag (default)
+node bin/task-master use-tag master  
+node bin/task-master command-name
+```
+
+## Migration Strategy
+
+1. **Audit Phase**: Systematically check each command against the checklist
+2. **Fix Phase**: Apply the standard patterns to non-compliant commands
+3. **Test Phase**: Verify tag resolution works correctly
+4. **Document Phase**: Update command documentation with tag support
+
+This ensures consistent, predictable behavior across all Task Master commands and prevents tag deletion bugs.

.cursor/rules/taskmaster.mdc

@@ -11,6 +11,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 **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
@@ -24,6 +26,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `--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'.`
+    *   `--no-git`: `Skip initializing a Git repository entirely.`
     *   `-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.`
@@ -34,9 +37,11 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `noGit`: `Skip initializing a Git repository entirely. Default is false.` (CLI: `--no-git`)
     *   `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 Cursor. 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 scripts/example_prd.txt. 
+*   **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`)
 
@@ -45,12 +50,12 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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 'tasks/tasks.json'.` (CLI: `-o, --output <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 `scripts/example_prd.txt` as a template for creating the PRD based on their idea, for use with `parse-prd`.
+*   **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`.
 
 ---
 
@@ -74,13 +79,14 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `--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 `.taskmasterconfig` 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.
+*   **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 .taskmasterconfig 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.
+*   **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.
 
 ---
 
@@ -92,8 +98,9 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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, e.g., 'pending' or 'done'.` (CLI: `-s, --status <status>`)
+    *   `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.
 
@@ -104,17 +111,20 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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 a specific Taskmaster task or subtask by its ID.`
+*   **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', or subtask, e.g., '15.2', you want to view.` (CLI: `[id]` positional or `-i, --id <id>`)
+    *   `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, implementation notes, and test strategy for a specific task before starting work.
+*   **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.
 
 ---
 
@@ -130,6 +140,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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.
@@ -148,6 +159,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `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.
 
@@ -160,6 +172,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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.
@@ -168,13 +181,15 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 
 *   **MCP Tool:** `update_task`
 *   **CLI Command:** `task-master update-task [options]`
-*   **Description:** `Modify a specific Taskmaster task or subtask by its ID, incorporating new information or changes.`
+*   **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', or subtask, e.g., '15.2', you want to update.` (CLI: `-i, --id <id>`)
+    *   `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 or feedback. Example CLI: `task-master update-task --id='15' --prompt='Clarification: Use PostgreSQL instead of MySQL.\nUpdate schema details...'`
+*   **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`)
@@ -183,11 +198,12 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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 specific ID of the Taskmaster subtask, e.g., '15.2', you want to add information to.` (CLI: `-i, --id <id>`)
-    *   `prompt`: `Required. Provide the information or notes Taskmaster should append to the subtask's details. Ensure this adds *new* information not already present.` (CLI: `-p, --prompt <text>`)
+    *   `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:** Add implementation notes, code snippets, or clarifications to a subtask during development. Before calling, review the subtask's current details to append only fresh insights, helping to build a detailed log of the implementation journey and avoid redundancy. Example CLI: `task-master update-subtask --id='15.2' --prompt='Discovered that the API requires header X.\nImplementation needs adjustment...'`
+*   **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`)
@@ -198,6 +214,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
 
@@ -209,6 +226,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
@@ -228,6 +246,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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.
@@ -242,6 +261,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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.
@@ -252,8 +272,9 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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>`)
+    *   `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.
 
@@ -266,6 +287,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
     *   `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`)
+    *   `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.
 
@@ -277,6 +299,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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
@@ -306,6 +329,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
 
@@ -317,6 +341,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
 
@@ -326,6 +351,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
 
@@ -335,6 +361,7 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
 
@@ -348,9 +375,10 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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: 'scripts/task-complexity-report.json').` (CLI: `-o, --output <file>`)
+    *   `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.
@@ -361,7 +389,8 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **CLI Command:** `task-master complexity-report [options]`
 *   **Description:** `Display the task complexity analysis report in a readable format.`
 *   **Key Parameters/Options:**
-    *   `file`: `Path to the complexity report (default: 'scripts/task-complexity-report.json').` (CLI: `-f, --file <file>`)
+    *   `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.
 
 ---
@@ -375,14 +404,137 @@ This document provides a detailed reference for interacting with Taskmaster, cov
 *   **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.
+*   **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 **`.taskmasterconfig`** file (in project root) for configuration (models, parameters, logging level, etc.), managed via `task-master models --setup`.
+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:
 
@@ -395,13 +547,13 @@ Environment variables are used **only** for sensitive API keys related to AI pro
     *   `AZURE_OPENAI_API_KEY` (Requires `AZURE_OPENAI_ENDPOINT` too)
     *   `OPENROUTER_API_KEY`
     *   `XAI_API_KEY`
-    *   `OLLANA_API_KEY` (Requires `OLLAMA_BASE_URL` too)
-*   **Endpoints (Optional/Provider Specific inside .taskmasterconfig):**
+    *   `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 **`.cursor/mcp.json`** file (for MCP/Cursor integration). All other settings (model choice, max tokens, temperature, log level, custom endpoints) are managed in `.taskmasterconfig` via `task-master models` command or `models` MCP tool.
+**Set API keys** in your **`.env`** file in the project root (for CLI use) or within the `env` section of your **`.cursor/mcp.json`** file (for MCP/Cursor 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 [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).
+For details on how these commands fit into the development process, see the [Development Workflow Guide](mdc:.cursor/rules/dev_workflow.mdc).

.cursor/rules/tasks.mdc

@@ -3,9 +3,19 @@ description: Guidelines for implementing task management operations
 globs: scripts/modules/task-manager.js
 alwaysApply: false
 ---
-
 # Task Management Guidelines
 
+## Tagged Task Lists System
+
+Task Master now uses a **tagged task lists system** for multi-context task management:
+
+- **Data Structure**: Tasks are organized into separate contexts (tags) within `tasks.json`
+- **Legacy Format**: `{"tasks": [...]}`
+- **Tagged Format**: `{"master": {"tasks": [...]}, "feature-branch": {"tasks": [...]}}`
+- **Silent Migration**: Legacy format automatically converts to tagged format on first use
+- **Tag Resolution**: Core functions receive legacy format for 100% backward compatibility
+- **Default Tag**: "master" is used for all existing and new tasks unless otherwise specified
+
 ## Task Structure Standards
 
 - **Core Task Properties**:
@@ -28,6 +38,25 @@ alwaysApply: false
   };
   ```
 
+- **Tagged Data Structure**:
+  - ✅ DO: Access tasks through tag resolution layer
+  - ✅ DO: Use `getTasksForTag(data, tagName)` to retrieve tasks for a specific tag
+  - ✅ DO: Use `setTasksForTag(data, tagName, tasks)` to update tasks for a specific tag
+  - ❌ DON'T: Directly manipulate the tagged structure in core functions
+
+  ```javascript
+  // ✅ DO: Use tag resolution functions
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
+  // Manipulate tasks as normal...
+  
+  // Save back to the tagged structure
+  setTasksForTag(tasksData, currentTag, tasks);
+  writeJSON(tasksPath, tasksData);
+  ```
+
 - **Subtask Structure**:
   - ✅ DO: Use consistent properties across subtasks
   - ✅ DO: Maintain simple numeric IDs within parent tasks
@@ -48,53 +77,56 @@ alwaysApply: false
 ## Task Creation and Parsing
 
 - **ID Management**:
-  - ✅ DO: Assign unique sequential IDs to tasks
-  - ✅ DO: Calculate the next ID based on existing tasks
-  - ❌ DON'T: Hardcode or reuse IDs
+  - ✅ DO: Assign unique sequential IDs to tasks within each tag context
+  - ✅ DO: Calculate the next ID based on existing tasks in the current tag
+  - ❌ DON'T: Hardcode or reuse IDs within the same tag
 
   ```javascript
-  // ✅ DO: Calculate the next available ID
-  const highestId = Math.max(...data.tasks.map(t => t.id));
+  // ✅ DO: Calculate the next available ID within the current tag
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  const highestId = Math.max(...tasks.map(t => t.id));
   const nextTaskId = highestId + 1;
   ```
 
 - **PRD Parsing**:
   - ✅ DO: Extract tasks from PRD documents using AI
+  - ✅ DO: Create tasks in the current tag context (defaults to "master")
   - ✅ DO: Provide clear prompts to guide AI task generation
   - ✅ DO: Validate and clean up AI-generated tasks
 
   ```javascript
-  // ✅ DO: Validate AI responses
-  try {
-    // Parse the JSON response
-    taskData = JSON.parse(jsonContent);
-    
-    // Check that we have the required fields
-    if (!taskData.title || !taskData.description) {
-      throw new Error("Missing required fields in the generated task");
-    }
-  } catch (error) {
-    log('error', "Failed to parse AI's response as valid task JSON:", error);
-    process.exit(1);
-  }
+  // ✅ DO: Parse into current tag context
+  const tasksData = readJSON(tasksPath) || {};
+  const currentTag = getCurrentTag() || 'master';
+  
+  // Parse tasks and add to current tag
+  const newTasks = await parseTasksFromPRD(prdContent);
+  setTasksForTag(tasksData, currentTag, newTasks);
+  writeJSON(tasksPath, tasksData);
   ```
 
 ## Task Updates and Modifications
 
 - **Status Management**:
-  - ✅ DO: Provide functions for updating task status
+  - ✅ DO: Provide functions for updating task status within current tag context
   - ✅ DO: Handle both individual tasks and subtasks
   - ✅ DO: Consider subtask status when updating parent tasks
 
   ```javascript
-  // ✅ DO: Handle status updates for both tasks and subtasks
+  // ✅ DO: Handle status updates within tagged context
   async function setTaskStatus(tasksPath, taskIdInput, newStatus) {
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
+    
     // Check if it's a subtask (e.g., "1.2")
     if (taskIdInput.includes('.')) {
       const [parentId, subtaskId] = taskIdInput.split('.').map(id => parseInt(id, 10));
       
       // Find the parent task and subtask
-      const parentTask = data.tasks.find(t => t.id === parentId);
+      const parentTask = tasks.find(t => t.id === parentId);
       const subtask = parentTask.subtasks.find(st => st.id === subtaskId);
       
       // Update subtask status
@@ -109,7 +141,7 @@ alwaysApply: false
       }
     } else {
       // Handle regular task
-      const task = data.tasks.find(t => t.id === parseInt(taskIdInput, 10));
+      const task = tasks.find(t => t.id === parseInt(taskIdInput, 10));
       task.status = newStatus;
       
       // If marking as done, also mark subtasks
@@ -119,16 +151,24 @@ alwaysApply: false
         });
       }
     }
+    
+    // Save updated tasks back to tagged structure
+    setTasksForTag(tasksData, currentTag, tasks);
+    writeJSON(tasksPath, tasksData);
   }
   ```
 
 - **Task Expansion**:
-  - ✅ DO: Use AI to generate detailed subtasks
+  - ✅ DO: Use AI to generate detailed subtasks within current tag context
   - ✅ DO: Consider complexity analysis for subtask counts
   - ✅ DO: Ensure proper IDs for newly created subtasks
 
   ```javascript
   // ✅ DO: Generate appropriate subtasks based on complexity
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   if (taskAnalysis) {
     log('info', `Found complexity analysis for task ${taskId}: Score ${taskAnalysis.complexityScore}/10`);
     
