chore: apply requested changes

- make supported providers list more dynamic for cli models

.changeset/auto-update-changelog-highlights.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add changelog highlights to auto-update notifications
-
-When the CLI auto-updates to a new version, it now displays a "What's New" section.

.changeset/config.json

@@ -11,6 +11,7 @@
   "access": "public",
   "baseBranch": "main",
   "ignore": [
-    "docs"
+    "docs",
+    "@tm/claude-code-plugin"
   ]
 }

.changeset/dirty-hairs-know.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": patch
+---
+
+Improve auth token refresh flow

.changeset/fix-parent-directory-traversal.md

@@ -0,0 +1,7 @@
+---
+"task-master-ai": patch
+---
+
+Enable Task Master commands to traverse parent directories to find project root from nested paths
+
+Fixes #1301

.changeset/fix-warning-box-alignment.md

@@ -0,0 +1,5 @@
+---
+"@tm/cli": patch
+---
+
+Fix warning message box width to match dashboard box width for consistent UI alignment

.changeset/light-owls-stay.md

@@ -0,0 +1,35 @@
+---
+"task-master-ai": minor
+---
+
+Add configurable MCP tool loading to optimize LLM context usage
+
+You can now control which Task Master MCP tools are loaded by setting the `TASK_MASTER_TOOLS` environment variable in your MCP configuration. This helps reduce context usage for LLMs by only loading the tools you need.
+
+**Configuration Options:**
+
+- `all` (default): Load all 36 tools
+- `core` or `lean`: Load only 7 essential tools for daily development
+  - Includes: `get_tasks`, `next_task`, `get_task`, `set_task_status`, `update_subtask`, `parse_prd`, `expand_task`
+- `standard`: Load 15 commonly used tools (all core tools plus 8 more)
+  - Additional tools: `initialize_project`, `analyze_project_complexity`, `expand_all`, `add_subtask`, `remove_task`, `generate`, `add_task`, `complexity_report`
+- Custom list: Comma-separated tool names (e.g., `get_tasks,next_task,set_task_status`)
+
+**Example .mcp.json configuration:**
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "standard",
+        "ANTHROPIC_API_KEY": "your_key_here"
+      }
+    }
+  }
+}
+```
+
+For complete details on all available tools, configuration examples, and usage guidelines, see the [MCP Tools documentation](https://docs.task-master.dev/capabilities/mcp#configurable-tool-loading).

.changeset/mean-planes-wave.md

@@ -1,47 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add Claude Code plugin with marketplace distribution
-
-This release introduces official Claude Code plugin support, marking the evolution from legacy `.claude` directory copying to a modern plugin-based architecture.
-
-## 🎉 New: Claude Code Plugin
-
-Task Master AI commands and agents are now distributed as a proper Claude Code plugin:
-
-- **49 slash commands** with clean naming (`/task-master-ai:command-name`)
-- **3 specialized AI agents** (task-orchestrator, task-executor, task-checker)
-- **MCP server integration** for deep Claude Code integration
-
-**Installation:**
-
-```bash
-/plugin marketplace add eyaltoledano/claude-task-master
-/plugin install taskmaster@taskmaster
-```
-
-### The `rules add claude` command no longer copies commands and agents to `.claude/commands/` and `.claude/agents/`. Instead, it now
-
-- Shows plugin installation instructions
-- Only manages CLAUDE.md imports for agent instructions
-- Directs users to install the official plugin
-
-**Migration for Existing Users:**
-
-If you previously used `rules add claude`:
-
-1. The old commands in `.claude/commands/` will continue to work but won't receive updates
-2. Install the plugin for the latest features: `/plugin install taskmaster@taskmaster`
-3. remove old `.claude/commands/` and `.claude/agents/` directories
-
-**Why This Change?**
-
-Claude Code plugins provide:
-
-- ✅ Automatic updates when we release new features
-- ✅ Better command organization and naming
-- ✅ Seamless integration with Claude Code
-- ✅ No manual file copying or management
-
-The plugin system is the future of Task Master AI integration with Claude Code!

.changeset/metal-rocks-help.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": minor
+---
+
+Improve next command to work with remote

.changeset/nice-ways-hope.md

@@ -1,17 +0,0 @@
----
-"task-master-ai": minor
----
-
-Add RPG (Repository Planning Graph) method template for structured PRD creation. The new `example_prd_rpg.txt` template teaches AI agents and developers the RPG methodology through embedded instructions, inline good/bad examples, and XML-style tags for structure. This template enables creation of dependency-aware PRDs that automatically generate topologically-ordered task graphs when parsed with Task Master.
-
-Key features:
-- Method-as-template: teaches RPG principles (dual-semantics, explicit dependencies, topological order) while being used
-- Inline instructions at decision points guide AI through each section
-- Good/bad examples for immediate pattern matching
-- Flexible plain-text format with XML-style tags for parseability
-- Critical dependency-graph section ensures correct task ordering
-- Automatic inclusion during `task-master init`
-- Comprehensive documentation at [docs.task-master.dev/capabilities/rpg-method](https://docs.task-master.dev/capabilities/rpg-method)
-- Tool recommendations for code-context-aware PRD creation (Claude Code, Cursor, Gemini CLI, Codex/Grok)
-
-The RPG template complements the existing `example_prd.txt` and provides a more structured approach for complex projects requiring clear module boundaries and dependency chains.

.changeset/open-tips-notice.md

@@ -0,0 +1,5 @@
+---
+"task-master-ai": minor
+---
+
+Add 4.5 haiku and sonnet to supported models for claude-code and anthropic ai providers

.changeset/plain-falcons-serve.md

@@ -1,7 +0,0 @@
----
-"task-master-ai": patch
----
-
-Fix cross-level task dependencies not being saved
-
-Fixes an issue where adding dependencies between subtasks and top-level tasks (e.g., `task-master add-dependency --id=2.2 --depends-on=11`) would report success but fail to persist the changes. Dependencies can now be created in both directions between any task levels.

.changeset/smart-owls-relax.md

@@ -1,16 +0,0 @@
----
-"task-master-ai": minor
----
-
-Enhance `expand_all` to intelligently use complexity analysis recommendations when expanding tasks. 
-
-The expand-all operation now automatically leverages recommendations from `analyze-complexity` to determine optimal subtask counts for each task, resulting in more accurate and context-aware task breakdowns.
-
-Key improvements:
-- Automatic integration with complexity analysis reports
-- Tag-aware complexity report path resolution
-- Intelligent subtask count determination based on task complexity
-- Falls back to defaults when complexity analysis is unavailable
-- Enhanced logging for better visibility into expansion decisions
-
-When you run `task-master expand --all` after `task-master analyze-complexity`, Task Master now uses the recommended subtask counts from the complexity analysis instead of applying uniform defaults, ensuring each task is broken down according to its actual complexity.

CHANGELOG.md

@@ -1,5 +1,175 @@
 # task-master-ai
 
+## 0.29.0
+
+### Minor Changes
+
+- [#1286](https://github.com/eyaltoledano/claude-task-master/pull/1286) [`f12a16d`](https://github.com/eyaltoledano/claude-task-master/commit/f12a16d09649f62148515f11f616157c7d0bd2d5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add changelog highlights to auto-update notifications
+
+  When the CLI auto-updates to a new version, it now displays a "What's New" section.
+
+- [#1293](https://github.com/eyaltoledano/claude-task-master/pull/1293) [`3010b90`](https://github.com/eyaltoledano/claude-task-master/commit/3010b90d98f3a7d8636caa92fc33d6ee69d4bed0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code plugin with marketplace distribution
+
+  This release introduces official Claude Code plugin support, marking the evolution from legacy `.claude` directory copying to a modern plugin-based architecture.
+
+  ## 🎉 New: Claude Code Plugin
+
+  Task Master AI commands and agents are now distributed as a proper Claude Code plugin:
+  - **49 slash commands** with clean naming (`/taskmaster:command-name`)
+  - **3 specialized AI agents** (task-orchestrator, task-executor, task-checker)
+  - **MCP server integration** for deep Claude Code integration
+
+  **Installation:**
+
+  ```bash
+  /plugin marketplace add eyaltoledano/claude-task-master
+  /plugin install taskmaster@taskmaster
+  ```
+
+  ### The `rules add claude` command no longer copies commands and agents to `.claude/commands/` and `.claude/agents/`. Instead, it now
+  - Shows plugin installation instructions
+  - Only manages CLAUDE.md imports for agent instructions
+  - Directs users to install the official plugin
+
+  **Migration for Existing Users:**
+
+  If you previously used `rules add claude`:
+  1. The old commands in `.claude/commands/` will continue to work but won't receive updates
+  2. Install the plugin for the latest features: `/plugin install taskmaster@taskmaster`
+  3. remove old `.claude/commands/` and `.claude/agents/` directories
+
+  **Why This Change?**
+
+  Claude Code plugins provide:
+  - ✅ Automatic updates when we release new features
+  - ✅ Better command organization and naming
+  - ✅ Seamless integration with Claude Code
+  - ✅ No manual file copying or management
+
+  The plugin system is the future of Task Master AI integration with Claude Code!
+
+- [#1285](https://github.com/eyaltoledano/claude-task-master/pull/1285) [`2a910a4`](https://github.com/eyaltoledano/claude-task-master/commit/2a910a40bac375f9f61d797bf55597303d556b48) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add RPG (Repository Planning Graph) method template for structured PRD creation. The new `example_prd_rpg.txt` template teaches AI agents and developers the RPG methodology through embedded instructions, inline good/bad examples, and XML-style tags for structure. This template enables creation of dependency-aware PRDs that automatically generate topologically-ordered task graphs when parsed with Task Master.
+
+  Key features:
+  - Method-as-template: teaches RPG principles (dual-semantics, explicit dependencies, topological order) while being used
+  - Inline instructions at decision points guide AI through each section
+  - Good/bad examples for immediate pattern matching
+  - Flexible plain-text format with XML-style tags for parseability
+  - Critical dependency-graph section ensures correct task ordering
+  - Automatic inclusion during `task-master init`
+  - Comprehensive documentation at [docs.task-master.dev/capabilities/rpg-method](https://docs.task-master.dev/capabilities/rpg-method)
+  - Tool recommendations for code-context-aware PRD creation (Claude Code, Cursor, Gemini CLI, Codex/Grok)
+
+  The RPG template complements the existing `example_prd.txt` and provides a more structured approach for complex projects requiring clear module boundaries and dependency chains.
+
+- [#1287](https://github.com/eyaltoledano/claude-task-master/pull/1287) [`90e6bdc`](https://github.com/eyaltoledano/claude-task-master/commit/90e6bdcf1c59f65ad27fcdfe3b13b9dca7e77654) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhance `expand_all` to intelligently use complexity analysis recommendations when expanding tasks.
+
+  The expand-all operation now automatically leverages recommendations from `analyze-complexity` to determine optimal subtask counts for each task, resulting in more accurate and context-aware task breakdowns.
+
+  Key improvements:
+  - Automatic integration with complexity analysis reports
+  - Tag-aware complexity report path resolution
+  - Intelligent subtask count determination based on task complexity
+  - Falls back to defaults when complexity analysis is unavailable
+  - Enhanced logging for better visibility into expansion decisions
+
+  When you run `task-master expand --all` after `task-master analyze-complexity`, Task Master now uses the recommended subtask counts from the complexity analysis instead of applying uniform defaults, ensuring each task is broken down according to its actual complexity.
+
+### Patch Changes
+
+- [#1191](https://github.com/eyaltoledano/claude-task-master/pull/1191) [`aaf903f`](https://github.com/eyaltoledano/claude-task-master/commit/aaf903ff2f606c779a22e9a4b240ab57b3683815) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix cross-level task dependencies not being saved
+
+  Fixes an issue where adding dependencies between subtasks and top-level tasks (e.g., `task-master add-dependency --id=2.2 --depends-on=11`) would report success but fail to persist the changes. Dependencies can now be created in both directions between any task levels.
+
+- [#1299](https://github.com/eyaltoledano/claude-task-master/pull/1299) [`4c1ef2c`](https://github.com/eyaltoledano/claude-task-master/commit/4c1ef2ca94411c53bcd2a78ec710b06c500236dd) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve refresh token when authenticating
+
+## 0.29.0-rc.1
+
+### Patch Changes
+
+- [#1299](https://github.com/eyaltoledano/claude-task-master/pull/1299) [`a6c5152`](https://github.com/eyaltoledano/claude-task-master/commit/a6c5152f20edd8717cf1aea34e7c178b1261aa99) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Improve refresh token when authenticating
+
+## 0.29.0-rc.0
+
+### Minor Changes
+
+- [#1286](https://github.com/eyaltoledano/claude-task-master/pull/1286) [`f12a16d`](https://github.com/eyaltoledano/claude-task-master/commit/f12a16d09649f62148515f11f616157c7d0bd2d5) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add changelog highlights to auto-update notifications
+
+  When the CLI auto-updates to a new version, it now displays a "What's New" section.
+
+- [#1293](https://github.com/eyaltoledano/claude-task-master/pull/1293) [`3010b90`](https://github.com/eyaltoledano/claude-task-master/commit/3010b90d98f3a7d8636caa92fc33d6ee69d4bed0) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add Claude Code plugin with marketplace distribution
+
+  This release introduces official Claude Code plugin support, marking the evolution from legacy `.claude` directory copying to a modern plugin-based architecture.
+
+  ## 🎉 New: Claude Code Plugin
+
+  Task Master AI commands and agents are now distributed as a proper Claude Code plugin:
+  - **49 slash commands** with clean naming (`/task-master-ai:command-name`)
+  - **3 specialized AI agents** (task-orchestrator, task-executor, task-checker)
+  - **MCP server integration** for deep Claude Code integration
+
+  **Installation:**
+
+  ```bash
+  /plugin marketplace add eyaltoledano/claude-task-master
+  /plugin install taskmaster@taskmaster
+  ```
+
+  ### The `rules add claude` command no longer copies commands and agents to `.claude/commands/` and `.claude/agents/`. Instead, it now
+  - Shows plugin installation instructions
+  - Only manages CLAUDE.md imports for agent instructions
+  - Directs users to install the official plugin
+
+  **Migration for Existing Users:**
+
+  If you previously used `rules add claude`:
+  1. The old commands in `.claude/commands/` will continue to work but won't receive updates
+  2. Install the plugin for the latest features: `/plugin install taskmaster@taskmaster`
+  3. remove old `.claude/commands/` and `.claude/agents/` directories
+
+  **Why This Change?**
+
+  Claude Code plugins provide:
+  - ✅ Automatic updates when we release new features
+  - ✅ Better command organization and naming
+  - ✅ Seamless integration with Claude Code
+  - ✅ No manual file copying or management
+
+  The plugin system is the future of Task Master AI integration with Claude Code!
+
+- [#1285](https://github.com/eyaltoledano/claude-task-master/pull/1285) [`2a910a4`](https://github.com/eyaltoledano/claude-task-master/commit/2a910a40bac375f9f61d797bf55597303d556b48) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Add RPG (Repository Planning Graph) method template for structured PRD creation. The new `example_prd_rpg.txt` template teaches AI agents and developers the RPG methodology through embedded instructions, inline good/bad examples, and XML-style tags for structure. This template enables creation of dependency-aware PRDs that automatically generate topologically-ordered task graphs when parsed with Task Master.
+
+  Key features:
+  - Method-as-template: teaches RPG principles (dual-semantics, explicit dependencies, topological order) while being used
+  - Inline instructions at decision points guide AI through each section
+  - Good/bad examples for immediate pattern matching
+  - Flexible plain-text format with XML-style tags for parseability
+  - Critical dependency-graph section ensures correct task ordering
+  - Automatic inclusion during `task-master init`
+  - Comprehensive documentation at [docs.task-master.dev/capabilities/rpg-method](https://docs.task-master.dev/capabilities/rpg-method)
+  - Tool recommendations for code-context-aware PRD creation (Claude Code, Cursor, Gemini CLI, Codex/Grok)
+
+  The RPG template complements the existing `example_prd.txt` and provides a more structured approach for complex projects requiring clear module boundaries and dependency chains.
+
+- [#1287](https://github.com/eyaltoledano/claude-task-master/pull/1287) [`90e6bdc`](https://github.com/eyaltoledano/claude-task-master/commit/90e6bdcf1c59f65ad27fcdfe3b13b9dca7e77654) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Enhance `expand_all` to intelligently use complexity analysis recommendations when expanding tasks.
+
+  The expand-all operation now automatically leverages recommendations from `analyze-complexity` to determine optimal subtask counts for each task, resulting in more accurate and context-aware task breakdowns.
+
+  Key improvements:
+  - Automatic integration with complexity analysis reports
+  - Tag-aware complexity report path resolution
+  - Intelligent subtask count determination based on task complexity
+  - Falls back to defaults when complexity analysis is unavailable
+  - Enhanced logging for better visibility into expansion decisions
+
+  When you run `task-master expand --all` after `task-master analyze-complexity`, Task Master now uses the recommended subtask counts from the complexity analysis instead of applying uniform defaults, ensuring each task is broken down according to its actual complexity.
+
+### Patch Changes
+
+- [#1191](https://github.com/eyaltoledano/claude-task-master/pull/1191) [`aaf903f`](https://github.com/eyaltoledano/claude-task-master/commit/aaf903ff2f606c779a22e9a4b240ab57b3683815) Thanks [@Crunchyman-ralph](https://github.com/Crunchyman-ralph)! - Fix cross-level task dependencies not being saved
+
+  Fixes an issue where adding dependencies between subtasks and top-level tasks (e.g., `task-master add-dependency --id=2.2 --depends-on=11`) would report success but fail to persist the changes. Dependencies can now be created in both directions between any task levels.
+
 ## 0.28.0
 
 ### Minor Changes

README.md

@@ -119,6 +119,7 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
       "command": "npx",
       "args": ["-y", "task-master-ai"],
       "env": {
+        // "TASK_MASTER_TOOLS": "all", // Options: "all", "standard", "core", or comma-separated list of tools
         "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
         "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
         "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
@@ -148,6 +149,7 @@ MCP (Model Control Protocol) lets you run Task Master directly from your editor.
       "command": "npx",
       "args": ["-y", "task-master-ai"],
       "env": {
+        // "TASK_MASTER_TOOLS": "all", // Options: "all", "standard", "core", or comma-separated list of tools
         "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
         "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
         "OPENAI_API_KEY": "YOUR_OPENAI_KEY_HERE",
@@ -196,7 +198,7 @@ Initialize taskmaster-ai in my project
 
 #### 5. Make sure you have a PRD (Recommended)
 
-For **new projects**: Create your PRD at `.taskmaster/docs/prd.txt`  
+For **new projects**: Create your PRD at `.taskmaster/docs/prd.txt`.
 For **existing projects**: You can use `scripts/prd.txt` or migrate with `task-master migrate`
 
 An example PRD template is available after initialization in `.taskmaster/templates/example_prd.txt`.
@@ -282,6 +284,76 @@ task-master generate
 task-master rules add windsurf,roo,vscode
 ```
 
+## Tool Loading Configuration
+
+### Optimizing MCP Tool Loading
+
+Task Master's MCP server supports selective tool loading to reduce context window usage. By default, all 36 tools are loaded (~21,000 tokens) to maintain backward compatibility with existing installations.
+
+You can optimize performance by configuring the `TASK_MASTER_TOOLS` environment variable:
+
+### Available Modes
+
+| Mode | Tools | Context Usage | Use Case |
+|------|-------|--------------|----------|
+| `all` (default) | 36 | ~21,000 tokens | Complete feature set - all tools available |
+| `standard` | 15 | ~10,000 tokens | Common task management operations |
+| `core` (or `lean`) | 7 | ~5,000 tokens | Essential daily development workflow |
+| `custom` | Variable | Variable | Comma-separated list of specific tools |
+
+### Configuration Methods
+
+#### Method 1: Environment Variable in MCP Configuration
+
+Add `TASK_MASTER_TOOLS` to your MCP configuration file's `env` section:
+
+```jsonc
+{
+  "mcpServers": {  // or "servers" for VS Code
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "--package=task-master-ai", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "standard",  // Options: "all", "standard", "core", "lean", or comma-separated list
+        "ANTHROPIC_API_KEY": "your-key-here",
+        // ... other API keys
+      }
+    }
+  }
+}
+```
+
+#### Method 2: Claude Code CLI (One-Time Setup)
+
+For Claude Code users, you can set the mode during installation:
+
+```bash
+# Core mode example (~70% token reduction)
+claude mcp add task-master-ai --scope user \
+  --env TASK_MASTER_TOOLS="core" \
+  -- npx -y task-master-ai@latest
+
+# Custom tools example
+claude mcp add task-master-ai --scope user \
+  --env TASK_MASTER_TOOLS="get_tasks,next_task,set_task_status" \
+  -- npx -y task-master-ai@latest
+```
+
+### Tool Sets Details
+
+**Core Tools (7):** `get_tasks`, `next_task`, `get_task`, `set_task_status`, `update_subtask`, `parse_prd`, `expand_task`
+
+**Standard Tools (15):** All core tools plus `initialize_project`, `analyze_project_complexity`, `expand_all`, `add_subtask`, `remove_task`, `generate`, `add_task`, `complexity_report`
+
+**All Tools (36):** Complete set including project setup, task management, analysis, dependencies, tags, research, and more
+
+### Recommendations
+
+- **New users**: Start with `"standard"` mode for a good balance
+- **Large projects**: Use `"core"` mode to minimize token usage
+- **Complex workflows**: Use `"all"` mode or custom selection
+- **Backward compatibility**: If not specified, defaults to `"all"` mode
+
 ## Claude Code Support
 
 Task Master now supports Claude models through the Claude Code CLI, which requires no API key:
@@ -310,6 +382,12 @@ cd claude-task-master
 node scripts/init.js
 ```
 
+## Join Our Team
+
+<a href="https://tryhamster.com" target="_blank">
+  <img src="./images/hamster-hiring.png" alt="Join Hamster's founding team" />
+</a>
+
 ## Contributors
 
 <a href="https://github.com/eyaltoledano/claude-task-master/graphs/contributors">

apps/cli/CHANGELOG.md

@@ -11,6 +11,13 @@
 
 ### Patch Changes
 
+- Updated dependencies []:
+  - @tm/core@null
+
+## null
+
+### Patch Changes
+
 - Updated dependencies []:
   - @tm/core@null
 

apps/cli/src/command-registry.ts

@@ -8,6 +8,7 @@ import { Command } from 'commander';
 // Import all commands
 import { ListTasksCommand } from './commands/list.command.js';
 import { ShowCommand } from './commands/show.command.js';
+import { NextCommand } from './commands/next.command.js';
 import { AuthCommand } from './commands/auth.command.js';
 import { ContextCommand } from './commands/context.command.js';
 import { StartCommand } from './commands/start.command.js';
@@ -45,6 +46,12 @@ export class CommandRegistry {
 			commandClass: ShowCommand as any,
 			category: 'task'
 		},
+		{
+			name: 'next',
+			description: 'Find the next available task to work on',
+			commandClass: NextCommand as any,
+			category: 'task'
+		},
 		{
 			name: 'start',
 			description: 'Start working on a task with claude-code',

apps/cli/src/commands/auth.command.ts

@@ -187,19 +187,29 @@ export class AuthCommand extends Command {
 			if (credentials.expiresAt) {
 				const expiresAt = new Date(credentials.expiresAt);
 				const now = new Date();
-				const hoursRemaining = Math.floor(
+				const timeRemaining = expiresAt.getTime() - now.getTime();
-					(expiresAt.getTime() - now.getTime()) / (1000 * 60 * 60)
+				const hoursRemaining = Math.floor(timeRemaining / (1000 * 60 * 60));
-				);
+				const minutesRemaining = Math.floor(timeRemaining / (1000 * 60));
 