@@ -138,6 +178,11 @@ alwaysApply: false
       log('info', `Using recommended number of subtasks: ${numSubtasks}`);
     }
   }
+  
+  // Generate subtasks and save back
+  // ... subtask generation logic ...
+  setTasksForTag(tasksData, currentTag, tasks);
+  writeJSON(tasksPath, tasksData);
   ```
 
 ## Task File Generation
@@ -155,67 +200,65 @@ alwaysApply: false
   
   // Format dependencies with their status
   if (task.dependencies && task.dependencies.length > 0) {
-    content += `# Dependencies: ${formatDependenciesWithStatus(task.dependencies, data.tasks)}\n`;
+    content += `# Dependencies: ${formatDependenciesWithStatus(task.dependencies, tasks)}\n`;
   } else {
     content += '# Dependencies: None\n';
   }
   ```
 
-- **Subtask Inclusion**:
-  - ✅ DO: Include subtasks in parent task files
-  - ✅ DO: Use consistent indentation for subtask sections
-  - ✅ DO: Display subtask dependencies with proper formatting
+- **Tagged Context Awareness**:
+  - ✅ DO: Generate task files from current tag context
+  - ✅ DO: Include tag information in generated files
+  - ❌ DON'T: Mix tasks from different tags in file generation
 
   ```javascript
-  // ✅ DO: Format subtasks correctly in task files
-  if (task.subtasks && task.subtasks.length > 0) {
-    content += '\n# Subtasks:\n';
+  // ✅ DO: Generate files for current tag context
+  async function generateTaskFiles(tasksPath, outputDir) {
+    const tasksData = readJSON(tasksPath);
+    const currentTag = getCurrentTag() || 'master';
+    const tasks = getTasksForTag(tasksData, currentTag);
     
-    task.subtasks.forEach(subtask => {
-      content += `## ${subtask.id}. ${subtask.title} [${subtask.status || 'pending'}]\n`;
-      
-      // Format subtask dependencies
-      if (subtask.dependencies && subtask.dependencies.length > 0) {
-        // Format the dependencies
-        content += `### Dependencies: ${formattedDeps}\n`;
-      } else {
-        content += '### Dependencies: None\n';
-      }
-      
-      content += `### Description: ${subtask.description || ''}\n`;
-      content += '### Details:\n';
-      content += (subtask.details || '').split('\n').map(line => line).join('\n');
-      content += '\n\n';
-    });
+    // Add tag context to file header
+    let content = `# Tag Context: ${currentTag}\n`;
+    content += `# Task ID: ${task.id}\n`;
+    // ... rest of file generation
   }
   ```
 
 ## Task Listing and Display
 
 - **Filtering and Organization**:
-  - ✅ DO: Allow filtering tasks by status
+  - ✅ DO: Allow filtering tasks by status within current tag context
   - ✅ DO: Handle subtask display in lists
   - ✅ DO: Use consistent table formats
 
   ```javascript
-  // ✅ DO: Implement clear filtering and organization
+  // ✅ DO: Implement clear filtering within tag context
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   // Filter tasks by status if specified
   const filteredTasks = statusFilter 
-    ? data.tasks.filter(task => 
+    ? tasks.filter(task => 
         task.status && task.status.toLowerCase() === statusFilter.toLowerCase())
-    : data.tasks;
+    : tasks;
   ```
 
 - **Progress Tracking**:
-  - ✅ DO: Calculate and display completion statistics
+  - ✅ DO: Calculate and display completion statistics for current tag
   - ✅ DO: Track both task and subtask completion
   - ✅ DO: Use visual progress indicators
 
   ```javascript
-  // ✅ DO: Track and display progress
+  // ✅ DO: Track and display progress within tag context
+  const tasksData = readJSON(tasksPath);
+  const currentTag = getCurrentTag() || 'master';
+  const tasks = getTasksForTag(tasksData, currentTag);
+  
   // Calculate completion statistics
-  const totalTasks = data.tasks.length;
-  const completedTasks = data.tasks.filter(task => 
+  const totalTasks = tasks.length;
+  const completedTasks = tasks.filter(task => 
     task.status === 'done' || task.status === 'completed').length;
   const completionPercentage = totalTasks > 0 ? (completedTasks / totalTasks) * 100 : 0;
   
@@ -223,7 +266,7 @@ alwaysApply: false
   let totalSubtasks = 0;
   let completedSubtasks = 0;
   
-  data.tasks.forEach(task => {
+  tasks.forEach(task => {
     if (task.subtasks && task.subtasks.length > 0) {
       totalSubtasks += task.subtasks.length;
       completedSubtasks += task.subtasks.filter(st => 
@@ -232,99 +275,52 @@ alwaysApply: false
   });
   ```
 
-## Complexity Analysis
+## Migration and Compatibility
 
-- **Scoring System**:
-  - ✅ DO: Use AI to analyze task complexity
-  - ✅ DO: Include complexity scores (1-10)
-  - ✅ DO: Generate specific expansion recommendations
+- **Silent Migration Handling**:
+  - ✅ DO: Implement silent migration in `readJSON()` function
+  - ✅ DO: Detect legacy format and convert automatically
+  - ✅ DO: Preserve all existing task data during migration
 
   ```javascript
-  // ✅ DO: Handle complexity analysis properly
-  const report = {
-    meta: {
-      generatedAt: new Date().toISOString(),
-      tasksAnalyzed: tasksData.tasks.length,
-      thresholdScore: thresholdScore,
-      projectName: tasksData.meta?.projectName || 'Your Project Name',
-      usedResearch: useResearch
-    },
-    complexityAnalysis: complexityAnalysis
-  };
-  ```
-
-- **Analysis-Based Workflow**:
-  - ✅ DO: Use complexity reports to guide task expansion
-  - ✅ DO: Prioritize complex tasks for more detailed breakdown
-  - ✅ DO: Use expansion prompts from complexity analysis
-
-  ```javascript
-  // ✅ DO: Apply complexity analysis to workflow
-  // Sort tasks by complexity if report exists, otherwise by ID
-  if (complexityReport && complexityReport.complexityAnalysis) {
-    log('info', 'Sorting tasks by complexity...');
+  // ✅ DO: Handle silent migration (implemented in utils.js)
+  function readJSON(filepath) {
+    let data = JSON.parse(fs.readFileSync(filepath, 'utf8'));
     
-    // Create a map of task IDs to complexity scores
-    const complexityMap = new Map();
-    complexityReport.complexityAnalysis.forEach(analysis => {
-      complexityMap.set(analysis.taskId, analysis.complexityScore);
-    });
+    // Silent migration for tasks.json files
+    if (data.tasks && Array.isArray(data.tasks) && !data.master && isTasksFile) {
+      const migratedData = {
+        master: {
+          tasks: data.tasks
+        }
+      };
+      writeJSON(filepath, migratedData);
+      data = migratedData;
+    }
     
-    // Sort tasks by complexity score (high to low)
-    tasksToExpand.sort((a, b) => {
-      const scoreA = complexityMap.get(a.id) || 0;
-      const scoreB = complexityMap.get(b.id) || 0;
-      return scoreB - scoreA;
-    });
+    return data;
   }
   ```
 
-## Next Task Selection
-
-- **Eligibility Criteria**:
-  - ✅ DO: Consider dependencies when finding next tasks
-  - ✅ DO: Prioritize by task priority and dependency count
-  - ✅ DO: Skip completed tasks
+- **Tag Resolution**:
+  - ✅ DO: Use tag resolution functions to maintain backward compatibility
+  - ✅ DO: Return legacy format to core functions
+  - ❌ DON'T: Expose tagged structure to existing core logic
 
   ```javascript
-  // ✅ DO: Use proper task prioritization logic
-  function findNextTask(tasks) {
-    // Get all completed task IDs
-    const completedTaskIds = new Set(
-      tasks
-        .filter(t => t.status === 'done' || t.status === 'completed')
-        .map(t => t.id)
-    );
+  // ✅ DO: Use tag resolution layer
+  function getTasksForTag(data, tagName) {
+    if (data.tasks && Array.isArray(data.tasks)) {
+      // Legacy format - return as-is
+      return data.tasks;
+    }
     
-    // Filter for pending tasks whose dependencies are all satisfied
-    const eligibleTasks = tasks.filter(task => 
-      (task.status === 'pending' || task.status === 'in-progress') && 
-      task.dependencies && 
-      task.dependencies.every(depId => completedTaskIds.has(depId))
-    );
+    if (data[tagName] && data[tagName].tasks) {
+      // Tagged format - return tasks for specified tag
+      return data[tagName].tasks;
+    }
     
-    // Sort by priority, dependency count, and ID
-    const priorityValues = { 'high': 3, 'medium': 2, 'low': 1 };
-    
-    const nextTask = eligibleTasks.sort((a, b) => {
-      // Priority first
-      const priorityA = priorityValues[a.priority || 'medium'] || 2;
-      const priorityB = priorityValues[b.priority || 'medium'] || 2;
-      
-      if (priorityB !== priorityA) {
-        return priorityB - priorityA; // Higher priority first
-      }
-      
-      // Dependency count next
-      if (a.dependencies.length !== b.dependencies.length) {
-        return a.dependencies.length - b.dependencies.length; // Fewer dependencies first
-      }
-      
-      // ID last
-      return a.id - b.id; // Lower ID first
-    })[0];
-    
-    return nextTask;
+    return [];
   }
   ```
 

.cursor/rules/ui.mdc

@@ -150,4 +150,91 @@ alwaysApply: false
   ));
   ```
 
-Refer to [`ui.js`](mdc:scripts/modules/ui.js) for implementation examples and [`new_features.mdc`](mdc:.cursor/rules/new_features.mdc) for integration guidelines. 
+## Enhanced Display Patterns
+
+### **Token Breakdown Display**
+- Use detailed, granular token breakdowns for AI-powered commands
+- Display context sources with individual token counts
+- Show both token count and character count for transparency
+
+  ```javascript
+  // ✅ DO: Display detailed token breakdown
+  function displayDetailedTokenBreakdown(tokenBreakdown, systemTokens, userTokens) {
+    const sections = [];
+    
+    if (tokenBreakdown.tasks?.length > 0) {
+      const taskDetails = tokenBreakdown.tasks.map(task => 
+        `${task.type === 'subtask' ? '  ' : ''}${task.id}: ${task.tokens.toLocaleString()}`
+      ).join('\n');
+      sections.push(`Tasks (${tokenBreakdown.tasks.reduce((sum, t) => sum + t.tokens, 0).toLocaleString()}):\n${taskDetails}`);
+    }
+    
+    const content = sections.join('\n\n');
+    console.log(boxen(content, {
+      title: chalk.cyan('Token Usage'),
+      padding: { top: 1, bottom: 1, left: 2, right: 2 },
+      borderStyle: 'round',
+      borderColor: 'cyan'
+    }));
+  }
+  ```
+
+### **Code Block Syntax Highlighting**
+- Use `cli-highlight` library for syntax highlighting in terminal output
+- Process code blocks in AI responses for better readability
+
+  ```javascript
+  // ✅ DO: Enhance code blocks with syntax highlighting
+  import { highlight } from 'cli-highlight';
+  
+  function processCodeBlocks(text) {
+    return text.replace(/```(\w+)?\n([\s\S]*?)```/g, (match, language, code) => {
+      try {
+        const highlighted = highlight(code.trim(), { 
+          language: language || 'javascript',
+          theme: 'default'
+        });
+        return `\n${highlighted}\n`;
+      } catch (error) {
+        return `\n${code.trim()}\n`;
+      }
+    });
+  }
+  ```
+
+### **Multi-Section Result Display**
+- Use separate boxes for headers, content, and metadata
+- Maintain consistent styling across different result types
+
+  ```javascript
+  // ✅ DO: Use structured result display
+  function displayResults(result, query, detailLevel) {
+    // Header with query info
+    const header = boxen(
+      chalk.green.bold('Research Results') + '\n\n' +
+      chalk.gray('Query: ') + chalk.white(query) + '\n' +
+      chalk.gray('Detail Level: ') + chalk.cyan(detailLevel),
+      {
+        padding: { top: 1, bottom: 1, left: 2, right: 2 },
+        margin: { top: 1, bottom: 0 },
+        borderStyle: 'round',
+        borderColor: 'green'
+      }
+    );
+    console.log(header);
+    
+    // Process and display main content
+    const processedResult = processCodeBlocks(result);
+    const contentBox = boxen(processedResult, {
+      padding: { top: 1, bottom: 1, left: 2, right: 2 },
+      margin: { top: 0, bottom: 1 },
+      borderStyle: 'single',
+      borderColor: 'gray'
+    });
+    console.log(contentBox);
+    
+    console.log(chalk.green('✓ Operation complete'));
+  }
+  ```
+
+Refer to [`ui.js`](mdc:scripts/modules/ui.js) for implementation examples, [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc) for context display patterns, and [`new_features.mdc`](mdc:.cursor/rules/new_features.mdc) for integration guidelines. 

.cursor/rules/utilities.mdc

@@ -1,6 +1,6 @@
 ---
-description: Guidelines for implementing utility functions
-globs: scripts/modules/utils.js, mcp-server/src/**/*
+description: 
+globs: 
 alwaysApply: false
 ---
 # Utility Function Guidelines
@@ -46,7 +46,7 @@ alwaysApply: false
 - **Location**:
     - **Core CLI Utilities**: Place utilities used primarily by the core `task-master` CLI logic and command modules (`scripts/modules/*`) into [`scripts/modules/utils.js`](mdc:scripts/modules/utils.js).
     - **MCP Server Utilities**: Place utilities specifically designed to support the MCP server implementation into the appropriate subdirectories within `mcp-server/src/`.
-        - Path/Core Logic Helpers: [`mcp-server/src/core/utils/`](mdc:mcp-server/src/core/utils/) (e.g., `path-utils.js`).
+        - Path/Core Logic Helpers: [`mcp-server/src/core/utils/`](mdc:mcp-server/src/core/utils) (e.g., `path-utils.js`).
         - Tool Execution/Response Helpers: [`mcp-server/src/tools/utils.js`](mdc:mcp-server/src/tools/utils.js).
 
 ## Documentation Standards
@@ -110,7 +110,7 @@ Taskmaster configuration (excluding API keys) is primarily managed through the `
   - ✅ DO: Use appropriate icons for different log levels
   - ✅ DO: Respect the configured log level
   - ❌ DON'T: Add direct console.log calls outside the logging utility
-  - **Note on Passed Loggers**: When a logger object (like the FastMCP `log` object) is passed *as a parameter* (e.g., as `mcpLog`) into core Task Master functions, the receiving function often expects specific methods (`.info`, `.warn`, `.error`, etc.) to be directly callable on that object (e.g., `mcpLog[level](...)`). If the passed logger doesn't have this exact structure, a wrapper object may be needed. See the **Handling Logging Context (`mcpLog`)** section in [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) for the standard pattern used in direct functions.
+  - **Note on Passed Loggers**: When a logger object (like the FastMCP `log` object) is passed *as a parameter* (e.g., as `mcpLog`) into core Task Master functions, the receiving function often expects specific methods (`.info`, `.warn`, `.error`, etc.) to be directly callable on that object (e.g., `mcpLog[level](mdc:...)`). If the passed logger doesn't have this exact structure, a wrapper object may be needed. See the **Handling Logging Context (`mcpLog`)** section in [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) for the standard pattern used in direct functions.
 
 - **Logger Wrapper Pattern**: 
   - ✅ DO: Use the logger wrapper pattern when passing loggers to prevent `mcpLog[level] is not a function` errors:
@@ -548,4 +548,628 @@ export {
 };
 ```
 