-				if (hoursRemaining > 0) {
+				if (timeRemaining > 0) {
-					console.log(
+					// Token is still valid
-						chalk.gray(
+					if (hoursRemaining > 0) {
-							`  Expires: ${expiresAt.toLocaleString()} (${hoursRemaining} hours remaining)`
+						console.log(
-						)
+							chalk.gray(
-					);
+								`  Expires at: ${expiresAt.toLocaleString()} (${hoursRemaining} hours remaining)`
+							)
+						);
+					} else {
+						console.log(
+							chalk.gray(
+								`  Expires at: ${expiresAt.toLocaleString()} (${minutesRemaining} minutes remaining)`
+							)
+						);
+					}
 				} else {
+					// Token has expired
 					console.log(
-						chalk.yellow(`  Token expired at: ${expiresAt.toLocaleString()}`)
+						chalk.yellow(`  Expired at: ${expiresAt.toLocaleString()}`)
 					);
 				}
 			} else {

apps/cli/src/commands/context.command.ts

@@ -250,7 +250,7 @@ export class ContextCommand extends Command {
 			]);
 
 			// Update context
-			await this.authManager.updateContext({
+			this.authManager.updateContext({
 				orgId: selectedOrg.id,
 				orgName: selectedOrg.name,
 				// Clear brief when changing org
@@ -343,7 +343,7 @@ export class ContextCommand extends Command {
 			if (selectedBrief) {
 				// Update context with brief
 				const briefName = `Brief ${selectedBrief.id.slice(0, 8)}`;
-				await this.authManager.updateContext({
+				this.authManager.updateContext({
 					briefId: selectedBrief.id,
 					briefName: briefName
 				});
@@ -358,7 +358,7 @@ export class ContextCommand extends Command {
 				};
 			} else {
 				// Clear brief selection
-				await this.authManager.updateContext({
+				this.authManager.updateContext({
 					briefId: undefined,
 					briefName: undefined
 				});
@@ -491,7 +491,7 @@ export class ContextCommand extends Command {
 
 			// Update context: set org and brief
 			const briefName = `Brief ${brief.id.slice(0, 8)}`;
-			await this.authManager.updateContext({
+			this.authManager.updateContext({
 				orgId: brief.accountId,
 				orgName,
 				briefId: brief.id,
@@ -613,7 +613,7 @@ export class ContextCommand extends Command {
 				};
 			}
 
-			await this.authManager.updateContext(context);
+			this.authManager.updateContext(context);
 			ui.displaySuccess('Context updated');
 
 			// Display what was set

apps/cli/src/commands/export.command.ts

@@ -103,7 +103,7 @@ export class ExportCommand extends Command {
 			await this.initializeServices();
 
 			// Get current context
-			const context = this.authManager.getContext();
+			const context = await this.authManager.getContext();
 
 			// Determine org and brief IDs
 			let orgId = options?.org || context?.orgId;

apps/cli/src/commands/next.command.ts

@@ -0,0 +1,247 @@
+/**
+ * @fileoverview NextCommand using Commander's native class pattern
+ * Extends Commander.Command for better integration with the framework
+ */
+
+import path from 'node:path';
+import { Command } from 'commander';
+import chalk from 'chalk';
+import boxen from 'boxen';
+import { createTaskMasterCore, type Task, type TaskMasterCore } from '@tm/core';
+import type { StorageType } from '@tm/core/types';
+import { displayTaskDetails } from '../ui/components/task-detail.component.js';
+import { displayHeader } from '../ui/index.js';
+
+/**
+ * Options interface for the next command
+ */
+export interface NextCommandOptions {
+	tag?: string;
+	format?: 'text' | 'json';
+	silent?: boolean;
+	project?: string;
+}
+
+/**
+ * Result type from next command
+ */
+export interface NextTaskResult {
+	task: Task | null;
+	found: boolean;
+	tag: string;
+	storageType: Exclude<StorageType, 'auto'>;
+}
+
+/**
+ * NextCommand extending Commander's Command class
+ * This is a thin presentation layer over @tm/core
+ */
+export class NextCommand extends Command {
+	private tmCore?: TaskMasterCore;
+	private lastResult?: NextTaskResult;
+
+	constructor(name?: string) {
+		super(name || 'next');
+
+		// Configure the command
+		this.description('Find the next available task to work on')
+			.option('-t, --tag <tag>', 'Filter by tag')
+			.option('-f, --format <format>', 'Output format (text, json)', 'text')
+			.option('--silent', 'Suppress output (useful for programmatic usage)')
+			.option('-p, --project <path>', 'Project root directory', process.cwd())
+			.action(async (options: NextCommandOptions) => {
+				await this.executeCommand(options);
+			});
+	}
+
+	/**
+	 * Execute the next command
+	 */
+	private async executeCommand(options: NextCommandOptions): Promise<void> {
+		try {
+			// Validate options (throws on invalid options)
+			this.validateOptions(options);
+
+			// Initialize tm-core
+			await this.initializeCore(options.project || process.cwd());
+
+			// Get next task from core
+			const result = await this.getNextTask(options);
+
+			// Store result for programmatic access
+			this.setLastResult(result);
+
+			// Display results
+			if (!options.silent) {
+				this.displayResults(result, options);
+			}
+		} catch (error: any) {
+			const msg = error?.getSanitizedDetails?.() ?? {
+				message: error?.message ?? String(error)
+			};
+
+			// Allow error to propagate for library compatibility
+			throw new Error(msg.message || 'Unexpected error in next command');
+		} finally {
+			// Always clean up resources, even on error
+			await this.cleanup();
+		}
+	}
+
+	/**
+	 * Validate command options
+	 */
+	private validateOptions(options: NextCommandOptions): void {
+		// Validate format
+		if (options.format && !['text', 'json'].includes(options.format)) {
+			throw new Error(
+				`Invalid format: ${options.format}. Valid formats are: text, json`
+			);
+		}
+	}
+
+	/**
+	 * Initialize TaskMasterCore
+	 */
+	private async initializeCore(projectRoot: string): Promise<void> {
+		if (!this.tmCore) {
+			const resolved = path.resolve(projectRoot);
+			this.tmCore = await createTaskMasterCore({ projectPath: resolved });
+		}
+	}
+
+	/**
+	 * Get next task from tm-core
+	 */
+	private async getNextTask(
+		options: NextCommandOptions
+	): Promise<NextTaskResult> {
+		if (!this.tmCore) {
+			throw new Error('TaskMasterCore not initialized');
+		}
+
+		// Call tm-core to get next task
+		const task = await this.tmCore.getNextTask(options.tag);
+
+		// Get storage type and active tag
+		const storageType = this.tmCore.getStorageType();
+		if (storageType === 'auto') {
+			throw new Error('Storage type must be resolved before use');
+		}
+		const activeTag = options.tag || this.tmCore.getActiveTag();
+
+		return {
+			task,
+			found: task !== null,
+			tag: activeTag,
+			storageType
+		};
+	}
+
+	/**
+	 * Display results based on format
+	 */
+	private displayResults(
+		result: NextTaskResult,
+		options: NextCommandOptions
+	): void {
+		const format = options.format || 'text';
+
+		switch (format) {
+			case 'json':
+				this.displayJson(result);
+				break;
+
+			case 'text':
+			default:
+				this.displayText(result);
+				break;
+		}
+	}
+
+	/**
+	 * Display in JSON format
+	 */
+	private displayJson(result: NextTaskResult): void {
+		console.log(JSON.stringify(result, null, 2));
+	}
+
+	/**
+	 * Display in text format
+	 */
+	private displayText(result: NextTaskResult): void {
+		// Display header with tag (no file path for next command)
+		displayHeader({
+			tag: result.tag || 'master'
+		});
+
+		if (!result.found || !result.task) {
+			// No next task available
+			console.log(
+				boxen(
+					chalk.yellow(
+						'No tasks available to work on. All tasks are either completed, blocked by dependencies, or in progress.'
+					),
+					{
+						padding: 1,
+						borderStyle: 'round',
+						borderColor: 'yellow',
+						title: '⚠ NO TASKS AVAILABLE ⚠',
+						titleAlignment: 'center'
+					}
+				)
+			);
+			console.log(`\n${chalk.gray('Storage: ' + result.storageType)}`);
+			console.log(
+				`\n${chalk.dim('Tip: Try')} ${chalk.cyan('task-master list --status pending')} ${chalk.dim('to see all pending tasks')}`
+			);
+			return;
+		}
+
+		const task = result.task;
+
+		// Display the task details using the same component as 'show' command
+		// with a custom header indicating this is the next task
+		const customHeader = `Next Task: #${task.id} - ${task.title}`;
+		displayTaskDetails(task, {
+			customHeader,
+			headerColor: 'green',
+			showSuggestedActions: true
+		});
+
+		console.log(`\n${chalk.gray('Storage: ' + result.storageType)}`);
+	}
+
+	/**
+	 * Set the last result for programmatic access
+	 */
+	private setLastResult(result: NextTaskResult): void {
+		this.lastResult = result;
+	}
+
+	/**
+	 * Get the last result (for programmatic usage)
+	 */
+	getLastResult(): NextTaskResult | undefined {
+		return this.lastResult;
+	}
+
+	/**
+	 * Clean up resources
+	 */
+	async cleanup(): Promise<void> {
+		if (this.tmCore) {
+			await this.tmCore.close();
+			this.tmCore = undefined;
+		}
+	}
+
+	/**
+	 * Register this command on an existing program
+	 */
+	static register(program: Command, name?: string): NextCommand {
+		const nextCommand = new NextCommand(name);
+		program.addCommand(nextCommand);
+		return nextCommand;
+	}
+}

apps/cli/src/index.ts

@@ -6,6 +6,7 @@
 // Commands
 export { ListTasksCommand } from './commands/list.command.js';
 export { ShowCommand } from './commands/show.command.js';
+export { NextCommand } from './commands/next.command.js';
 export { AuthCommand } from './commands/auth.command.js';
 export { ContextCommand } from './commands/context.command.js';
 export { StartCommand } from './commands/start.command.js';

apps/cli/src/ui/components/header.component.ts

@@ -25,9 +25,9 @@ export function displayHeader(options: HeaderOptions = {}): void {
 		let tagInfo = '';
 
 		if (tag && tag !== 'master') {
-			tagInfo = `🏷 tag: ${chalk.cyan(tag)}`;
+			tagInfo = `🏷  tag: ${chalk.cyan(tag)}`;
 		} else {
-			tagInfo = `🏷 tag: ${chalk.cyan('master')}`;
+			tagInfo = `🏷  tag: ${chalk.cyan('master')}`;
 		}
 
 		console.log(tagInfo);
@@ -39,7 +39,5 @@ export function displayHeader(options: HeaderOptions = {}): void {
 				: `${process.cwd()}/${filePath}`;
 			console.log(`Listing tasks from: ${chalk.dim(absolutePath)}`);
 		}
-
-		console.log(); // Empty line for spacing
 	}
 }

apps/cli/src/ui/components/next-task.component.ts

@@ -6,7 +6,7 @@
 import chalk from 'chalk';
 import boxen from 'boxen';
 import type { Task } from '@tm/core/types';
-import { getComplexityWithColor } from '../../utils/ui.js';
+import { getComplexityWithColor, getBoxWidth } from '../../utils/ui.js';
 
 /**
  * Next task display options
@@ -113,7 +113,7 @@ export function displayRecommendedNextTask(
 			borderColor: '#FFA500', // Orange color
 			title: chalk.hex('#FFA500')('⚡ RECOMMENDED NEXT TASK ⚡'),
 			titleAlignment: 'center',
-			width: process.stdout.columns * 0.97,
+			width: getBoxWidth(0.97),
 			fullscreen: false
 		})
 	);

apps/cli/src/ui/components/suggested-steps.component.ts

@@ -5,6 +5,7 @@
 
 import chalk from 'chalk';
 import boxen from 'boxen';
+import { getBoxWidth } from '../../utils/ui.js';
 
 /**
  * Display suggested next steps section
@@ -24,7 +25,7 @@ export function displaySuggestedNextSteps(): void {
 				margin: { top: 0, bottom: 1 },
 				borderStyle: 'round',
 				borderColor: 'gray',
-				width: process.stdout.columns * 0.97
+				width: getBoxWidth(0.97)
 			}
 		)
 	);

apps/cli/src/utils/ui.spec.ts

@@ -0,0 +1,158 @@
+/**
+ * CLI UI utilities tests
+ * Tests for apps/cli/src/utils/ui.ts
+ */
+
+import { describe, it, expect, beforeEach, afterEach, vi } from 'vitest';
+import type { MockInstance } from 'vitest';
+import { getBoxWidth } from './ui.js';
+
+describe('CLI UI Utilities', () => {
+	describe('getBoxWidth', () => {
+		let columnsSpy: MockInstance;
+		let originalDescriptor: PropertyDescriptor | undefined;
+
+		beforeEach(() => {
+			// Store original descriptor if it exists
+			originalDescriptor = Object.getOwnPropertyDescriptor(
+				process.stdout,
+				'columns'
+			);
+
+			// If columns doesn't exist or isn't a getter, define it as one
+			if (!originalDescriptor || !originalDescriptor.get) {
+				const currentValue = process.stdout.columns || 80;
+				Object.defineProperty(process.stdout, 'columns', {
+					get() {
+						return currentValue;
+					},
+					configurable: true
+				});
+			}
+
+			// Now spy on the getter
+			columnsSpy = vi.spyOn(process.stdout, 'columns', 'get');
+		});
+
+		afterEach(() => {
+			// Restore the spy
+			columnsSpy.mockRestore();
+
+			// Restore original descriptor or delete the property
+			if (originalDescriptor) {
+				Object.defineProperty(process.stdout, 'columns', originalDescriptor);
+			} else {
+				delete (process.stdout as any).columns;
+			}
+		});
+
+		it('should calculate width as percentage of terminal width', () => {
+			columnsSpy.mockReturnValue(100);
+			const width = getBoxWidth(0.9, 40);
+			expect(width).toBe(90);
+		});
+
+		it('should use default percentage of 0.9 when not specified', () => {
+			columnsSpy.mockReturnValue(100);
+			const width = getBoxWidth();
+			expect(width).toBe(90);
+		});
+
+		it('should use default minimum width of 40 when not specified', () => {
+			columnsSpy.mockReturnValue(30);
+			const width = getBoxWidth();
+			expect(width).toBe(40); // Should enforce minimum
+		});
+
+		it('should enforce minimum width when terminal is too narrow', () => {
+			columnsSpy.mockReturnValue(50);
+			const width = getBoxWidth(0.9, 60);
+			expect(width).toBe(60); // Should use minWidth instead of 45
+		});
+
+		it('should handle undefined process.stdout.columns', () => {
+			columnsSpy.mockReturnValue(undefined);
+			const width = getBoxWidth(0.9, 40);
+			// Should fall back to 80 columns: Math.floor(80 * 0.9) = 72
+			expect(width).toBe(72);
+		});
+
+		it('should handle custom percentage values', () => {
+			columnsSpy.mockReturnValue(100);
+			expect(getBoxWidth(0.95, 40)).toBe(95);
+			expect(getBoxWidth(0.8, 40)).toBe(80);
+			expect(getBoxWidth(0.5, 40)).toBe(50);
+		});
+
+		it('should handle custom minimum width values', () => {
+			columnsSpy.mockReturnValue(60);
+			expect(getBoxWidth(0.9, 70)).toBe(70); // 60 * 0.9 = 54, but min is 70
+			expect(getBoxWidth(0.9, 50)).toBe(54); // 60 * 0.9 = 54, min is 50
+		});
+
+		it('should floor the calculated width', () => {
+			columnsSpy.mockReturnValue(99);
+			const width = getBoxWidth(0.9, 40);
+			// 99 * 0.9 = 89.1, should floor to 89
+			expect(width).toBe(89);
+		});
+
+		it('should match warning box width calculation', () => {
+			// Test the specific case from displayWarning()
+			columnsSpy.mockReturnValue(80);
+			const width = getBoxWidth(0.9, 40);
+			expect(width).toBe(72);
+		});
+
+		it('should match table width calculation', () => {
+			// Test the specific case from createTaskTable()
+			columnsSpy.mockReturnValue(111);
+			const width = getBoxWidth(0.9, 100);
+			// 111 * 0.9 = 99.9, floor to 99, but max(99, 100) = 100
+			expect(width).toBe(100);
+		});
+
+		it('should match recommended task box width calculation', () => {
+			// Test the specific case from displayRecommendedNextTask()
+			columnsSpy.mockReturnValue(120);
+			const width = getBoxWidth(0.97, 40);
+			// 120 * 0.97 = 116.4, floor to 116
+			expect(width).toBe(116);
+		});
+
+		it('should handle edge case of zero terminal width', () => {
+			columnsSpy.mockReturnValue(0);
+			const width = getBoxWidth(0.9, 40);
+			// When columns is 0, it uses fallback of 80: Math.floor(80 * 0.9) = 72
+			expect(width).toBe(72);
+		});
+
+		it('should handle very large terminal widths', () => {
+			columnsSpy.mockReturnValue(1000);
+			const width = getBoxWidth(0.9, 40);
+			expect(width).toBe(900);
+		});
+
+		it('should handle very small percentages', () => {
+			columnsSpy.mockReturnValue(100);
+			const width = getBoxWidth(0.1, 5);
+			// 100 * 0.1 = 10, which is greater than min 5
+			expect(width).toBe(10);
+		});
+
+		it('should handle percentage of 1.0 (100%)', () => {
+			columnsSpy.mockReturnValue(80);
+			const width = getBoxWidth(1.0, 40);
+			expect(width).toBe(80);
+		});
+
+		it('should consistently return same value for same inputs', () => {
+			columnsSpy.mockReturnValue(100);
+			const width1 = getBoxWidth(0.9, 40);
+			const width2 = getBoxWidth(0.9, 40);
+			const width3 = getBoxWidth(0.9, 40);
+			expect(width1).toBe(width2);
+			expect(width2).toBe(width3);
+		});
+	});
+});

apps/cli/src/utils/ui.ts

@@ -126,6 +126,20 @@ export function getComplexityWithScore(complexity: number | undefined): string {
 	return color(`${complexity}/10 (${label})`);
 }
 
+/**
+ * Calculate box width as percentage of terminal width
+ * @param percentage - Percentage of terminal width to use (default: 0.9)
+ * @param minWidth - Minimum width to enforce (default: 40)
+ * @returns Calculated box width
+ */
+export function getBoxWidth(
+	percentage: number = 0.9,
+	minWidth: number = 40
+): number {
+	const terminalWidth = process.stdout.columns || 80;
+	return Math.max(Math.floor(terminalWidth * percentage), minWidth);
+}
+
 /**
  * Truncate text to specified length
  */
@@ -176,6 +190,8 @@ export function displayBanner(title: string = 'Task Master'): void {
  * Display an error message (matches scripts/modules/ui.js style)
  */
 export function displayError(message: string, details?: string): void {
+	const boxWidth = getBoxWidth();
+
 	console.error(
 		boxen(
 			chalk.red.bold('X Error: ') +
@@ -184,7 +200,8 @@ export function displayError(message: string, details?: string): void {
 			{
 				padding: 1,
 				borderStyle: 'round',
-				borderColor: 'red'
+				borderColor: 'red',
+				width: boxWidth
 			}
 		)
 	);
@@ -194,13 +211,16 @@ export function displayError(message: string, details?: string): void {
  * Display a success message
  */
 export function displaySuccess(message: string): void {
+	const boxWidth = getBoxWidth();
+
 	console.log(
 		boxen(
 			chalk.green.bold(String.fromCharCode(8730) + ' ') + chalk.white(message),
 			{
 				padding: 1,
 				borderStyle: 'round',
-				borderColor: 'green'
+				borderColor: 'green',
+				width: boxWidth
 			}
 		)
 	);
@@ -210,11 +230,14 @@ export function displaySuccess(message: string): void {
  * Display a warning message
  */
 export function displayWarning(message: string): void {
+	const boxWidth = getBoxWidth();
+
 	console.log(
 		boxen(chalk.yellow.bold('⚠ ') + chalk.white(message), {
 			padding: 1,
 			borderStyle: 'round',
-			borderColor: 'yellow'
+			borderColor: 'yellow',
+			width: boxWidth
 		})
 	);
 }
@@ -223,11 +246,14 @@ export function displayWarning(message: string): void {
  * Display info message
  */
 export function displayInfo(message: string): void {
+	const boxWidth = getBoxWidth();
+
 	console.log(
 		boxen(chalk.blue.bold('i ') + chalk.white(message), {
 			padding: 1,
 			borderStyle: 'round',
-			borderColor: 'blue'
+			borderColor: 'blue',
+			width: boxWidth
 		})
 	);
 }
@@ -282,23 +308,23 @@ export function createTaskTable(
 	} = options || {};
 
 	// Calculate dynamic column widths based on terminal width
-	const terminalWidth = process.stdout.columns * 0.9 || 100;
+	const tableWidth = getBoxWidth(0.9, 100);
 	// Adjust column widths to better match the original layout
 	const baseColWidths = showComplexity
 		? [
-				Math.floor(terminalWidth * 0.1),
+				Math.floor(tableWidth * 0.1),
-				Math.floor(terminalWidth * 0.4),
+				Math.floor(tableWidth * 0.4),
-				Math.floor(terminalWidth * 0.15),
+				Math.floor(tableWidth * 0.15),
-				Math.floor(terminalWidth * 0.1),
+				Math.floor(tableWidth * 0.1),
-				Math.floor(terminalWidth * 0.2),
+				Math.floor(tableWidth * 0.2),
-				Math.floor(terminalWidth * 0.1)
+				Math.floor(tableWidth * 0.1)
 			] // ID, Title, Status, Priority, Dependencies, Complexity
 		: [
-				Math.floor(terminalWidth * 0.08),
+				Math.floor(tableWidth * 0.08),
-				Math.floor(terminalWidth * 0.4),
+				Math.floor(tableWidth * 0.4),
-				Math.floor(terminalWidth * 0.18),
+				Math.floor(tableWidth * 0.18),
-				Math.floor(terminalWidth * 0.12),
+				Math.floor(tableWidth * 0.12),
-				Math.floor(terminalWidth * 0.2)
+				Math.floor(tableWidth * 0.2)
 			]; // ID, Title, Status, Priority, Dependencies
 
 	const headers = [

apps/docs/CHANGELOG.md

@@ -1,5 +1,7 @@
 # docs
 
+## 0.0.6
+
 ## 0.0.5
 
 ## 0.0.4

apps/docs/capabilities/mcp.mdx

@@ -13,6 +13,126 @@ The MCP interface is built on top of the `fastmcp` library and registers a set o
 
 Each tool is defined with a name, a description, and a set of parameters that are validated using the `zod` library. The `execute` function of each tool calls the corresponding core logic function from `scripts/modules/task-manager.js`.
 