-Refer to [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for more context on MCP server architecture and integration. 
+## Context Gathering Utilities
+
+### **ContextGatherer** (`scripts/modules/utils/contextGatherer.js`)
+
+- **Multi-Source Context Extraction**:
+  - ✅ DO: Use for AI-powered commands that need project context
+  - ✅ DO: Support tasks, files, custom text, and project tree context
+  - ✅ DO: Implement detailed token counting with `gpt-tokens` library
+  - ✅ DO: Provide multiple output formats (research, chat, system-prompt)
+
+  ```javascript
+  // ✅ DO: Use ContextGatherer for consistent context extraction
+  import { ContextGatherer } from '../utils/contextGatherer.js';
+  
+  const gatherer = new ContextGatherer(projectRoot, tasksPath);
+  const result = await gatherer.gather({
+    tasks: ['15', '16.2'],
+    files: ['src/api.js'],
+    customContext: 'Additional context',
+    includeProjectTree: true,
+    format: 'research',
+    includeTokenCounts: true
+  });
+  ```
+
+### **FuzzyTaskSearch** (`scripts/modules/utils/fuzzyTaskSearch.js`)
+
+- **Intelligent Task Discovery**:
+  - ✅ DO: Use for automatic task relevance detection
+  - ✅ DO: Configure search parameters based on use case context
+  - ✅ DO: Implement purpose-based categorization for better matching
+  - ✅ DO: Sort results by relevance score and task ID
+
+  ```javascript
+  // ✅ DO: Use FuzzyTaskSearch for intelligent task discovery
+  import { FuzzyTaskSearch } from '../utils/fuzzyTaskSearch.js';
+  
+  const fuzzySearch = new FuzzyTaskSearch(tasksData.tasks, 'research');
+  const searchResults = fuzzySearch.findRelevantTasks(query, {
+    maxResults: 8,
+    includeRecent: true,
+    includeCategoryMatches: true
+  });
+  const taskIds = fuzzySearch.getTaskIds(searchResults);
+  ```
+
+- **Integration Guidelines**:
+  - ✅ DO: Use fuzzy search to supplement user-provided task IDs
+  - ✅ DO: Display discovered task IDs to users for transparency
+  - ✅ DO: Sort discovered task IDs numerically for better readability
+  - ❌ DON'T: Replace explicit user task selections with fuzzy results
+
+Refer to [`context_gathering.mdc`](mdc:.cursor/rules/context_gathering.mdc) for detailed implementation patterns, [`mcp.mdc`](mdc:.cursor/rules/mcp.mdc) and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for more context on MCP server architecture and integration. 
+
+## File System Operations
+
+- **JSON File Handling**:
+  - ✅ DO: Use `readJSON` and `writeJSON` for all JSON operations
+  - ✅ DO: Include error handling for file operations
+  - ✅ DO: Validate JSON structure after reading
+  - ❌ DON'T: Use raw `fs.readFileSync` or `fs.writeFileSync` for JSON
+
+  ```javascript
+  // ✅ DO: Use utility functions with error handling
+  function readJSON(filepath) {
+    try {
+      if (!fs.existsSync(filepath)) {
+        return null; // or appropriate default
+      }
+      
+      let data = JSON.parse(fs.readFileSync(filepath, 'utf8'));
+      
+      // Silent migration for tasks.json files: Transform old format to tagged format
+      const isTasksFile = filepath.includes('tasks.json') || path.basename(filepath) === 'tasks.json';
+      
+      if (data && data.tasks && Array.isArray(data.tasks) && !data.master && isTasksFile) {
+        // Migrate from old format { "tasks": [...] } to new format { "master": { "tasks": [...] } }
+        const migratedData = {
+          master: {
+            tasks: data.tasks
+          }
+        };
+        
+        writeJSON(filepath, migratedData);
+        
+        // Set global flag for CLI notice and perform complete migration
+        global.taskMasterMigrationOccurred = true;
+        performCompleteTagMigration(filepath);
+        
+        data = migratedData;
+      }
+      
+      return data;
+    } catch (error) {
+      log('error', `Failed to read JSON from ${filepath}: ${error.message}`);
+      return null;
+    }
+  }
+  
+  function writeJSON(filepath, data) {
+    try {
+      const dirPath = path.dirname(filepath);
+      if (!fs.existsSync(dirPath)) {
+        fs.mkdirSync(dirPath, { recursive: true });
+      }
+      fs.writeFileSync(filepath, JSON.stringify(data, null, 2));
+    } catch (error) {
+      log('error', `Failed to write JSON to ${filepath}: ${error.message}`);
+      throw error;
+    }
+  }
+  ```
+
+- **Path Resolution**:
+  - ✅ DO: Use `path.join()` for cross-platform path construction
+  - ✅ DO: Use `path.resolve()` for absolute paths
+  - ✅ DO: Validate paths before file operations
+
+  ```javascript
+  // ✅ DO: Handle paths correctly
+  function findProjectRoot(startPath = process.cwd()) {
+    let currentPath = path.resolve(startPath);
+    const rootPath = path.parse(currentPath).root;
+    
+    while (currentPath !== rootPath) {
+      const taskMasterPath = path.join(currentPath, '.taskmaster');
+      if (fs.existsSync(taskMasterPath)) {
+        return currentPath;
+      }
+      currentPath = path.dirname(currentPath);
+    }
+    
+    return null; // Not found
+  }
+  ```
+
+## Tagged Task Lists System Utilities
+
+- **Tag Resolution Functions**:
+  - ✅ DO: Use tag resolution layer for all task data access
+  - ✅ DO: Provide backward compatibility with legacy format
+  - ✅ DO: Default to "master" tag when no tag is specified
+
+  ```javascript
+  // ✅ DO: Implement tag resolution functions
+  function getTasksForTag(data, tagName = 'master') {
+    if (!data) {
+      return [];
+    }
+    
+    // Handle legacy format - direct tasks array
+    if (data.tasks && Array.isArray(data.tasks)) {
+      return data.tasks;
+    }
+    
+    // Handle tagged format - tasks under specific tag
+    if (data[tagName] && data[tagName].tasks && Array.isArray(data[tagName].tasks)) {
+      return data[tagName].tasks;
+    }
+    
+    return [];
+  }
+  
+  function setTasksForTag(data, tagName = 'master', tasks) {
+    // Ensure data object exists
+    if (!data) {
+      data = {};
+    }
+    
+    // Create tag structure if it doesn't exist
+    if (!data[tagName]) {
+      data[tagName] = {};
+    }
+    
+    // Set tasks for the tag
+    data[tagName].tasks = tasks;
+    
+    return data;
+  }
+  
+  function getCurrentTag() {
+    // Get current tag from state.json or default to 'master'
+    try {
+      const projectRoot = findProjectRoot();
+      if (!projectRoot) return 'master';
+      
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      if (fs.existsSync(statePath)) {
+        const state = readJSON(statePath);
+        return state.currentTag || 'master';
+      }
+    } catch (error) {
+      log('debug', `Error reading current tag: ${error.message}`);
+    }
+    
+    return 'master';
+  }
+  ```
+
+- **Migration Functions**:
+  - ✅ DO: Implement complete migration for all related files
+  - ✅ DO: Handle configuration and state file creation
+  - ✅ DO: Provide migration status tracking
+
+  ```javascript
+  // ✅ DO: Implement complete migration system
+  function performCompleteTagMigration(tasksJsonPath) {
+    try {
+      // Derive project root from tasks.json path
+      const projectRoot = findProjectRoot(path.dirname(tasksJsonPath)) || path.dirname(tasksJsonPath);
+      
+      // 1. Migrate config.json - add defaultTag and tags section
+      const configPath = path.join(projectRoot, '.taskmaster', 'config.json');
+      if (fs.existsSync(configPath)) {
+        migrateConfigJson(configPath);
+      }
+      
+      // 2. Create state.json if it doesn't exist
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      if (!fs.existsSync(statePath)) {
+        createStateJson(statePath);
+      }
+      
+      if (getDebugFlag()) {
+        log('debug', 'Completed tagged task lists migration for project');
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error during complete tag migration: ${error.message}`);
+      }
+    }
+  }
+  
+  function migrateConfigJson(configPath) {
+    try {
+      const config = readJSON(configPath);
+      if (!config) return;
+      
+      let modified = false;
+      
+      // Add global.defaultTag if missing
+      if (!config.global) {
+        config.global = {};
+      }
+      if (!config.global.defaultTag) {
+        config.global.defaultTag = 'master';
+        modified = true;
+      }
+      
+      // Add tags section if missing
+      if (!config.tags) {
+        config.tags = {
+                  // Git integration settings removed - now manual only
+        };
+        modified = true;
+      }
+      
+      if (modified) {
+        writeJSON(configPath, config);
+        if (getDebugFlag()) {
+          log('debug', 'Updated config.json with tagged task system settings');
+        }
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error migrating config.json: ${error.message}`);
+      }
+    }
+  }
+  
+  function createStateJson(statePath) {
+    try {
+      const initialState = {
+        currentTag: 'master',
+        lastSwitched: new Date().toISOString(),
+        migrationNoticeShown: false
+      };
+      
+      writeJSON(statePath, initialState);
+      if (getDebugFlag()) {
+        log('debug', 'Created initial state.json for tagged task system');
+      }
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error creating state.json: ${error.message}`);
+      }
+    }
+  }
+  
+  function markMigrationForNotice() {
+    try {
+      const projectRoot = findProjectRoot();
+      if (!projectRoot) return;
+      
+      const statePath = path.join(projectRoot, '.taskmaster', 'state.json');
+      const state = readJSON(statePath) || {};
+      
+      state.migrationNoticeShown = false; // Reset to show notice
+      writeJSON(statePath, state);
+    } catch (error) {
+      if (getDebugFlag()) {
+        log('warn', `Error marking migration for notice: ${error.message}`);
+      }
+    }
+  }
+  ```
+
+## Logging Functions
+
+- **Consistent Logging**:
+  - ✅ DO: Use the central `log` function for all output
+  - ✅ DO: Use appropriate log levels (info, warn, error, debug)
+  - ✅ DO: Support silent mode for programmatic usage
+
+  ```javascript
+  // ✅ DO: Implement consistent logging with silent mode
+  let silentMode = false;
+  
+  function log(level, ...messages) {
+    if (silentMode && level !== 'error') {
+      return; // Suppress non-error logs in silent mode
+    }
+    
+    const timestamp = new Date().toISOString();
+    const formattedMessage = messages.join(' ');
+    
+    switch (level) {
+      case 'error':
+        console.error(`[ERROR] ${formattedMessage}`);
+        break;
+      case 'warn':
+        console.warn(`[WARN] ${formattedMessage}`);
+        break;
+      case 'info':
+        console.log(`[INFO] ${formattedMessage}`);
+        break;
+      case 'debug':
+        if (getDebugFlag()) {
+          console.log(`[DEBUG] ${formattedMessage}`);
+        }
+        break;
+      default:
+        console.log(formattedMessage);
+    }
+  }
+  
+  function enableSilentMode() {
+    silentMode = true;
+  }
+  
+  function disableSilentMode() {
+    silentMode = false;
+  }
+  
+  function isSilentMode() {
+    return silentMode;
+  }
+  ```
+
+## Task Utilities
+
+- **Task Finding and Manipulation**:
+  - ✅ DO: Use tagged task system aware functions
+  - ✅ DO: Handle both task and subtask operations
+  - ✅ DO: Validate task IDs before operations
+
+  ```javascript
+  // ✅ DO: Implement tag-aware task utilities
+  function findTaskById(tasks, taskId) {
+    if (!Array.isArray(tasks)) {
+      return null;
+    }
+    return tasks.find(task => task.id === taskId) || null;
+  }
+  
+  function findSubtaskById(tasks, parentId, subtaskId) {
+    const parentTask = findTaskById(tasks, parentId);
+    if (!parentTask || !parentTask.subtasks) {
+      return null;
+    }
+    
+    return parentTask.subtasks.find(subtask => subtask.id === subtaskId) || null;
+  }
+  
+  function getNextTaskId(tasks) {
+    if (!Array.isArray(tasks) || tasks.length === 0) {
+      return 1;
+    }
+    
+    const maxId = Math.max(...tasks.map(task => task.id));
+    return maxId + 1;
+  }
+  
+  function getNextSubtaskId(parentTask) {
+    if (!parentTask.subtasks || parentTask.subtasks.length === 0) {
+      return 1;
+    }
+    
+    const maxId = Math.max(...parentTask.subtasks.map(subtask => subtask.id));
+    return maxId + 1;
+  }
+  ```
+
+## String Utilities
+
+- **Text Processing**:
+  - ✅ DO: Handle text truncation appropriately
+  - ✅ DO: Provide consistent formatting functions
+  - ✅ DO: Support different output formats
+
+  ```javascript
+  // ✅ DO: Implement useful string utilities
+  function truncate(str, maxLength = 50) {
+    if (!str || typeof str !== 'string') {
+      return '';
+    }
+    
+    if (str.length <= maxLength) {
+      return str;
+    }
+    
+    return str.substring(0, maxLength - 3) + '...';
+  }
+  
+  function formatDuration(ms) {
+    const seconds = Math.floor(ms / 1000);
+    const minutes = Math.floor(seconds / 60);
+    const hours = Math.floor(minutes / 60);
+    
+    if (hours > 0) {
+      return `${hours}h ${minutes % 60}m ${seconds % 60}s`;
+    } else if (minutes > 0) {
+      return `${minutes}m ${seconds % 60}s`;
+    } else {
+      return `${seconds}s`;
+    }
+  }
+  
+  function capitalizeFirst(str) {
+    if (!str || typeof str !== 'string') {
+      return '';
+    }
+    
+    return str.charAt(0).toUpperCase() + str.slice(1).toLowerCase();
+  }
+  ```
+
+## Dependency Management Utilities
+
+- **Dependency Analysis**:
+  - ✅ DO: Detect circular dependencies
+  - ✅ DO: Validate dependency references
+  - ✅ DO: Support cross-tag dependency checking (future enhancement)
+
+  ```javascript
+  // ✅ DO: Implement dependency utilities
+  function findCycles(tasks) {
+    const cycles = [];
+    const visited = new Set();
+    const recStack = new Set();
+    
+    function dfs(taskId, path = []) {
+      if (recStack.has(taskId)) {
+        // Found a cycle
+        const cycleStart = path.indexOf(taskId);
+        const cycle = path.slice(cycleStart).concat([taskId]);
+        cycles.push(cycle);
+        return;
+      }
+      
+      if (visited.has(taskId)) {
+        return;
+      }
+      
+      visited.add(taskId);
+      recStack.add(taskId);
+      
+      const task = findTaskById(tasks, taskId);
+      if (task && task.dependencies) {
+        task.dependencies.forEach(depId => {
+          dfs(depId, path.concat([taskId]));
+        });
+      }
+      
+      recStack.delete(taskId);
+    }
+    
+    tasks.forEach(task => {
+      if (!visited.has(task.id)) {
+        dfs(task.id);
+      }
+    });
+    
+    return cycles;
+  }
+  
+  function validateDependencies(tasks) {
+    const validationErrors = [];
+    const taskIds = new Set(tasks.map(task => task.id));
+    
+    tasks.forEach(task => {
+      if (task.dependencies) {
+        task.dependencies.forEach(depId => {
+          if (!taskIds.has(depId)) {
+            validationErrors.push({
+              taskId: task.id,
+              invalidDependency: depId,
+              message: `Task ${task.id} depends on non-existent task ${depId}`
+            });
+          }
+        });
+      }
+    });
+    
+    return validationErrors;
+  }
+  ```
+
+## Environment and Configuration Utilities
+
+- **Environment Variable Resolution**:
+  - ✅ DO: Support both `.env` files and MCP session environment
+  - ✅ DO: Provide fallbacks for missing values
+  - ✅ DO: Handle API key resolution correctly
+
+  ```javascript
+  // ✅ DO: Implement flexible environment resolution
+  function resolveEnvVariable(key, sessionEnv = null) {
+    // First check session environment (for MCP)
+    if (sessionEnv && sessionEnv[key]) {
+      return sessionEnv[key];
+    }
+    
+    // Then check process environment
+    if (process.env[key]) {
+      return process.env[key];
+    }
+    
+    // Finally try .env file if in project root
+    try {
+      const projectRoot = findProjectRoot();
+      if (projectRoot) {
+        const envPath = path.join(projectRoot, '.env');
+        if (fs.existsSync(envPath)) {
+          const envContent = fs.readFileSync(envPath, 'utf8');
+          const lines = envContent.split('\n');
+          
+          for (const line of lines) {
+            const [envKey, envValue] = line.split('=');
+            if (envKey && envKey.trim() === key) {
+              return envValue ? envValue.trim().replace(/^["']|["']$/g, '') : undefined;
+            }
+          }
+        }
+      }
+    } catch (error) {
+      log('debug', `Error reading .env file: ${error.message}`);
+    }
+    
+    return undefined;
+  }
+  
+  function getDebugFlag() {
+    const debugFlag = resolveEnvVariable('TASKMASTER_DEBUG') || 
+                     resolveEnvVariable('DEBUG') || 
+                     'false';
+    return debugFlag.toLowerCase() === 'true';
+  }
+  ```
+
+## Export Pattern
+
+- **Module Exports**:
+  - ✅ DO: Export all utility functions explicitly
+  - ✅ DO: Group related functions logically
+  - ✅ DO: Include new tagged system utilities
+
+  ```javascript
+  // ✅ DO: Export utilities in logical groups
+  module.exports = {
+    // File system utilities
+    readJSON,
+    writeJSON,
+    findProjectRoot,
+    
+    // Tagged task system utilities
+    getTasksForTag,
+    setTasksForTag,
+    getCurrentTag,
+    performCompleteTagMigration,
+    migrateConfigJson,
+    createStateJson,
+    markMigrationForNotice,
+    
+    // Logging utilities
+    log,
+    enableSilentMode,
+    disableSilentMode,
+    isSilentMode,
+    
+    // Task utilities
+    findTaskById,
+    findSubtaskById,
+    getNextTaskId,
+    getNextSubtaskId,
+    
+    // String utilities
+    truncate,
+    formatDuration,
+    capitalizeFirst,
+    
+    // Dependency utilities
+    findCycles,
+    validateDependencies,
+    
+    // Environment utilities
+    resolveEnvVariable,
+    getDebugFlag,
+    
+    // Legacy utilities (maintained for compatibility)
+    aggregateTelemetry
+  };
+  ```
+
+Refer to [`utils.js`](mdc:scripts/modules/utils.js) for implementation examples and [`architecture.mdc`](mdc:.cursor/rules/architecture.mdc) for integration patterns.