+## Configurable Tool Loading
+
+To optimize LLM context usage, you can control which Task Master MCP tools are loaded using the `TASK_MASTER_TOOLS` environment variable. This is particularly useful when working with LLMs that have context limits or when you only need a subset of tools.
+
+### Configuration Modes
+
+#### All Tools (Default)
+Loads all 36 available tools. Use when you need full Task Master functionality.
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "all",
+        "ANTHROPIC_API_KEY": "your_key_here"
+      }
+    }
+  }
+}
+```
+
+If `TASK_MASTER_TOOLS` is not set, all tools are loaded by default.
+
+#### Core Tools (Lean Mode)
+Loads only 7 essential tools for daily development. Ideal for minimal context usage.
+
+**Core tools included:**
+- `get_tasks` - List all tasks
+- `next_task` - Find the next task to work on
+- `get_task` - Get detailed task information
+- `set_task_status` - Update task status
+- `update_subtask` - Add implementation notes
+- `parse_prd` - Generate tasks from PRD
+- `expand_task` - Break down tasks into subtasks
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "core",
+        "ANTHROPIC_API_KEY": "your_key_here"
+      }
+    }
+  }
+}
+```
+
+You can also use `"lean"` as an alias for `"core"`.
+
+#### Standard Tools
+Loads 15 commonly used tools. Balances functionality with context efficiency.
+
+**Standard tools include all core tools plus:**
+- `initialize_project` - Set up new projects
+- `analyze_project_complexity` - Analyze task complexity
+- `expand_all` - Expand all eligible tasks
+- `add_subtask` - Add subtasks manually
+- `remove_task` - Remove tasks
+- `generate` - Generate task markdown files
+- `add_task` - Create new tasks
+- `complexity_report` - View complexity analysis
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "standard",
+        "ANTHROPIC_API_KEY": "your_key_here"
+      }
+    }
+  }
+}
+```
+
+#### Custom Tool Selection
+Specify exactly which tools to load using a comma-separated list. Tool names are case-insensitive and support both underscores and hyphens.
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "env": {
+        "TASK_MASTER_TOOLS": "get_tasks,next_task,set_task_status,update_subtask",
+        "ANTHROPIC_API_KEY": "your_key_here"
+      }
+    }
+  }
+}
+```
+
+### Choosing the Right Configuration
+
+- **Use `core`/`lean`**: When working with basic task management workflows or when context limits are strict
+- **Use `standard`**: For most development workflows that include task creation and analysis
+- **Use `all`**: When you need full functionality including tag management, dependencies, and advanced features
+- **Use custom list**: When you have specific tool requirements or want to experiment with minimal sets
+
+### Verification
+
+When the MCP server starts, it logs which tools were loaded:
+
+```
+Task Master MCP Server starting...
+Tool mode configuration: standard
+Loading standard tools
+Registering 15 MCP tools (mode: standard)
+Successfully registered 15/15 tools
+```
+
 ## Tool Categories
 
 The MCP tools can be categorized in the same way as the core functionalities:

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

@@ -37,6 +37,25 @@ For MCP/Cursor usage: Configure keys in the env section of your .cursor/mcp.json
 }
 ```
 
+<Tip>
+**Optimize Context Usage**: You can control which Task Master MCP tools are loaded using the `TASK_MASTER_TOOLS` environment variable. This helps reduce LLM context usage by only loading the tools you need.
+
+Options:
+- `all` (default) - All 36 tools
+- `standard` - 15 commonly used tools
+- `core` or `lean` - 7 essential tools
+
+Example:
+```json
+"env": {
+  "TASK_MASTER_TOOLS": "standard",
+  "ANTHROPIC_API_KEY": "your_key_here"
+}
+```
+
+See the [MCP Tools documentation](/capabilities/mcp#configurable-tool-loading) for details.
+</Tip>
+
 ### CLI Usage: `.env` File
 
 Create a `.env` file in your project root and include the keys for the providers you plan to use:

apps/docs/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "docs",
-	"version": "0.0.5",
+	"version": "0.0.6",
 	"private": true,
 	"description": "Task Master documentation powered by Mintlify",
 	"scripts": {

apps/extension/CHANGELOG.md

@@ -1,5 +1,14 @@
 # Change Log
 
+## 0.25.6
+
+## 0.25.6-rc.0
+
+### Patch Changes
+
+- Updated dependencies [[`f12a16d`](https://github.com/eyaltoledano/claude-task-master/commit/f12a16d09649f62148515f11f616157c7d0bd2d5), [`3010b90`](https://github.com/eyaltoledano/claude-task-master/commit/3010b90d98f3a7d8636caa92fc33d6ee69d4bed0), [`2a910a4`](https://github.com/eyaltoledano/claude-task-master/commit/2a910a40bac375f9f61d797bf55597303d556b48), [`aaf903f`](https://github.com/eyaltoledano/claude-task-master/commit/aaf903ff2f606c779a22e9a4b240ab57b3683815), [`90e6bdc`](https://github.com/eyaltoledano/claude-task-master/commit/90e6bdcf1c59f65ad27fcdfe3b13b9dca7e77654)]:
+  - task-master-ai@0.29.0-rc.0
+
 ## 0.25.5
 
 ### Patch Changes

apps/extension/package.json

@@ -3,7 +3,7 @@
 	"private": true,
 	"displayName": "TaskMaster",
 	"description": "A visual Kanban board interface for TaskMaster projects in VS Code",
-	"version": "0.25.5",
+	"version": "0.25.6",
 	"publisher": "Hamster",
 	"icon": "assets/icon.png",
 	"engines": {
@@ -239,9 +239,6 @@
 		"watch:css": "npx @tailwindcss/cli -i ./src/webview/index.css -o ./dist/index.css --watch",
 		"check-types": "tsc --noEmit"
 	},
-	"dependencies": {
-		"task-master-ai": "*"
-	},
 	"devDependencies": {
 		"@dnd-kit/core": "^6.3.1",
 		"@dnd-kit/modifiers": "^9.0.0",
@@ -277,7 +274,8 @@
 		"tailwind-merge": "^3.3.1",
 		"tailwindcss": "4.1.11",
 		"typescript": "^5.9.2",
-		"@tm/core": "*"
+		"@tm/core": "*",
+		"task-master-ai": "*"
 	},
 	"overrides": {
 		"glob@<8": "^10.4.5",

docs/configuration.md

@@ -59,6 +59,76 @@ Taskmaster uses two primary methods for configuration:
     - **Migration:** Use `task-master migrate` to move this to `.taskmaster/config.json`.
     - **Deprecation:** While still supported, you'll see warnings encouraging migration to the new structure.
 
+## MCP Tool Loading Configuration
+
+### TASK_MASTER_TOOLS Environment Variable
+
+The `TASK_MASTER_TOOLS` environment variable controls which tools are loaded by the Task Master MCP server. This allows you to optimize token usage based on your workflow needs.
+
+> Note
+> Prefer setting `TASK_MASTER_TOOLS` in your MCP client's `env` block (e.g., `.cursor/mcp.json`) or in CI/deployment env. The `.env` file is reserved for API keys/endpoints; avoid persisting non-secret settings there.
+
+#### Configuration Options
+
+- **`all`** (default): Loads all 36 available tools (~21,000 tokens)
+  - Best for: Users who need the complete feature set
+  - Use when: Working with complex projects requiring all Task Master features
+  - Backward compatibility: This is the default to maintain compatibility with existing installations
+
+- **`standard`**: Loads 15 commonly used tools (~10,000 tokens, 50% reduction)
+  - Best for: Regular task management workflows
+  - Tools included: All core tools plus project initialization, complexity analysis, task generation, and more
+  - Use when: You need a balanced set of features with reduced token usage
+
+- **`core`** (or `lean`): Loads 7 essential tools (~5,000 tokens, 70% reduction)
+  - Best for: Daily development with minimal token overhead
+  - Tools included: `get_tasks`, `next_task`, `get_task`, `set_task_status`, `update_subtask`, `parse_prd`, `expand_task`
+  - Use when: Working in large contexts where token usage is critical
+  - Note: "lean" is an alias for "core" (same tools, token estimate and recommended use). You can refer to it as either "core" or "lean" when configuring.
+
+- **Custom list**: Comma-separated list of specific tool names
+  - Best for: Specialized workflows requiring specific tools
+  - Example: `"get_tasks,next_task,set_task_status"`
+  - Use when: You know exactly which tools you need
+
+#### How to Configure
+
+1. **In MCP configuration files** (`.cursor/mcp.json`, `.vscode/mcp.json`, etc.) - **Recommended**:
+
+   ```jsonc
+   {
+     "mcpServers": {
+       "task-master-ai": {
+         "env": {
+           "TASK_MASTER_TOOLS": "standard",  // Set tool loading mode
+           // API keys can still use .env for security
+         }
+       }
+     }
+   }
+   ```
+
+2. **Via Claude Code CLI**:
+
+   ```bash
+   claude mcp add task-master-ai --scope user \
+     --env TASK_MASTER_TOOLS="core" \
+     -- npx -y task-master-ai@latest
+   ```
+
+3. **In CI/deployment environment variables**:
+   ```bash
+   export TASK_MASTER_TOOLS="standard"
+   node mcp-server/server.js
+   ```
+
+#### Tool Loading Behavior
+
+- When `TASK_MASTER_TOOLS` is unset or empty, the system defaults to `"all"`
+- Invalid tool names in a user-specified list are ignored (a warning is emitted for each)
+- If every tool name in a custom list is invalid, the system falls back to `"all"`
+- Tool names are case-insensitive (e.g., `"CORE"`, `"core"`, and `"Core"` are treated identically)
+
 ## Environment Variables (`.env` file or MCP `env` block - For API Keys Only)
 
 - Used **exclusively** for sensitive API keys and specific endpoint URLs.

mcp-server/src/index.js

@@ -4,12 +4,14 @@ import dotenv from 'dotenv';
 import { fileURLToPath } from 'url';
 import fs from 'fs';
 import logger from './logger.js';
-import { registerTaskMasterTools } from './tools/index.js';
+import {
+	registerTaskMasterTools,
+	getToolsConfiguration
+} from './tools/index.js';
 import ProviderRegistry from '../../src/provider-registry/index.js';
 import { MCPProvider } from './providers/mcp-provider.js';
 import packageJson from '../../package.json' with { type: 'json' };
 
-// Load environment variables
 dotenv.config();
 
 // Constants
@@ -29,12 +31,10 @@ class TaskMasterMCPServer {
 		this.server = new FastMCP(this.options);
 		this.initialized = false;
 
-		// Bind methods
 		this.init = this.init.bind(this);
 		this.start = this.start.bind(this);
 		this.stop = this.stop.bind(this);
 
-		// Setup logging
 		this.logger = logger;
 	}
 
@@ -44,8 +44,34 @@ class TaskMasterMCPServer {
 	async init() {
 		if (this.initialized) return;
 
-		// Pass the manager instance to the tool registration function
+		const normalizedToolMode = getToolsConfiguration();
-		registerTaskMasterTools(this.server, this.asyncManager);
+
+		this.logger.info('Task Master MCP Server starting...');
+		this.logger.info(`Tool mode configuration: ${normalizedToolMode}`);
+
+		const registrationResult = registerTaskMasterTools(
+			this.server,
+			normalizedToolMode
+		);
+
+		this.logger.info(
+			`Normalized tool mode: ${registrationResult.normalizedMode}`
+		);
+		this.logger.info(
+			`Registered ${registrationResult.registeredTools.length} tools successfully`
+		);
+
+		if (registrationResult.registeredTools.length > 0) {
+			this.logger.debug(
+				`Registered tools: ${registrationResult.registeredTools.join(', ')}`
+			);
+		}
+
+		if (registrationResult.failedTools.length > 0) {
+			this.logger.warn(
+				`Failed to register ${registrationResult.failedTools.length} tools: ${registrationResult.failedTools.join(', ')}`
+			);
+		}
 
 		this.initialized = true;
 

mcp-server/src/tools/index.js

@@ -3,109 +3,238 @@
  * Export all Task Master CLI tools for MCP server
  */
 
-import { registerListTasksTool } from './get-tasks.js';
 import logger from '../logger.js';
-import { registerSetTaskStatusTool } from './set-task-status.js';
+import {
-import { registerParsePRDTool } from './parse-prd.js';
+	toolRegistry,
-import { registerUpdateTool } from './update.js';
+	coreTools,
-import { registerUpdateTaskTool } from './update-task.js';
+	standardTools,
-import { registerUpdateSubtaskTool } from './update-subtask.js';
+	getAvailableTools,
-import { registerGenerateTool } from './generate.js';
+	getToolRegistration,
-import { registerShowTaskTool } from './get-task.js';
+	isValidTool
-import { registerNextTaskTool } from './next-task.js';
+} from './tool-registry.js';
-import { registerExpandTaskTool } from './expand-task.js';
-import { registerAddTaskTool } from './add-task.js';
-import { registerAddSubtaskTool } from './add-subtask.js';
-import { registerRemoveSubtaskTool } from './remove-subtask.js';
-import { registerAnalyzeProjectComplexityTool } from './analyze.js';
-import { registerClearSubtasksTool } from './clear-subtasks.js';
-import { registerExpandAllTool } from './expand-all.js';
-import { registerRemoveDependencyTool } from './remove-dependency.js';
-import { registerValidateDependenciesTool } from './validate-dependencies.js';
-import { registerFixDependenciesTool } from './fix-dependencies.js';
-import { registerComplexityReportTool } from './complexity-report.js';
-import { registerAddDependencyTool } from './add-dependency.js';
-import { registerRemoveTaskTool } from './remove-task.js';
-import { registerInitializeProjectTool } from './initialize-project.js';
-import { registerModelsTool } from './models.js';
-import { registerMoveTaskTool } from './move-task.js';
-import { registerResponseLanguageTool } from './response-language.js';
-import { registerAddTagTool } from './add-tag.js';
-import { registerDeleteTagTool } from './delete-tag.js';
-import { registerListTagsTool } from './list-tags.js';
-import { registerUseTagTool } from './use-tag.js';
-import { registerRenameTagTool } from './rename-tag.js';
-import { registerCopyTagTool } from './copy-tag.js';
-import { registerResearchTool } from './research.js';
-import { registerRulesTool } from './rules.js';
-import { registerScopeUpTool } from './scope-up.js';
-import { registerScopeDownTool } from './scope-down.js';
 
 /**
- * Register all Task Master tools with the MCP server
+ * Helper function to safely read and normalize the TASK_MASTER_TOOLS environment variable
- * @param {Object} server - FastMCP server instance
+ * @returns {string} The tools configuration string, defaults to 'all'
  */
-export function registerTaskMasterTools(server) {
+export function getToolsConfiguration() {
+	const rawValue = process.env.TASK_MASTER_TOOLS;
+
+	if (!rawValue || rawValue.trim() === '') {
+		logger.debug('No TASK_MASTER_TOOLS env var found, defaulting to "all"');
+		return 'all';
+	}
+
+	const normalizedValue = rawValue.trim();
+	logger.debug(`TASK_MASTER_TOOLS env var: "${normalizedValue}"`);
+	return normalizedValue;
+}
+
+/**
+ * Register Task Master tools with the MCP server
+ * Supports selective tool loading via TASK_MASTER_TOOLS environment variable
+ * @param {Object} server - FastMCP server instance
+ * @param {string} toolMode - The tool mode configuration (defaults to 'all')
+ * @returns {Object} Object containing registered tools, failed tools, and normalized mode
+ */
+export function registerTaskMasterTools(server, toolMode = 'all') {
+	const registeredTools = [];
+	const failedTools = [];
+
 	try {
-		// Register each tool in a logical workflow order
+		const enabledTools = toolMode.trim();
+		let toolsToRegister = [];
 
-		// Group 1: Initialization & Setup
+		const lowerCaseConfig = enabledTools.toLowerCase();
-		registerInitializeProjectTool(server);
-		registerModelsTool(server);
-		registerRulesTool(server);
-		registerParsePRDTool(server);
 
-		// Group 2: Task Analysis & Expansion
+		switch (lowerCaseConfig) {
-		registerAnalyzeProjectComplexityTool(server);
+			case 'all':
-		registerExpandTaskTool(server);
+				toolsToRegister = Object.keys(toolRegistry);
-		registerExpandAllTool(server);
+				logger.info('Loading all available tools');
-		registerScopeUpTool(server);
+				break;
-		registerScopeDownTool(server);
+			case 'core':
+			case 'lean':
+				toolsToRegister = coreTools;
+				logger.info('Loading core tools only');
+				break;
+			case 'standard':
+				toolsToRegister = standardTools;
+				logger.info('Loading standard tools');
+				break;
+			default:
+				const requestedTools = enabledTools
+					.split(',')
+					.map((t) => t.trim())
+					.filter((t) => t.length > 0);
 
-		// Group 3: Task Listing & Viewing
+				const uniqueTools = new Set();
-		registerListTasksTool(server);
+				const unknownTools = [];
-		registerShowTaskTool(server);
-		registerNextTaskTool(server);
-		registerComplexityReportTool(server);
 
-		// Group 4: Task Status & Management
+				const aliasMap = {
-		registerSetTaskStatusTool(server);
+					response_language: 'response-language'
-		registerGenerateTool(server);
+				};
 
-		// Group 5: Task Creation & Modification
+				for (const toolName of requestedTools) {
-		registerAddTaskTool(server);
+					let resolvedName = null;
-		registerAddSubtaskTool(server);
+					const lowerToolName = toolName.toLowerCase();
-		registerUpdateTool(server);
-		registerUpdateTaskTool(server);
-		registerUpdateSubtaskTool(server);
-		registerRemoveTaskTool(server);
-		registerRemoveSubtaskTool(server);
-		registerClearSubtasksTool(server);
-		registerMoveTaskTool(server);
 
-		// Group 6: Dependency Management
+					if (aliasMap[lowerToolName]) {
-		registerAddDependencyTool(server);
+						const aliasTarget = aliasMap[lowerToolName];
-		registerRemoveDependencyTool(server);
+						for (const registryKey of Object.keys(toolRegistry)) {
-		registerValidateDependenciesTool(server);
+							if (registryKey.toLowerCase() === aliasTarget.toLowerCase()) {
-		registerFixDependenciesTool(server);
+								resolvedName = registryKey;
-		registerResponseLanguageTool(server);
+								break;
+							}
+						}
+					}
 
-		// Group 7: Tag Management
+					if (!resolvedName) {
-		registerListTagsTool(server);
+						for (const registryKey of Object.keys(toolRegistry)) {
-		registerAddTagTool(server);
+							if (registryKey.toLowerCase() === lowerToolName) {
-		registerDeleteTagTool(server);
+								resolvedName = registryKey;
-		registerUseTagTool(server);
+								break;
-		registerRenameTagTool(server);
+							}
-		registerCopyTagTool(server);
+						}
+					}
 
-		// Group 8: Research Features