.env.example

@@ -4,6 +4,13 @@ PERPLEXITY_API_KEY=YOUR_PERPLEXITY_KEY_HERE
 OPENAI_API_KEY=YOUR_OPENAI_KEY_HERE
 GOOGLE_API_KEY=YOUR_GOOGLE_KEY_HERE
 MISTRAL_API_KEY=YOUR_MISTRAL_KEY_HERE
+GROQ_API_KEY=YOUR_GROQ_KEY_HERE
 OPENROUTER_API_KEY=YOUR_OPENROUTER_KEY_HERE
 XAI_API_KEY=YOUR_XAI_KEY_HERE
 AZURE_OPENAI_API_KEY=YOUR_AZURE_KEY_HERE
+
+# Google Vertex AI Configuration
+VERTEX_PROJECT_ID=your-gcp-project-id
+VERTEX_LOCATION=us-central1
+# Optional: Path to service account credentials JSON file (alternative to API key)
+GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account-credentials.json

.github/workflows/update-models-md.yml

@@ -0,0 +1,40 @@
+name: Update models.md from supported-models.json
+
+on:
+  push:
+    branches:
+      - main
+      - next
+    paths:
+      - 'scripts/modules/supported-models.json'
+      - 'docs/scripts/models-json-to-markdown.js'
+
+jobs:
+  update_markdown:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Run transformation script
+        run: node docs/scripts/models-json-to-markdown.js
+
+      - name: Format Markdown with Prettier
+        run: npx prettier --write docs/models.md
+
+      - name: Stage docs/models.md
+        run: git add docs/models.md
+
+      - name: Commit & Push docs/models.md
+        uses: actions-js/push@master
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          branch: ${{ github.ref_name }}
+          message: 'docs: Auto-update and format models.md'
+          author_name: 'github-actions[bot]'
+          author_email: 'github-actions[bot]@users.noreply.github.com'

.gitignore

@@ -19,13 +19,26 @@ npm-debug.log*
 yarn-debug.log*
 yarn-error.log*
 lerna-debug.log*
-tests/e2e/_runs/
-tests/e2e/log/
 
 # Coverage directory used by tools like istanbul
-coverage
+coverage/
 *.lcov
 
+# Jest cache
+.jest/
+
+# Test temporary files and directories
+tests/temp/
+tests/e2e/_runs/
+tests/e2e/log/
+tests/**/*.log
+tests/**/coverage/
+
+# Test database files (if any)
+tests/**/*.db
+tests/**/*.sqlite
+tests/**/*.sqlite3
+
 # Optional npm cache directory
 .npm
 
@@ -64,3 +77,13 @@ dev-debug.log
 
 # NPMRC
 .npmrc
+
+# Added by Task Master AI
+# Editor directories and files
+.idea
+.vscode
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?

.nvmrc

@@ -0,0 +1 @@
+22 

.prettierignore

@@ -1,7 +0,0 @@
-# Ignore artifacts:
-build
-coverage
-.changeset
-tasks
-package-lock.json
-tests/fixture/*.json

.prettierrc

@@ -1,11 +0,0 @@
-{
-	"printWidth": 80,
-	"tabWidth": 2,
-	"useTabs": true,
-	"semi": true,
-	"singleQuote": true,
-	"trailingComma": "none",
-	"bracketSpacing": true,
-	"arrowParens": "always",
-	"endOfLine": "lf"
-}

.taskmaster/config.json

@@ -0,0 +1,37 @@
+{
+	"models": {
+		"main": {
+			"provider": "groq",
+			"modelId": "llama-3.1-8b-instant",
+			"maxTokens": 131072,
+			"temperature": 0.2
+		},
+		"research": {
+			"provider": "groq",
+			"modelId": "llama-3.3-70b-versatile",
+			"maxTokens": 32768,
+			"temperature": 0.1
+		},
+		"fallback": {
+			"provider": "anthropic",
+			"modelId": "claude-3-7-sonnet-20250219",
+			"maxTokens": 128000,
+			"temperature": 0.2
+		}
+	},
+	"global": {
+		"logLevel": "info",
+		"debug": false,
+		"defaultNumTasks": 10,
+		"defaultSubtasks": 5,
+		"defaultPriority": "medium",
+		"projectName": "Taskmaster",
+		"ollamaBaseURL": "http://localhost:11434/api",
+		"bedrockBaseURL": "https://bedrock.us-east-1.amazonaws.com",
+		"responseLanguage": "English",
+		"userId": "1234567890",
+		"azureBaseURL": "https://your-endpoint.azure.com/",
+		"defaultTag": "master"
+	},
+	"claudeCode": {}
+}

.taskmaster/docs/README.md

@@ -382,25 +382,25 @@ The output report structure is:
 
 ```json
 {
-	"meta": {
-		"generatedAt": "2023-06-15T12:34:56.789Z",
-		"tasksAnalyzed": 20,
-		"thresholdScore": 5,
-		"projectName": "Your Project Name",
-		"usedResearch": true
-	},
-	"complexityAnalysis": [
-		{
-			"taskId": 8,
-			"taskTitle": "Develop Implementation Drift Handling",
-			"complexityScore": 9.5,
-			"recommendedSubtasks": 6,
-			"expansionPrompt": "Create subtasks that handle detecting...",
-			"reasoning": "This task requires sophisticated logic...",
-			"expansionCommand": "node scripts/dev.js expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
-		}
-		// More tasks sorted by complexity score (highest first)
-	]
+ "meta": {
+  "generatedAt": "2023-06-15T12:34:56.789Z",
+  "tasksAnalyzed": 20,
+  "thresholdScore": 5,
+  "projectName": "Your Project Name",
+  "usedResearch": true
+ },
+ "complexityAnalysis": [
+  {
+   "taskId": 8,
+   "taskTitle": "Develop Implementation Drift Handling",
+   "complexityScore": 9.5,
+   "recommendedSubtasks": 6,
+   "expansionPrompt": "Create subtasks that handle detecting...",
+   "reasoning": "This task requires sophisticated logic...",
+   "expansionCommand": "node scripts/dev.js expand --id=8 --num=6 --prompt=\"Create subtasks...\" --research"
+  }
+  // More tasks sorted by complexity score (highest first)
+ ]
 }
 ```
 

.taskmaster/docs/research/2025-06-14_how-can-i-improve-the-scope-up-and-scope-down-comm.md

@@ -0,0 +1,128 @@
+---
+title: Research Session
+query: "how can i improve the scope-up and scope-down command"
+date: 6/14/2025
+time: 4:35:03 PM
+timestamp: 2025-06-14T20:35:03.231Z
+exchanges: 2
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** how can i improve the scope-up and scope-down command
+
+**Response:**
+
+## Improving the `scope-up` and `scope-down` Commands
+
+**Clarify Command Purpose and User Experience**
+
+- Ensure the commands have clear, intuitive behavior. For example, `scope-up` should consistently broaden the context or task view, while `scope-down` should reliably narrow it.
+- Provide immediate, user-friendly feedback after each command, indicating what changed (e.g., "Now viewing parent task and all subtasks" or "Focused on subtask: X").
+- Document the commands with examples in your `docs/command-reference.md` and `docs/examples.md` to help users understand their effects and use cases.
+
+**Enhance Context Awareness**
+
+- Make the commands context-sensitive: if the user is already at the top or bottom of the scope hierarchy, return a helpful message instead of failing silently.
+- Allow optional arguments to specify the exact level or target (e.g., `scope-up 2` to move up two levels, or `scope-down <subtask-id>` to jump directly to a subtask).
+
+**Robust Error Handling and Validation**
+
+- Implement checks to prevent invalid operations, such as attempting to scope up from the root or scope down when no subtasks exist.
+- Provide clear error messages and suggestions for next steps, improving user trust and reducing confusion[1][5].
+
+**Integrate with Task and Tag Systems**
+
+- Ensure `scope-up` and `scope-down` interact smoothly with your tagging and task hierarchy features. For example, scoping up from a subtask should show the parent task and its context, while scoping down should allow selection from available subtasks or related tags.
+- Consider supporting batch operations, such as scoping down into all subtasks and displaying them in a summarized view.
+
+**Improve Performance and Synchronization**
+
+- Optimize the underlying logic to minimize delays, especially in large task trees. Use asynchronous operations where possible to keep the UI responsive.
+- If the commands trigger data loading or context switching, ensure synchronization so that subsequent commands operate on the correct, updated context[2][4].
+
+**Testing and Stakeholder Feedback**
+
+- Add or expand unit and integration tests for these commands (see `tests/unit/commands.test.js` and `integration/cli/commands.test.js`) to cover edge cases and ensure reliability.
+- Gather feedback from users and stakeholders to identify pain points and desired enhancements, then iterate on the command design and implementation[1][5].
+
+**Example Improvements Table**
+
+| Area                | Current Issue                | Suggested Improvement                        |
+|---------------------|-----------------------------|----------------------------------------------|
+| User Feedback       | Minimal or unclear output    | Add explicit, contextual messages            |
+| Error Handling      | Silent failures              | Informative errors and recovery suggestions  |
+| Flexibility         | Only single-level movement   | Support multi-level and targeted navigation  |
+| Integration         | Limited context awareness    | Sync with tags, parent/child relationships   |
+| Performance         | Slow on large hierarchies    | Optimize data access and UI updates          |
+
+By focusing on these areas, you can make `scope-up` and `scope-down` more robust, user-friendly, and aligned with best practices in scope management and command design[1][5].
+
+---
+
+## Follow-up 1
+
+**Question:** how might i do this relative to the tag system?
+
+**Response:**
+
+## Integrating Scope-Up and Scope-Down with the Tag System
+
+**Conceptual Mapping**
+
+- In your project, *scope-up* and *scope-down* commands currently operate on the task hierarchy, broadening or narrowing the context by moving between parent and child tasks.
+- The tag system provides a parallel, orthogonal way to group and filter tasks—tags can represent categories, priorities, or any custom grouping, independent of strict parent/child relationships.
+
+**How to Make Scope Commands Tag-Aware**
+
+- **Scoping by Tag**: Allow users to "scope-down" into a tag, viewing only tasks associated with that tag. Conversely, "scope-up" could move from a specific tag context back to the broader task list or to a parent tag grouping if you support tag hierarchies.
+- **Tag-Scoped Views**: When a tag is active as the current scope, all navigation and operations (listing, editing, etc.) are limited to tasks with that tag. This is similar to how some systems let you set the "Tag Scope" to filter navigation and search to only tagged items[1][5].
+- **Combining Hierarchy and Tags**: Enable compound scoping, such as "all subtasks of Task X that also have Tag Y." This can be implemented by intersecting the results of hierarchical and tag-based queries.
+
+**Implementation Strategies**
+
+- **Scope Stack or Context Object**: Maintain a stack or context object that tracks both the current task scope and any active tag filters. Each scope change (up/down or tag in/out) updates this context.
+- **Commands**:
+  - `scope-down --tag <tag>`: Narrows the view to tasks with the specified tag.
+  - `scope-up --tag`: Removes the tag filter, broadening the view.
+  - `scope-down <subtask-id> --tag <tag>`: Narrows to a specific subtask *and* applies a tag filter.
+- **Tag Hierarchies (Optional)**: If your tag system supports parent/child tags or tag groups, allow "scope-up" to move from a specific tag to its parent tag or group, and "scope-down" to move into a child tag[4][5].
+
+**Example User Flows**
+
+- *Scoping Down by Tag*:  
+  User runs `scope-down --tag urgent` → Only tasks tagged "urgent" are shown.
+- *Combining Task and Tag*:  
+  User runs `scope-down <task-id> --tag frontend` → Only subtasks of `<task-id>` that are tagged "frontend" are shown.
+- *Scoping Up from Tag*:  
+  User runs `scope-up --tag` → Removes the tag filter, returning to the previous broader context.
+
+**Technical Considerations**
+
+- **Efficient Filtering**: Use indexed queries or in-memory filtering to efficiently combine tag and hierarchy filters, especially for large task sets.
+- **Feedback and UI**: Always display the current scope context (e.g., "Viewing tasks tagged 'urgent' under 'Feature X'") so users understand what they're seeing.
+- **Extensibility**: Design the scope system so new types of scopes (e.g., by status, assignee) can be added in the future, not just tags and hierarchy.
+
+**Relevant Precedents**
+
+- Tag-based file systems and management tools often implement "scopes" as dynamic groups defined by tag criteria, allowing users to build up complex views by combining tags and other filters[5].
+- Some systems allow scoping into tag management itself, where you can create, edit, or view tags and their associated objects, which could be mirrored in your CLI or UI[4].
+
+**Summary Table**
+
+| Command Example                  | Resulting Scope                                  |
+|----------------------------------|--------------------------------------------------|
+| `scope-down --tag bug`           | All tasks tagged "bug"                           |
+| `scope-down <task-id> --tag api` | Subtasks of `<task-id>` tagged "api"             |
+| `scope-up --tag`                 | Removes tag filter, returns to previous scope    |
+| `scope-down --tag frontend`      | All tasks tagged "frontend"                      |
+
+By integrating tag-based scoping, you make your scope commands more flexible and powerful, supporting both hierarchical and ad-hoc organizational strategies[1][5].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T20:35:03.231Z*