+					if (!resolvedName) {
-		registerResearchTool(server);
+						const withHyphens = lowerToolName.replace(/_/g, '-');
+						for (const registryKey of Object.keys(toolRegistry)) {
+							if (registryKey.toLowerCase() === withHyphens) {
+								resolvedName = registryKey;
+								break;
+							}
+						}
+					}
+
+					if (!resolvedName) {
+						const withUnderscores = lowerToolName.replace(/-/g, '_');
+						for (const registryKey of Object.keys(toolRegistry)) {
+							if (registryKey.toLowerCase() === withUnderscores) {
+								resolvedName = registryKey;
+								break;
+							}
+						}
+					}
+
+					if (resolvedName) {
+						uniqueTools.add(resolvedName);
+						logger.debug(`Resolved tool "${toolName}" to "${resolvedName}"`);
+					} else {
+						unknownTools.push(toolName);
+						logger.warn(`Unknown tool specified: "${toolName}"`);
+					}
+				}
+
+				toolsToRegister = Array.from(uniqueTools);
+
+				if (unknownTools.length > 0) {
+					logger.warn(`Unknown tools: ${unknownTools.join(', ')}`);
+				}
+
+				if (toolsToRegister.length === 0) {
+					logger.warn(
+						`No valid tools found in custom list. Loading all tools as fallback.`
+					);
+					toolsToRegister = Object.keys(toolRegistry);
+				} else {
+					logger.info(
+						`Loading ${toolsToRegister.length} custom tools from list (${uniqueTools.size} unique after normalization)`
+					);
+				}
+				break;
+		}
+
+		logger.info(
+			`Registering ${toolsToRegister.length} MCP tools (mode: ${enabledTools})`
+		);
+
+		toolsToRegister.forEach((toolName) => {
+			try {
+				const registerFunction = getToolRegistration(toolName);
+				if (registerFunction) {
+					registerFunction(server);
+					logger.debug(`Registered tool: ${toolName}`);
+					registeredTools.push(toolName);
+				} else {
+					logger.warn(`Tool ${toolName} not found in registry`);
+					failedTools.push(toolName);
+				}
+			} catch (error) {
+				if (error.message && error.message.includes('already registered')) {
+					logger.debug(`Tool ${toolName} already registered, skipping`);
+					registeredTools.push(toolName);
+				} else {
+					logger.error(`Failed to register tool ${toolName}: ${error.message}`);
+					failedTools.push(toolName);
+				}
+			}
+		});
+
+		logger.info(
+			`Successfully registered ${registeredTools.length}/${toolsToRegister.length} tools`
+		);
+		if (failedTools.length > 0) {
+			logger.warn(`Failed tools: ${failedTools.join(', ')}`);
+		}
+
+		return {
+			registeredTools,
+			failedTools,
+			normalizedMode: lowerCaseConfig
+		};
 	} catch (error) {
-		logger.error(`Error registering Task Master tools: ${error.message}`);
+		logger.error(
-		throw error;
+			`Error parsing TASK_MASTER_TOOLS environment variable: ${error.message}`
+		);
+		logger.info('Falling back to loading all tools');
+
+		const fallbackTools = Object.keys(toolRegistry);
+		for (const toolName of fallbackTools) {
+			const registerFunction = getToolRegistration(toolName);
+			if (registerFunction) {
+				try {
+					registerFunction(server);
+					registeredTools.push(toolName);
+				} catch (err) {
+					if (err.message && err.message.includes('already registered')) {
+						logger.debug(
+							`Fallback tool ${toolName} already registered, skipping`
+						);
+						registeredTools.push(toolName);
+					} else {
+						logger.warn(
+							`Failed to register fallback tool '${toolName}': ${err.message}`
+						);
+						failedTools.push(toolName);
+					}
+				}
+			} else {
+				logger.warn(`Tool '${toolName}' not found in registry`);
+				failedTools.push(toolName);
+			}
+		}
+		logger.info(
+			`Successfully registered ${registeredTools.length} fallback tools`
+		);
+
+		return {
+			registeredTools,
+			failedTools,
+			normalizedMode: 'all'
+		};
 	}
 }
 
+export {
+	toolRegistry,
+	coreTools,
+	standardTools,
+	getAvailableTools,
+	getToolRegistration,
+	isValidTool
+};
+
 export default {
 	registerTaskMasterTools
 };

mcp-server/src/tools/tool-registry.js

@@ -0,0 +1,168 @@
+/**
+ * tool-registry.js
+ * Tool Registry Object Structure - Maps all 36 tool names to registration functions
+ */
+
+import { registerListTasksTool } from './get-tasks.js';
+import { registerSetTaskStatusTool } from './set-task-status.js';
+import { registerParsePRDTool } from './parse-prd.js';
+import { registerUpdateTool } from './update.js';
+import { registerUpdateTaskTool } from './update-task.js';
+import { registerUpdateSubtaskTool } from './update-subtask.js';
+import { registerGenerateTool } from './generate.js';
+import { registerShowTaskTool } from './get-task.js';
+import { registerNextTaskTool } from './next-task.js';
+import { registerExpandTaskTool } from './expand-task.js';
+import { registerAddTaskTool } from './add-task.js';
+import { registerAddSubtaskTool } from './add-subtask.js';
+import { registerRemoveSubtaskTool } from './remove-subtask.js';
+import { registerAnalyzeProjectComplexityTool } from './analyze.js';
+import { registerClearSubtasksTool } from './clear-subtasks.js';
+import { registerExpandAllTool } from './expand-all.js';
+import { registerRemoveDependencyTool } from './remove-dependency.js';
+import { registerValidateDependenciesTool } from './validate-dependencies.js';
+import { registerFixDependenciesTool } from './fix-dependencies.js';
+import { registerComplexityReportTool } from './complexity-report.js';
+import { registerAddDependencyTool } from './add-dependency.js';
+import { registerRemoveTaskTool } from './remove-task.js';
+import { registerInitializeProjectTool } from './initialize-project.js';
+import { registerModelsTool } from './models.js';
+import { registerMoveTaskTool } from './move-task.js';
+import { registerResponseLanguageTool } from './response-language.js';
+import { registerAddTagTool } from './add-tag.js';
+import { registerDeleteTagTool } from './delete-tag.js';
+import { registerListTagsTool } from './list-tags.js';
+import { registerUseTagTool } from './use-tag.js';
+import { registerRenameTagTool } from './rename-tag.js';
+import { registerCopyTagTool } from './copy-tag.js';
+import { registerResearchTool } from './research.js';
+import { registerRulesTool } from './rules.js';
+import { registerScopeUpTool } from './scope-up.js';
+import { registerScopeDownTool } from './scope-down.js';
+
+/**
+ * Comprehensive tool registry mapping all 36 tool names to their registration functions
+ * Used for dynamic tool registration and validation
+ */
+export const toolRegistry = {
+	initialize_project: registerInitializeProjectTool,
+	models: registerModelsTool,
+	rules: registerRulesTool,
+	parse_prd: registerParsePRDTool,
+	'response-language': registerResponseLanguageTool,
+	analyze_project_complexity: registerAnalyzeProjectComplexityTool,
+	expand_task: registerExpandTaskTool,
+	expand_all: registerExpandAllTool,
+	scope_up_task: registerScopeUpTool,
+	scope_down_task: registerScopeDownTool,
+	get_tasks: registerListTasksTool,
+	get_task: registerShowTaskTool,
+	next_task: registerNextTaskTool,
+	complexity_report: registerComplexityReportTool,
+	set_task_status: registerSetTaskStatusTool,
+	generate: registerGenerateTool,
+	add_task: registerAddTaskTool,
+	add_subtask: registerAddSubtaskTool,
+	update: registerUpdateTool,
+	update_task: registerUpdateTaskTool,
+	update_subtask: registerUpdateSubtaskTool,
+	remove_task: registerRemoveTaskTool,
+	remove_subtask: registerRemoveSubtaskTool,
+	clear_subtasks: registerClearSubtasksTool,
+	move_task: registerMoveTaskTool,
+	add_dependency: registerAddDependencyTool,
+	remove_dependency: registerRemoveDependencyTool,
+	validate_dependencies: registerValidateDependenciesTool,
+	fix_dependencies: registerFixDependenciesTool,
+	list_tags: registerListTagsTool,
+	add_tag: registerAddTagTool,
+	delete_tag: registerDeleteTagTool,
+	use_tag: registerUseTagTool,
+	rename_tag: registerRenameTagTool,
+	copy_tag: registerCopyTagTool,
+	research: registerResearchTool
+};
+
+/**
+ * Core tools array containing the 7 essential tools for daily development
+ * These represent the minimal set needed for basic task management operations
+ */
+export const coreTools = [
+	'get_tasks',
+	'next_task',
+	'get_task',
+	'set_task_status',
+	'update_subtask',
+	'parse_prd',
+	'expand_task'
+];
+
+/**
+ * Standard tools array containing the 15 most commonly used tools
+ * Includes all core tools plus frequently used additional tools
+ */
+export const standardTools = [
+	...coreTools,
+	'initialize_project',
+	'analyze_project_complexity',
+	'expand_all',
+	'add_subtask',
+	'remove_task',
+	'generate',
+	'add_task',
+	'complexity_report'
+];
+
+/**
+ * Get all available tool names
+ * @returns {string[]} Array of tool names
+ */
+export function getAvailableTools() {
+	return Object.keys(toolRegistry);
+}
+
+/**
+ * Get tool counts for all categories
+ * @returns {Object} Object with core, standard, and total counts
+ */
+export function getToolCounts() {
+	return {
+		core: coreTools.length,
+		standard: standardTools.length,
+		total: Object.keys(toolRegistry).length
+	};
+}
+
+/**
+ * Get tool arrays organized by category
+ * @returns {Object} Object with arrays for each category
+ */
+export function getToolCategories() {
+	const allTools = Object.keys(toolRegistry);
+	return {
+		core: [...coreTools],
+		standard: [...standardTools],
+		all: [...allTools],
+		extended: allTools.filter((t) => !standardTools.includes(t))
+	};
+}
+
+/**
+ * Get registration function for a specific tool
+ * @param {string} toolName - Name of the tool
+ * @returns {Function|null} Registration function or null if not found
+ */
+export function getToolRegistration(toolName) {
+	return toolRegistry[toolName] || null;
+}
+
+/**
+ * Validate if a tool exists in the registry
+ * @param {string} toolName - Name of the tool
+ * @returns {boolean} True if tool exists
+ */
+export function isValidTool(toolName) {
+	return toolName in toolRegistry;
+}
+
+export default toolRegistry;

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "task-master-ai",
-	"version": "0.28.0",
+	"version": "0.29.0",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "task-master-ai",
-			"version": "0.28.0",
+			"version": "0.29.0",
 			"license": "MIT WITH Commons-Clause",
 			"workspaces": [
 				"apps/*",
@@ -125,16 +125,13 @@
 			}
 		},
 		"apps/docs": {
-			"version": "0.0.5",
+			"version": "0.0.6",
 			"devDependencies": {
 				"mintlify": "^4.2.111"
 			}
 		},
 		"apps/extension": {
-			"version": "0.25.5",
+			"version": "0.25.6",
-			"dependencies": {
-				"task-master-ai": "*"
-			},
 			"devDependencies": {
 				"@dnd-kit/core": "^6.3.1",
 				"@dnd-kit/modifiers": "^9.0.0",
@@ -170,6 +167,7 @@
 				"react-dom": "^19.0.0",
 				"tailwind-merge": "^3.3.1",
 				"tailwindcss": "4.1.11",
+				"task-master-ai": "*",
 				"typescript": "^5.9.2"
 			},
 			"engines": {
@@ -178,6 +176,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/amazon-bedrock": {
 			"version": "2.2.12",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -195,6 +194,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/anthropic": {
 			"version": "1.2.12",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -209,6 +209,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/azure": {
 			"version": "1.3.25",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/openai": "1.3.24",
@@ -224,6 +225,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/google": {
 			"version": "1.2.22",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -238,6 +240,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/google-vertex": {
 			"version": "2.2.27",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/anthropic": "1.2.12",
@@ -255,6 +258,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/groq": {
 			"version": "1.2.9",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -269,6 +273,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/mistral": {
 			"version": "1.2.8",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -283,6 +288,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/openai": {
 			"version": "1.3.24",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -297,6 +303,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/openai-compatible": {
 			"version": "0.2.16",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -311,6 +318,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/perplexity": {
 			"version": "1.1.9",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -325,6 +333,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/provider": {
 			"version": "1.1.3",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"json-schema": "^0.4.0"
@@ -335,6 +344,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/provider-utils": {
 			"version": "2.2.8",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -350,6 +360,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/react": {
 			"version": "1.2.12",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider-utils": "2.2.8",
@@ -372,6 +383,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/ui-utils": {
 			"version": "1.2.11",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -387,6 +399,7 @@
 		},
 		"apps/extension/node_modules/@ai-sdk/xai": {
 			"version": "1.2.18",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/openai-compatible": "0.2.16",
@@ -402,6 +415,7 @@
 		},
 		"apps/extension/node_modules/@openrouter/ai-sdk-provider": {
 			"version": "0.4.6",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.0.9",
@@ -416,6 +430,7 @@
 		},
 		"apps/extension/node_modules/@openrouter/ai-sdk-provider/node_modules/@ai-sdk/provider": {
 			"version": "1.0.9",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"json-schema": "^0.4.0"
@@ -426,6 +441,7 @@
 		},
 		"apps/extension/node_modules/@openrouter/ai-sdk-provider/node_modules/@ai-sdk/provider-utils": {
 			"version": "2.1.10",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.0.9",
@@ -447,6 +463,7 @@
 		},
 		"apps/extension/node_modules/ai": {
 			"version": "4.3.19",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "1.1.3",
@@ -471,6 +488,7 @@
 		},
 		"apps/extension/node_modules/ai-sdk-provider-gemini-cli": {
 			"version": "0.1.3",
+			"dev": true,
 			"license": "MIT",
 			"optional": true,
 			"dependencies": {
@@ -504,6 +522,7 @@
 		},
 		"apps/extension/node_modules/ollama-ai-provider": {
 			"version": "1.2.0",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@ai-sdk/provider": "^1.0.0",
@@ -524,6 +543,7 @@
 		},
 		"apps/extension/node_modules/openai": {
 			"version": "4.104.0",
+			"dev": true,
 			"license": "Apache-2.0",
 			"dependencies": {
 				"@types/node": "^18.11.18",
@@ -552,6 +572,7 @@
 		},
 		"apps/extension/node_modules/openai/node_modules/@types/node": {
 			"version": "18.19.127",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"undici-types": "~5.26.4"
@@ -559,10 +580,12 @@