.taskmaster/docs/research/2025-06-14_should-i-be-using-any-specific-libraries-for-this.md

@@ -0,0 +1,158 @@
+---
+title: Research Session
+query: "should i be using any specific libraries for this?"
+date: 6/14/2025
+time: 5:20:00 PM
+timestamp: 2025-06-14T21:20:00.561Z
+exchanges: 2
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** should i be using any specific libraries for this?
+
+**Response:**
+
+HELL YEAH PARTNER
+
+For implementing a GitHub Issue export feature with bidirectional linking in your project, you absolutely should use a dedicated library for interacting with the GitHub API. This will save you a ton of time, reduce boilerplate, and help you avoid common pitfalls with authentication, pagination, and error handling.
+
+## Recommended Library: PyGithub
+
+- **PyGithub** is the most widely used and well-documented Python library for accessing the GitHub REST API v3. It allows you to manage repositories, issues, user profiles, and more, all with a clean, object-oriented interface[1][2][3][5].
+- It supports all the operations you’ll need for your export feature, including creating issues, updating them, and managing references for bidirectional linking.
+
+### Key Features
+
+- **Authentication**: Easily authenticate with a personal access token.
+- **Issue Management**: Create, update, and link issues programmatically.
+- **Repository Access**: Fetch and manipulate repository data.
+- **User/Org Support**: Works for both user and organization repos.
+- **Pagination & Rate Limiting**: Handles these for you.
+
+### Example Usage
+
+```python
+from github import Github, Auth
+
+# Authenticate with a personal access token
+auth = Auth.Token("your_github_token")
+g = Github(auth=auth)
+
+# Get the repo
+repo = g.get_repo("owner/repo_name")
+
+# Create a new issue
+issue = repo.create_issue(
+    title="Exported from Task Master",
+    body="This issue was created by Task Master. [Task ID: 123]"
+)
+
+# Add a comment or update the issue to include a backlink
+issue.create_comment("Linked to Task Master task #123")
+```
+[3][5]
+
+## Why Not Use Raw Requests?
+
+- While you *can* use the `requests` library to call the GitHub API directly[4], PyGithub abstracts away authentication, error handling, and pagination, making your code much cleaner and less error-prone[2][5].
+
+## Integration Tips
+
+- Store your GitHub token securely (e.g., in environment variables).
+- Use PyGithub’s objects to fetch, create, and update issues.
+- For bidirectional linking, store the GitHub issue URL in your task data and the Task Master task ID in the GitHub issue body or as a label/comment.
+- PyGithub is actively maintained and widely used, so you’ll find plenty of support and documentation.
+
+## Installation
+
+```bash
+pip install PyGithub
+```
+[3]
+
+## Summary Table
+
+| Library   | Language | API Coverage | Ease of Use | Maintained | Docs/Support |
+|-----------|----------|--------------|-------------|------------|--------------|
+| PyGithub  | Python   | Full         | High        | Yes        | Excellent    |
+| requests  | Python   | Full (manual)| Medium      | Yes        | Good         |
+
+**Use PyGithub for all GitHub API interactions in your export/import features.** It’s the standard for Python projects and will make your implementation faster, safer, and more maintainable[1][2][3][5].
+
+---
+
+## Follow-up 1
+
+**Question:** we don't want to use py github because we have a node project
+
+**Response:**
+
+HELL YEAH PARTNER
+
+For a Node.js project, you should use a Node-native library to interact with the GitHub API instead of PyGithub, which is Python-only. The industry standard for Node.js is **Octokit**, the official GitHub SDK for JavaScript/TypeScript[1][2].
+
+## Why Use Octokit?
+
+- **Official & Complete**: Octokit is maintained by GitHub and covers all REST and GraphQL API endpoints, including issues, repositories, users, and more[1][2].
+- **Universal**: Works in Node.js, browsers, and Deno environments[2].
+- **Typed & Tested**: Comes with TypeScript declarations and 100% test coverage[2].
+- **Authentication**: Supports personal access tokens, GitHub Apps, OAuth, and more.
+- **Pagination & Error Handling**: Handles pagination and common error scenarios out of the box.
+- **Extendable**: Supports plugins and custom hooks for advanced use cases[2].
+
+## How to Use Octokit for GitHub Issue Export
+
+Install Octokit in your Node.js project:
+
+```bash
+npm install @octokit/rest
+```
+
+Basic usage for creating and linking issues:
+
+```js
+const { Octokit } = require("@octokit/rest");
+
+// Authenticate with a personal access token
+const octokit = new Octokit({ auth: process.env.GITHUB_TOKEN });
+
+// Create a new issue
+const { data: issue } = await octokit.issues.create({
+  owner: "owner",
+  repo: "repo_name",
+  title: "Exported from Task Master",
+  body: "This issue was created by Task Master. [Task ID: 123]"
+});
+
+// Add a comment for bidirectional linking
+await octokit.issues.createComment({
+  owner: "owner",
+  repo: "repo_name",
+  issue_number: issue.number,
+  body: "Linked to Task Master task #123"
+});
+```
+
+## Alternatives
+
+- **node-github**: An older library, less maintained than Octokit, but still functional for basic API access[5].
+- **Raw HTTP Requests**: You can use `node-fetch` or `axios` to call the GitHub API directly, but you’ll need to handle authentication, pagination, and error handling yourself[3]. Octokit abstracts all of this for you.
+
+## Summary Table
+
+| Library         | Language | API Coverage | Maintained | TypeScript | Docs/Support |
+|-----------------|----------|--------------|------------|------------|--------------|
+| Octokit         | Node.js  | Full         | Yes        | Yes        | Excellent    |
+| node-github     | Node.js  | Full         | No         | No         | Limited      |
+| Raw HTTP        | Node.js  | Full (manual)| N/A        | N/A        | N/A          |
+
+**Recommendation:** Use Octokit for all GitHub API interactions in your Node.js project. It’s the official, most robust, and best-supported option for your use case[1][2].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T21:20:00.561Z*

.taskmaster/docs/research/2025-06-14_test-save-functionality.md

@@ -0,0 +1,76 @@
+---
+title: Research Session
+query: "test save functionality"
+date: 6/14/2025
+time: 5:50:23 PM
+timestamp: 2025-06-14T21:50:23.797Z
+exchanges: 1
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** test save functionality
+
+**Response:**
+
+## Testing Save Functionality in a Task Management System
+
+**Core Steps for Testing Save Functionality**
+
+- Create or update a task in the system using the CLI or UI.
+- Trigger the save operation (e.g., by issuing a command or clicking a save button).
+- Verify that the data is correctly written to the persistent storage (e.g., `tasks.json`).
+- Reload or re-query the data to ensure the saved changes persist and are accurately reflected.
+- Validate that all required fields and relationships (such as dependencies and subtasks) are preserved and correctly structured.
+
+**Key Test Scenarios**
+
+- **Basic Save:** Add a new task and confirm it appears in `tasks.json` with all fields populated.
+- **Update Save:** Modify an existing task (e.g., change status, description, or priority) and verify the changes are saved.
+- **Subtask and Dependency Preservation:** Update a parent task and ensure that completed subtasks and dependency links remain intact, especially after using commands like `updateTask`.
+- **Batch Operations:** Perform bulk updates or additions and confirm all affected tasks are saved correctly, with no data loss or corruption.
+- **Validation:** Attempt to save invalid data and ensure the system rejects it or provides meaningful error messages, confirming validation logic is enforced.
+
+**Recommended Practices**
+
+- Use automated tests to simulate save operations for various scenarios, including edge cases (e.g., circular dependencies, missing required fields).
+- After each save, reload the data and compare it to the expected state to ensure integrity.
+- Log all save operations and errors for traceability and debugging.
+- Regularly back up the `tasks.json` file to prevent data loss during testing and development.
+
+**Relevant Features from Industry Standards**
+
+- Task management systems typically provide robust save and update mechanisms, ensuring that all task attributes (including dependencies, subtasks, and comments) are consistently maintained[1][2][5].
+- Validation and error handling are critical to prevent corrupt or incomplete saves, especially when handling complex relationships or batch operations[1][5].
+- User feedback (such as success messages or error alerts) is important for confirming save actions and guiding users in case of issues[1][2].
+
+**Example Test Case**
+
+1. Create a task with subtasks and dependencies.
+2. Mark some subtasks as complete.
+3. Use the `updateTask` command to modify the parent task.
+4. Save and reload the data.
+5. Assert that:
+   - The parent task reflects the updates.
+   - Completed subtasks remain marked as complete.
+   - Dependencies are unchanged and valid.
+
+**Summary Table: Save Functionality Test Aspects**
+
+| Aspect                | What to Test                                      | Expected Outcome                        |
+|-----------------------|---------------------------------------------------|-----------------------------------------|
+| Basic Save            | Add/update task, save, reload                     | Data persists and matches expectations  |
+| Subtask Preservation  | Update parent, check subtask status               | Completed subtasks remain complete      |
+| Dependency Handling   | Save with dependencies, reload                    | Dependencies are intact and valid       |
+| Batch Operations      | Bulk save/update, reload                          | All changes persist, no data loss       |
+| Validation            | Save invalid data                                 | Error is raised, data not corrupted     |
+
+These steps and scenarios ensure that the save functionality is robust, reliable, and meets the requirements of a modern task management system[1][2][5].
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T21:50:23.797Z*

.taskmaster/docs/research/2025-06-14_test-the-fix-for-duplicate-saves-final-test.md

@@ -0,0 +1,81 @@
+---
+title: Research Session
+query: "test the fix for duplicate saves - final test"
+date: 6/14/2025
+time: 6:10:00 PM
+timestamp: 2025-06-14T22:10:00.394Z
+exchanges: 1
+---
+
+# Research Session
+
+## Initial Query
+
+**Question:** test the fix for duplicate saves - final test
+
+**Response:**
+
+## Steps to Test the Fix for Duplicate Saves
+
+**1. Prepare a Clean Test Environment**
+- Ensure the tasks.json file and any related data stores are in a known, clean state with no pre-existing duplicate entries.
+- Back up the current tasks.json in case rollback is needed.
+
+**2. Define Test Scenarios**
+- Attempt to save a new task with unique data.
+- Attempt to save a task with the same ID or unique identifier as an existing task (simulate a duplicate).
+- Attempt to save a task with the same title or content but a different ID (to test if the fix is based on ID or content).
+- Simultaneously trigger multiple save operations (if the system supports concurrency) to test race conditions.
+
+**3. Execute Manual and Automated Tests**
+- Use the application's UI or API to create and save tasks as per the scenarios above.
+- For each save operation, check the tasks.json file or the data store to verify:
+  - No duplicate entries are created.
+  - Existing tasks are not overwritten unless intended (e.g., for updates).
+  - The system returns appropriate error messages or warnings when a duplicate save is attempted.
+
+**4. Validate System Behavior**
+- Confirm that after all test operations, each task in tasks.json is unique according to the defined criteria (ID, title, or other unique fields).
+- If the system is designed to merge duplicates, verify that merging occurs as expected.
+- If the system is designed to reject duplicates, ensure that the rejection is clear and no duplicate is present.
+
+**5. Test Edge Cases**
+- Attempt to save tasks with minor variations (e.g., whitespace differences, case sensitivity) to ensure the duplicate detection logic is robust.
+- Test with large numbers of tasks to ensure performance and correctness at scale.
+
+**6. Review Logs and Error Handling**
+- Check application logs for any errors or warnings related to duplicate saves.
+- Ensure that error handling is user-friendly and provides actionable feedback.
+
+**7. Regression Testing**
+- Run the full suite of task operations (create, update, delete) to ensure the fix for duplicate saves does not introduce new issues elsewhere in the system.
+
+## Additional Best Practices
+
+- Communicate test results with the team to confirm the fix is effective and to prevent future regressions[1][2][5].
+- Consider implementing automated duplicate detection as part of the save operation to prevent future issues[2][3].
+- Document the test cases and results for future reference and audits.
+
+## Example Test Case Table
+
+| Test Scenario                        | Expected Result                | Actual Result | Pass/Fail |
+|--------------------------------------|-------------------------------|---------------|-----------|
+| Save unique task                     | Task saved                    |               |           |
+| Save duplicate task (same ID)        | Duplicate rejected/merged     |               |           |
+| Save duplicate task (same title)     | Duplicate rejected/merged     |               |           |
+| Simultaneous saves (race condition)  | Only one unique task present  |               |           |
+| Save with minor variations           | No false positives/negatives  |               |           |
+
+Fill in the "Actual Result" and "Pass/Fail" columns during testing.
+
+## Action Items
+
+- Complete all test scenarios above.
+- Document any issues found and retest after fixes.
+- Confirm with stakeholders before closing the issue.
+
+
+---
+
+*Generated by Task Master Research Command*  
+*Timestamp: 2025-06-14T22:10:00.394Z*

.taskmaster/docs/task-template-importing-prd.txt

@@ -0,0 +1,471 @@
+# Task Template Importing System - Product Requirements Document
+
+<context>
+# Overview  
+The Task Template Importing system enables seamless integration of external task templates into the Task Master CLI through automatic file discovery. This system allows users to drop task template files into the tasks directory and immediately access them as new tag contexts without manual import commands or configuration. The solution addresses the need for multi-project task management, team collaboration through shared templates, and clean separation between permanent tasks and temporary project contexts.
+
+# Core Features  
+## Silent Task Template Discovery
+- **What it does**: Automatically scans for `tasks_*.json` files in the tasks directory during tag operations
+- **Why it's important**: Eliminates friction in adding new task contexts and enables zero-configuration workflow
+- **How it works**: File pattern matching extracts tag names from filenames and validates against internal tag keys
+
+## External Tag Resolution System
+- **What it does**: Provides fallback mechanism to external files when tags are not found in main tasks.json
+- **Why it's important**: Maintains clean separation between core tasks and project-specific templates
+- **How it works**: Tag resolution logic checks external files as secondary source while preserving main file precedence
+
+## Read-Only External Tag Access
+- **What it does**: Allows viewing and switching to external tags while preventing modifications
+- **Why it's important**: Protects template integrity and prevents accidental changes to shared templates
+- **How it works**: All task modifications route to main tasks.json regardless of current tag context
+
+## Tag Precedence Management
+- **What it does**: Ensures main tasks.json tags override external files with same tag names
+- **Why it's important**: Prevents conflicts and maintains data integrity
+- **How it works**: Priority system where main file tags take precedence over external file tags
+
+# User Experience  
+## User Personas
+- **Solo Developer**: Manages multiple projects with different task contexts
+- **Team Lead**: Shares standardized task templates across team members
+- **Project Manager**: Organizes tasks by project phases or feature branches
+
+## Key User Flows
+### Template Addition Flow
+1. User receives or creates a `tasks_projectname.json` file
+2. User drops file into `.taskmaster/tasks/` directory
+3. Tag becomes immediately available via `task-master use-tag projectname`
+4. User can list, view, and switch to external tag without configuration
+
+### Template Usage Flow
+1. User runs `task-master tags` to see available tags including external ones
+2. External tags display with `(imported)` indicator
+3. User switches to external tag with `task-master use-tag projectname`
+4. User can view tasks but modifications are routed to main tasks.json
+
+## UI/UX Considerations
+- External tags clearly marked with `(imported)` suffix in listings
+- Visual indicators distinguish between main and external tags
+- Error messages guide users when external files are malformed
+- Read-only warnings when attempting to modify external tag contexts
+</context>
+
+<PRD>
+# Technical Architecture  
+## System Components
+1. **External File Discovery Engine**
+   - File pattern scanner for `tasks_*.json` files
+   - Tag name extraction from filenames using regex
+   - Dynamic tag registry combining main and external sources
+   - Error handling for malformed external files
+
+2. **Enhanced Tag Resolution System**
+   - Fallback mechanism to external files when tags not found in main tasks.json
+   - Precedence management ensuring main file tags override external files
+   - Read-only access enforcement for external tags
+   - Tag metadata preservation during discovery operations
+
+3. **Silent Discovery Integration**
+   - Automatic scanning during tag-related operations
+   - Seamless integration with existing tag management functions
+   - Zero-configuration workflow requiring no manual import commands
+   - Dynamic tag availability without restart requirements
+
+## Data Models
+
+### External Task File Structure
+```json
+{
+  "meta": {
+    "projectName": "External Project Name",
+    "version": "1.0.0",
+    "templateSource": "external",
+    "createdAt": "ISO-8601 timestamp"
+  },
+  "tags": {
+    "projectname": {
+      "meta": {
+        "name": "Project Name",
+        "description": "Project description",
+        "createdAt": "ISO-8601 timestamp"
+      },
+      "tasks": [
+        // Array of task objects
+      ]
+    },
+    "master": {
+      // This section is ignored to prevent conflicts
+    }
+  }
+}
+```
+
+### Enhanced Tag Registry Model
+```json
+{
+  "mainTags": [
+    {
+      "name": "master",
+      "source": "main",
+      "taskCount": 150,
+      "isActive": true
+    }
+  ],
+  "externalTags": [
+    {
+      "name": "projectname",
+      "source": "external",
+      "filename": "tasks_projectname.json",
+      "taskCount": 25,
+      "isReadOnly": true
+    }
+  ]
+}
+```
+
+## APIs and Integrations
+1. **File System Discovery API**
+   - Directory scanning with pattern matching
+   - JSON file validation and parsing
+   - Error handling for corrupted or malformed files
+   - File modification time tracking for cache invalidation
+
+2. **Enhanced Tag Management API**
+   - `scanForExternalTaskFiles(projectRoot)` - Discover external template files
+   - `getExternalTagsFromFiles(projectRoot)` - Extract tag names from external files
+   - `readExternalTagData(projectRoot, tagName)` - Read specific external tag data
+   - `getAvailableTags(projectRoot)` - Combined main and external tag listing
+
+3. **Tag Resolution Enhancement**
+   - Modified `readJSON()` with external file fallback
+   - Enhanced `tags()` function with external tag display
+   - Updated `useTag()` function supporting external tag switching
+   - Read-only enforcement for external tag operations
+
+## Infrastructure Requirements
+1. **File System Access**
+   - Read permissions for tasks directory
+   - JSON parsing capabilities
+   - Pattern matching and regex support
+   - Error handling for file system operations
+
+2. **Backward Compatibility**
+   - Existing tag operations continue unchanged
+   - Main tasks.json structure preserved
+   - No breaking changes to current workflows
+   - Graceful degradation when external files unavailable
+
+# Development Roadmap  
+## Phase 1: Core External File Discovery (Foundation)
+1. **External File Scanner Implementation**
+   - Create `scanForExternalTaskFiles()` function in utils.js
+   - Implement file pattern matching for `tasks_*.json` files
+   - Add error handling for file system access issues
+   - Test with various filename patterns and edge cases
+
+2. **Tag Name Extraction System**
+   - Implement `getExternalTagsFromFiles()` function
+   - Create regex pattern for extracting tag names from filenames
+   - Add validation to ensure tag names match internal tag key format
+   - Handle special characters and invalid filename patterns
+
+3. **External Tag Data Reader**
+   - Create `readExternalTagData()` function
+   - Implement JSON parsing with error handling
+   - Add validation for required tag structure
+   - Ignore 'master' key in external files to prevent conflicts
+
+## Phase 2: Tag Resolution Enhancement (Core Integration)
+1. **Enhanced Tag Registry**
+   - Implement `getAvailableTags()` function combining main and external sources
+   - Create tag metadata structure including source information
+   - Add deduplication logic prioritizing main tags over external
+   - Implement caching mechanism for performance optimization
+
+2. **Modified readJSON Function**
+   - Add external file fallback when tag not found in main tasks.json
+   - Maintain precedence rule: main tasks.json overrides external files
+   - Preserve existing error handling and validation patterns
+   - Ensure read-only access for external tags
+
+3. **Tag Listing Enhancement**
+   - Update `tags()` function to display external tags with `(imported)` indicator
+   - Show external tag metadata and task counts
+   - Maintain current tag highlighting and sorting functionality
+   - Add visual distinction between main and external tags
+
+## Phase 3: User Interface Integration (User Experience)
+1. **Tag Switching Enhancement**
+   - Update `useTag()` function to support external tag switching
+   - Add read-only warnings when switching to external tags
+   - Update state.json with external tag context information
+   - Maintain current tag switching behavior for main tags
+
+2. **Error Handling and User Feedback**
+   - Implement comprehensive error messages for malformed external files
+   - Add user guidance for proper external file structure
+   - Create warnings for read-only operations on external tags
+   - Ensure graceful degradation when external files are corrupted
+
+3. **Documentation and Help Integration**
+   - Update command help text to include external tag information
+   - Add examples of external file structure and usage
+   - Create troubleshooting guide for common external file issues
+   - Document file naming conventions and best practices
+
+## Phase 4: Advanced Features and Optimization (Enhancement)
+1. **Performance Optimization**
+   - Implement file modification time caching
+   - Add lazy loading for external tag data
+   - Optimize file scanning for directories with many files
+   - Create efficient tag resolution caching mechanism
+
+2. **Advanced External File Features**
+   - Support for nested external file directories
+   - Batch external file validation and reporting
+   - External file metadata display and management
+   - Integration with version control ignore patterns
+
+3. **Team Collaboration Features**
+   - Shared external file validation
+   - External file conflict detection and resolution
+   - Team template sharing guidelines and documentation
+   - Integration with git workflows for template management
+
+# Logical Dependency Chain
+## Foundation Layer (Must Be Built First)
+1. **External File Scanner** 
+   - Core requirement for all other functionality
+   - Provides the discovery mechanism for external template files
+   - Must handle file system access and pattern matching reliably
+
+2. **Tag Name Extraction**
+   - Depends on file scanner functionality
+   - Required for identifying available external tags
+   - Must validate tag names against internal format requirements
+
+3. **External Tag Data Reader**
+   - Depends on tag name extraction
+   - Provides access to external tag content
+   - Must handle JSON parsing and validation safely
+
+## Integration Layer (Builds on Foundation)
+4. **Enhanced Tag Registry**
+   - Depends on all foundation components
+   - Combines main and external tag sources
+   - Required for unified tag management across the system
+
+5. **Modified readJSON Function**
+   - Depends on enhanced tag registry
+   - Provides fallback mechanism for tag resolution
+   - Critical for maintaining backward compatibility
+
+6. **Tag Listing Enhancement**
+   - Depends on enhanced tag registry
+   - Provides user visibility into external tags
+   - Required for user discovery of available templates
+
+## User Experience Layer (Completes the Feature)
+7. **Tag Switching Enhancement**
+   - Depends on modified readJSON and tag listing
+   - Enables user interaction with external tags
+   - Must enforce read-only access properly
+
+8. **Error Handling and User Feedback**
+   - Can be developed in parallel with other UX components
+   - Enhances reliability and user experience
+   - Should be integrated throughout development process
+
+9. **Documentation and Help Integration**
+   - Should be developed alongside implementation
+   - Required for user adoption and proper usage
+   - Can be completed in parallel with advanced features
+
+## Optimization Layer (Performance and Advanced Features)
+10. **Performance Optimization**
+    - Can be developed after core functionality is stable
+    - Improves user experience with large numbers of external files
+    - Not blocking for initial release
+
+11. **Advanced External File Features**
+    - Can be developed independently after core features
+    - Enhances power user workflows
+    - Optional for initial release
+
+12. **Team Collaboration Features**
+    - Depends on stable core functionality
+    - Enhances team workflows and template sharing
+    - Can be prioritized based on user feedback
+
+# Risks and Mitigations  
+## Technical Challenges
+
+### File System Performance
+**Risk**: Scanning for external files on every tag operation could impact performance with large directories.
+**Mitigation**: 
+- Implement file modification time caching to avoid unnecessary rescans
+- Use lazy loading for external tag data - only read when accessed
+- Add configurable limits on number of external files to scan
+- Optimize file pattern matching with efficient regex patterns
+
+### External File Corruption
+**Risk**: Malformed or corrupted external JSON files could break tag operations.
+**Mitigation**:
+- Implement robust JSON parsing with comprehensive error handling
+- Add file validation before attempting to parse external files
+- Gracefully skip corrupted files and continue with valid ones
+- Provide clear error messages guiding users to fix malformed files
+
+### Tag Name Conflicts
+**Risk**: External files might contain tag names that conflict with main tasks.json tags.
+**Mitigation**:
+- Implement strict precedence rule: main tasks.json always overrides external files
+- Add warnings when external tags are ignored due to conflicts
+- Document naming conventions to avoid common conflicts
+- Provide validation tools to check for potential conflicts
+
+## MVP Definition
+
+### Core Feature Scope
+**Risk**: Including too many advanced features could delay the core functionality.
+**Mitigation**:
+- Define MVP as basic external file discovery + tag switching
+- Focus on the silent discovery mechanism as the primary value proposition
+- Defer advanced features like nested directories and batch operations
+- Ensure each phase delivers complete, usable functionality
+
+### User Experience Complexity
+**Risk**: The read-only nature of external tags might confuse users.
+**Mitigation**:
+- Provide clear visual indicators for external tags in all interfaces
+- Add explicit warnings when users attempt to modify external tag contexts
+- Document the read-only behavior and its rationale clearly
+- Consider future enhancement for external tag modification workflows
+
+### Backward Compatibility
+**Risk**: Changes to tag resolution logic might break existing workflows.
+**Mitigation**:
+- Maintain existing tag operations unchanged for main tasks.json
+- Add external file support as enhancement, not replacement
+- Test thoroughly with existing task structures and workflows
+- Provide migration path if any breaking changes are necessary
+
+## Resource Constraints
+
+### Development Complexity
+**Risk**: Integration with existing tag management system could be complex.
+**Mitigation**:
+- Phase implementation to minimize risk of breaking existing functionality
+- Create comprehensive test suite covering both main and external tag scenarios
+- Use feature flags to enable/disable external file support during development
+- Implement thorough error handling to prevent system failures
+
+### File System Dependencies
+**Risk**: Different operating systems might handle file operations differently.
+**Mitigation**:
+- Use Node.js built-in file system APIs for cross-platform compatibility
+- Test on multiple operating systems (Windows, macOS, Linux)
+- Handle file path separators and naming conventions properly
+- Add fallback mechanisms for file system access issues
+
+### User Adoption
+**Risk**: Users might not understand or adopt the external file template system.
+**Mitigation**:
+- Create clear documentation with practical examples
+- Provide sample external template files for common use cases
+- Integrate help and guidance directly into the CLI interface
+- Gather user feedback early and iterate on the user experience
+
+# Appendix  
+## External File Naming Convention
+
+### Filename Pattern
+- **Format**: `tasks_[tagname].json`
+- **Examples**: `tasks_feature-auth.json`, `tasks_v2-migration.json`, `tasks_project-alpha.json`
+- **Validation**: Tag name must match internal tag key format (alphanumeric, hyphens, underscores)
+
+### File Structure Requirements
+```json
+{
+  "meta": {
+    "projectName": "Required: Human-readable project name",
+    "version": "Optional: Template version",
+    "templateSource": "Optional: Source identifier",
+    "createdAt": "Optional: ISO-8601 timestamp"
+  },
+  "tags": {
+    "[tagname]": {
+      "meta": {
+        "name": "Required: Tag display name",
+        "description": "Optional: Tag description",
+        "createdAt": "Optional: ISO-8601 timestamp"
+      },
+      "tasks": [
+        // Required: Array of task objects following standard task structure
+      ]
+    }
+  }
+}
+```
+
+## Implementation Functions Specification
+
+### Core Discovery Functions
+```javascript
+// Scan tasks directory for external template files
+function scanForExternalTaskFiles(projectRoot) {
+  // Returns: Array of external file paths
+}
+
+// Extract tag names from external filenames
+function getExternalTagsFromFiles(projectRoot) {
+  // Returns: Array of external tag names
+}
+
+// Read specific external tag data
+function readExternalTagData(projectRoot, tagName) {
+  // Returns: Tag data object or null if not found
+}
+
+// Get combined main and external tags
+function getAvailableTags(projectRoot) {
+  // Returns: Combined tag registry with metadata
+}
+```
+
+### Integration Points
+```javascript
+// Enhanced readJSON with external fallback
+function readJSON(projectRoot, tag = null) {
+  // Modified to check external files when tag not found in main
+}
+
+// Enhanced tags listing with external indicators
+function tags(projectRoot, options = {}) {
+  // Modified to display external tags with (imported) suffix
+}
+
+// Enhanced tag switching with external support
+function useTag(projectRoot, tagName) {
+  // Modified to support switching to external tags (read-only)
+}
+```
+
+## Error Handling Specifications
+
+### File System Errors
+- **ENOENT**: External file not found - gracefully skip and continue
+- **EACCES**: Permission denied - warn user and continue with available files
+- **EISDIR**: Directory instead of file - skip and continue scanning
+
+### JSON Parsing Errors
+- **SyntaxError**: Malformed JSON - skip file and log warning with filename
+- **Missing required fields**: Skip file and provide specific error message
+- **Invalid tag structure**: Skip file and guide user to correct format
+
+### Tag Conflict Resolution
+- **Duplicate tag names**: Main tasks.json takes precedence, log warning
+- **Invalid tag names**: Skip external file and provide naming guidance
+- **Master key in external**: Ignore master key, process other tags normally
+</PRD> 

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

@@ -0,0 +1,373 @@
+{
+	"meta": {
+		"generatedAt": "2025-05-27T16:34:53.088Z",
+		"tasksAnalyzed": 1,
+		"totalTasks": 84,
+		"analysisCount": 45,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": true
+	},
+	"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."
+		}
+	]
+}

.taskmaster/reports/task-complexity-report_test-prd-tag.json

@@ -0,0 +1,53 @@
+{
+	"meta": {
+		"generatedAt": "2025-06-13T06:52:00.611Z",
+		"tasksAnalyzed": 5,
+		"totalTasks": 5,
+		"analysisCount": 5,
+		"thresholdScore": 5,
+		"projectName": "Taskmaster",
+		"usedResearch": true
+	},
+	"complexityAnalysis": [
+		{
+			"taskId": 1,
+			"taskTitle": "Setup Project Repository and Node.js Environment",
+			"complexityScore": 4,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Break down the setup process into subtasks such as initializing npm, creating directory structure, installing dependencies, configuring package.json, adding configuration files, and setting up the main entry point.",
+			"reasoning": "This task involves several standard setup steps that are well-defined and sequential, with low algorithmic complexity but moderate procedural detail. Each step is independent and can be assigned as a subtask, making the overall complexity moderate."
+		},
+		{
+			"taskId": 2,
+			"taskTitle": "Implement Core Functionality and CLI Interface",
+			"complexityScore": 7,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "Expand into subtasks for implementing main logic, designing CLI commands, creating the CLI entry point, integrating business logic, adding error handling, formatting output, and ensuring CLI executability.",
+			"reasoning": "This task requires both application logic and user interface (CLI) development, including error handling and integration. The need to coordinate between core logic and CLI, plus ensuring usability, increases complexity and warrants detailed subtasking."
+		},
+		{
+			"taskId": 3,
+			"taskTitle": "Implement Testing Suite and Validation",
+			"complexityScore": 6,
+			"recommendedSubtasks": 6,
+			"expansionPrompt": "Divide into subtasks for configuring Jest, writing unit tests, writing integration tests, testing CLI commands, setting up coverage reporting, and preparing test fixtures/mocks.",
+			"reasoning": "Comprehensive testing involves multiple types of tests and configuration steps. While each is straightforward, the breadth of coverage and need for automation and validation increases the overall complexity."
+		},
+		{
+			"taskId": 4,
+			"taskTitle": "Setup Node.js Project with CLI Interface",
+			"complexityScore": 5,
+			"recommendedSubtasks": 7,
+			"expansionPrompt": "Break down into subtasks for npm initialization, package.json setup, directory structure creation, dependency installation, CLI entry point creation, package.json bin configuration, and CLI executability.",
+			"reasoning": "This task combines project setup with initial CLI implementation. While each step is standard, the integration of CLI elements adds a layer of complexity beyond a basic setup."
+		},
+		{
+			"taskId": 5,
+			"taskTitle": "Implement Core Functionality with Testing",
+			"complexityScore": 8,
+			"recommendedSubtasks": 8,
+			"expansionPrompt": "Expand into subtasks for implementing each feature (A, B, C), setting up the testing framework, writing tests for each feature, integrating CLI with core logic, and adding coverage reporting.",
+			"reasoning": "This task requires simultaneous development of multiple features, integration with CLI, and comprehensive testing. The coordination and depth required for both implementation and validation make it the most complex among the listed tasks."
+		}
+	]
+}

.taskmaster/state.json

@@ -0,0 +1,9 @@
+{
+	"currentTag": "master",
+	"lastSwitched": "2025-06-14T20:37:15.456Z",
+	"branchTagMapping": {
+		"v017-adds": "v017-adds",
+		"next": "next"
+	},
+	"migrationNoticeShown": true
+}

.taskmaster/tasks/task_001_test-tag.txt

@@ -0,0 +1,23 @@
+# Task ID: 1
+# Title: Implement TTS Flag for Taskmaster Commands
+# Status: pending
+# Dependencies: 16 (Not found)
+# Priority: medium
+# Description: Add text-to-speech functionality to taskmaster commands with configurable voice options and audio output settings.
+# Details:
+Implement TTS functionality including:
+- Add --tts flag to all relevant taskmaster commands (list, show, generate, etc.)
+- Integrate with system TTS engines (Windows SAPI, macOS say command, Linux espeak/festival)
+- Create TTS configuration options in the configuration management system
+- Add voice selection options (male/female, different languages if available)
+- Implement audio output settings (volume, speed, pitch)
+- Add TTS-specific error handling for cases where TTS is unavailable
+- Create fallback behavior when TTS fails (silent failure or text output)
+- Support for reading task titles, descriptions, and status updates aloud
+- Add option to read entire task lists or individual task details
+- Implement TTS for command confirmations and error messages
+- Create TTS output formatting to make spoken text more natural (removing markdown, formatting numbers/dates appropriately)
+- Add configuration option to enable/disable TTS globally
+
+# Test Strategy:
+Test TTS functionality across different operating systems (Windows, macOS, Linux). Verify that the --tts flag works with all major commands. Test voice configuration options and ensure audio output settings are properly applied. Test error handling when TTS services are unavailable. Verify that text formatting for speech is natural and understandable. Test with various task content types including special characters, code snippets, and long descriptions. Ensure TTS can be disabled and enabled through configuration.

.vscode/settings.json

@@ -0,0 +1,14 @@
+{
+	"json.schemas": [
+		{
+			"fileMatch": ["src/prompts/*.json"],
+			"url": "./src/prompts/schemas/prompt-template.schema.json"
+		}
+	],
+	"files.associations": {
+		"src/prompts/*.json": "json"
+	},
+
+	"json.format.enable": true,
+	"json.validate.enable": true
+}