 		},
 		"apps/extension/node_modules/openai/node_modules/undici-types": {
 			"version": "5.26.5",
+			"dev": true,
 			"license": "MIT"
 		},
 		"apps/extension/node_modules/task-master-ai": {
 			"version": "0.27.1",
+			"dev": true,
 			"license": "MIT WITH Commons-Clause",
 			"workspaces": [
 				"apps/*",
@@ -634,6 +657,7 @@
 		},
 		"apps/extension/node_modules/zod": {
 			"version": "3.25.76",
+			"dev": true,
 			"license": "MIT",
 			"funding": {
 				"url": "https://github.com/sponsors/colinhacks"
@@ -641,6 +665,7 @@
 		},
 		"apps/extension/node_modules/zod-to-json-schema": {
 			"version": "3.24.6",
+			"dev": true,
 			"license": "ISC",
 			"peerDependencies": {
 				"zod": "^3.24.1"
@@ -929,6 +954,7 @@
 		},
 		"node_modules/@anthropic-ai/sdk": {
 			"version": "0.39.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"@types/node": "^18.11.18",
@@ -942,6 +968,7 @@
 		},
 		"node_modules/@anthropic-ai/sdk/node_modules/@types/node": {
 			"version": "18.19.127",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"undici-types": "~5.26.4"
@@ -949,6 +976,7 @@
 		},
 		"node_modules/@anthropic-ai/sdk/node_modules/undici-types": {
 			"version": "5.26.5",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/@ark/schema": {
@@ -8408,6 +8436,7 @@
 		},
 		"node_modules/@types/diff-match-patch": {
 			"version": "1.0.36",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/@types/es-aggregate-error": {
@@ -8578,6 +8607,7 @@
 		},
 		"node_modules/@types/node-fetch": {
 			"version": "2.6.13",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"@types/node": "*",
@@ -9023,6 +9053,7 @@
 		},
 		"node_modules/abort-controller": {
 			"version": "3.0.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"event-target-shim": "^5.0.0"
@@ -9084,6 +9115,7 @@
 		},
 		"node_modules/agentkeepalive": {
 			"version": "4.6.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"humanize-ms": "^1.2.1"
@@ -9666,6 +9698,7 @@
 		},
 		"node_modules/asynckit": {
 			"version": "0.4.0",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/auto-bind": {
@@ -11443,6 +11476,7 @@
 		},
 		"node_modules/combined-stream": {
 			"version": "1.0.8",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"delayed-stream": "~1.0.0"
@@ -12081,6 +12115,7 @@
 		},
 		"node_modules/delayed-stream": {
 			"version": "1.0.0",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=0.4.0"
@@ -12103,6 +12138,7 @@
 		},
 		"node_modules/dequal": {
 			"version": "2.0.3",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=6"
@@ -12222,6 +12258,7 @@
 		},
 		"node_modules/diff-match-patch": {
 			"version": "1.0.5",
+			"dev": true,
 			"license": "Apache-2.0"
 		},
 		"node_modules/diff-sequences": {
@@ -12721,6 +12758,7 @@
 		},
 		"node_modules/es-set-tostringtag": {
 			"version": "2.1.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"es-errors": "^1.3.0",
@@ -13009,6 +13047,7 @@
 		},
 		"node_modules/event-target-shim": {
 			"version": "5.0.1",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=6"
@@ -14047,6 +14086,7 @@
 		},
 		"node_modules/form-data": {
 			"version": "4.0.4",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"asynckit": "^0.4.0",
@@ -14061,6 +14101,7 @@
 		},
 		"node_modules/form-data-encoder": {
 			"version": "1.7.2",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/format": {
@@ -14072,6 +14113,7 @@
 		},
 		"node_modules/formdata-node": {
 			"version": "4.4.1",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"node-domexception": "1.0.0",
@@ -14732,6 +14774,7 @@
 		},
 		"node_modules/has-tostringtag": {
 			"version": "1.0.2",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"has-symbols": "^1.0.3"
@@ -15306,6 +15349,7 @@
 		},
 		"node_modules/humanize-ms": {
 			"version": "1.2.1",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"ms": "^2.0.0"
@@ -18092,6 +18136,7 @@
 		},
 		"node_modules/jsondiffpatch": {
 			"version": "0.6.0",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"@types/diff-match-patch": "^1.0.36",
@@ -20273,6 +20318,7 @@
 		},
 		"node_modules/nanoid": {
 			"version": "3.3.11",
+			"devOptional": true,
 			"funding": [
 				{
 					"type": "github",
@@ -20381,6 +20427,7 @@
 		},
 		"node_modules/node-domexception": {
 			"version": "1.0.0",
+			"dev": true,
 			"funding": [
 				{
 					"type": "github",
@@ -21245,6 +21292,7 @@
 		},
 		"node_modules/partial-json": {
 			"version": "0.1.7",
+			"dev": true,
 			"license": "MIT"
 		},
 		"node_modules/patch-console": {
@@ -22017,6 +22065,7 @@
 		},
 		"node_modules/react": {
 			"version": "19.1.1",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=0.10.0"
@@ -23143,6 +23192,7 @@
 		},
 		"node_modules/secure-json-parse": {
 			"version": "2.7.0",
+			"dev": true,
 			"license": "BSD-3-Clause"
 		},
 		"node_modules/selderee": {
@@ -24190,6 +24240,26 @@
 				"url": "https://github.com/sponsors/sindresorhus"
 			}
 		},
+		"node_modules/strip-literal": {
+			"version": "3.1.0",
+			"resolved": "https://registry.npmjs.org/strip-literal/-/strip-literal-3.1.0.tgz",
+			"integrity": "sha512-8r3mkIM/2+PpjHoOtiAW8Rg3jJLHaV7xPwG+YRGrv6FP0wwk/toTpATxWYOW0BKdWwl82VT2tFYi5DlROa0Mxg==",
+			"dev": true,
+			"license": "MIT",
+			"dependencies": {
+				"js-tokens": "^9.0.1"
+			},
+			"funding": {
+				"url": "https://github.com/sponsors/antfu"
+			}
+		},
+		"node_modules/strip-literal/node_modules/js-tokens": {
+			"version": "9.0.1",
+			"resolved": "https://registry.npmjs.org/js-tokens/-/js-tokens-9.0.1.tgz",
+			"integrity": "sha512-mxa9E9ITFOt0ban3j6L5MpjwegGz6lBQmM1IJkWeBZGcMxto50+eWdjC/52xDbS2vy0k7vIMK0Fe2wfL9OQSpQ==",
+			"dev": true,
+			"license": "MIT"
+		},
 		"node_modules/strnum": {
 			"version": "2.1.1",
 			"funding": [
@@ -24367,6 +24437,7 @@
 		},
 		"node_modules/swr": {
 			"version": "2.3.6",
+			"dev": true,
 			"license": "MIT",
 			"dependencies": {
 				"dequal": "^2.0.3",
@@ -24559,6 +24630,7 @@
 		},
 		"node_modules/throttleit": {
 			"version": "2.1.0",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">=18"
@@ -25661,6 +25733,7 @@
 		},
 		"node_modules/use-sync-external-store": {
 			"version": "1.5.0",
+			"dev": true,
 			"license": "MIT",
 			"peerDependencies": {
 				"react": "^16.8.0 || ^17.0.0 || ^18.0.0 || ^19.0.0"
@@ -26069,6 +26142,7 @@
 		},
 		"node_modules/web-streams-polyfill": {
 			"version": "4.0.0-beta.3",
+			"dev": true,
 			"license": "MIT",
 			"engines": {
 				"node": ">= 14"
@@ -27062,22 +27136,8 @@
 		},
 		"packages/claude-code-plugin": {
 			"name": "@tm/claude-code-plugin",
-			"license": "MIT WITH Commons-Clause",
+			"version": "0.0.2",
-			"devDependencies": {
+			"license": "MIT WITH Commons-Clause"
-				"@types/node": "^20.0.0",
-				"tsx": "^4.20.4",
-				"typescript": "^5.9.2"
-			}
-		},
-		"packages/claude-code-plugin/node_modules/@types/node": {
-			"version": "20.19.20",
-			"resolved": "https://registry.npmjs.org/@types/node/-/node-20.19.20.tgz",
-			"integrity": "sha512-2Q7WS25j4pS1cS8yw3d6buNCVJukOTeQ39bAnwR6sOJbaxvyCGebzTMypDFN82CxBLnl+lSWVdCCWbRY6y9yZQ==",
-			"dev": true,
-			"license": "MIT",
-			"dependencies": {
-				"undici-types": "~6.21.0"
-			}
 		},
 		"packages/tm-core": {
 			"name": "@tm/core",
@@ -27089,6 +27149,7 @@
 			"devDependencies": {
 				"@types/node": "^22.10.5",
 				"@vitest/coverage-v8": "^3.2.4",
+				"strip-literal": "3.1.0",
 				"typescript": "^5.9.2",
 				"vitest": "^3.2.4"
 			}
@@ -27398,6 +27459,8 @@
 		},
 		"packages/tm-core/node_modules/vitest": {
 			"version": "3.2.4",
+			"resolved": "https://registry.npmjs.org/vitest/-/vitest-3.2.4.tgz",
+			"integrity": "sha512-LUCP5ev3GURDysTWiP47wRRUpLKMOfPh+yKTx3kVIEiu5KOMeqzpnYNsKyOoVrULivR8tLcks4+lga33Whn90A==",
 			"dev": true,
 			"license": "MIT",
 			"dependencies": {

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "task-master-ai",
-	"version": "0.28.0",
+	"version": "0.29.0",
 	"description": "A task management system for ambitious AI-driven development that doesn't overwhelm and confuse Cursor.",
 	"main": "index.js",
 	"type": "module",

packages/ai-sdk-provider-grok-cli/CHANGELOG.md

@@ -1,3 +1,5 @@
 # @tm/ai-sdk-provider-grok-cli
 
 ## null
+
+## null

packages/build-config/CHANGELOG.md

@@ -4,4 +4,6 @@
 
 ## null
 
+## null
+
 ## 1.0.1

packages/claude-code-plugin/CHANGELOG.md

@@ -0,0 +1,3 @@
+# @tm/claude-code-plugin
+
+## 0.0.2

packages/claude-code-plugin/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@tm/claude-code-plugin",
-	"version": "0.0.1",
+	"version": "0.0.2",
 	"description": "Task Master AI plugin for Claude Code - AI-powered task management with commands, agents, and MCP integration",
 	"type": "module",
 	"private": true,

packages/tm-core/CHANGELOG.md

@@ -4,6 +4,8 @@
 
 ## null
 
+## null
+
 ## 0.26.1
 
 All notable changes to the @task-master/tm-core package will be documented in this file.

packages/tm-core/package.json

@@ -37,7 +37,8 @@
 		"@types/node": "^22.10.5",
 		"@vitest/coverage-v8": "^3.2.4",
 		"typescript": "^5.9.2",
-		"vitest": "^3.2.4"
+		"vitest": "^3.2.4",
+		"strip-literal": "3.1.0"
 	},
 	"files": ["src", "README.md", "CHANGELOG.md"],
 	"keywords": ["task-management", "typescript", "ai", "prd", "parser"],

packages/tm-core/src/auth/auth-manager.spec.ts

@@ -21,16 +21,21 @@ const CredentialStoreSpy = vi.fn();
 vi.mock('./credential-store.js', () => {
 	return {
 		CredentialStore: class {
+			static getInstance(config?: any) {
+				return new (this as any)(config);
+			}
+			static resetInstance() {
+				// Mock reset instance method
+			}
 			constructor(config: any) {
 				CredentialStoreSpy(config);
-				this.getCredentials = vi.fn(() => null);
 			}
-			getCredentials() {
+			getCredentials(_options?: any) {
 				return null;
 			}
 			saveCredentials() {}
 			clearCredentials() {}
-			hasValidCredentials() {
+			hasCredentials() {
 				return false;
 			}
 		}
@@ -85,7 +90,7 @@ describe('AuthManager Singleton', () => {
 		expect(instance1).toBe(instance2);
 	});
 
-	it('should use config on first call', () => {
+	it('should use config on first call', async () => {
 		const config = {
 			baseUrl: 'https://test.auth.com',
 			configDir: '/test/config',
@@ -101,7 +106,7 @@ describe('AuthManager Singleton', () => {
 
 		// Verify the config is passed to internal components through observable behavior
 		// getCredentials would look in the configured file path
-		const credentials = instance.getCredentials();
+		const credentials = await instance.getCredentials();
 		expect(credentials).toBeNull(); // File doesn't exist, but config was propagated correctly
 	});
 

packages/tm-core/src/auth/auth-manager.ts

@@ -36,7 +36,10 @@ export class AuthManager {
 		this.oauthService = new OAuthService(this.credentialStore, config);
 
 		// Initialize Supabase client with session restoration
-		this.initializeSupabaseSession();
+		// Fire-and-forget with catch handler to prevent unhandled rejections
+		this.initializeSupabaseSession().catch(() => {
+			// Errors are already logged in initializeSupabaseSession
+		});
 	}
 
 	/**
@@ -78,6 +81,8 @@ export class AuthManager {
 
 	/**
 	 * Get stored authentication credentials
+	 * Returns credentials as-is (even if expired). Refresh must be triggered explicitly
+	 * via refreshToken() or will occur automatically when using the Supabase client for API calls.
 	 */
 	getCredentials(): AuthCredentials | null {
 		return this.credentialStore.getCredentials();
@@ -162,10 +167,11 @@ export class AuthManager {
 	}
 
 	/**
-	 * Check if authenticated
+	 * Check if authenticated (credentials exist, regardless of expiration)
+	 * @returns true if credentials are stored, including expired credentials
 	 */
 	isAuthenticated(): boolean {
-		return this.credentialStore.hasValidCredentials();
+		return this.credentialStore.hasCredentials();
 	}
 
 	/**
@@ -179,7 +185,7 @@ export class AuthManager {
 	/**
 	 * Update the user context (org/brief selection)
 	 */
-	async updateContext(context: Partial<UserContext>): Promise<void> {
+	updateContext(context: Partial<UserContext>): void {
 		const credentials = this.getCredentials();
 		if (!credentials) {
 			throw new AuthenticationError('Not authenticated', 'NOT_AUTHENTICATED');
@@ -205,7 +211,7 @@ export class AuthManager {
 	/**
 	 * Clear the user context
 	 */
-	async clearContext(): Promise<void> {
+	clearContext(): void {
 		const credentials = this.getCredentials();
 		if (!credentials) {
 			throw new AuthenticationError('Not authenticated', 'NOT_AUTHENTICATED');

packages/tm-core/src/auth/credential-store.spec.ts

@@ -0,0 +1,308 @@
+/**
+ * @fileoverview Unit tests for CredentialStore token expiration handling
+ */
+
+import { afterEach, beforeEach, describe, expect, it } from 'vitest';
+import fs from 'fs';
+import path from 'path';
+import os from 'os';
+import { CredentialStore } from './credential-store';
+import type { AuthCredentials } from './types';
+
+describe('CredentialStore - Token Expiration', () => {
+	let credentialStore: CredentialStore;
+	let tmpDir: string;
+	let authFile: string;
+
+	beforeEach(() => {
+		// Create temp directory for test credentials
+		tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'tm-cred-test-'));
+		authFile = path.join(tmpDir, 'auth.json');
+
+		// Create instance with test config
+		CredentialStore.resetInstance();
+		credentialStore = CredentialStore.getInstance({
+			configDir: tmpDir,
+			configFile: authFile
+		});
+	});
+
+	afterEach(() => {
+		// Clean up
+		try {
+			if (fs.existsSync(tmpDir)) {
+				fs.rmSync(tmpDir, { recursive: true, force: true });
+			}
+		} catch {
+			// Ignore cleanup errors
+		}
+		CredentialStore.resetInstance();
+	});
+
+	describe('Expiration Detection', () => {
+		it('should return null for expired token', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(), // 1 minute ago
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).toBeNull();
+		});
+
+		it('should return credentials for valid token', () => {
+			const validCredentials: AuthCredentials = {
+				token: 'valid-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 3600000).toISOString(), // 1 hour from now
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(validCredentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).not.toBeNull();
+			expect(retrieved?.token).toBe('valid-token');
+		});
+
+		it('should return expired token when allowExpired is true', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: true });
+
+			expect(retrieved).not.toBeNull();
+			expect(retrieved?.token).toBe('expired-token');
+		});
+
+		it('should return expired token by default (allowExpired defaults to true)', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token-default',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			// Call without options - should default to allowExpired: true
+			const retrieved = credentialStore.getCredentials();
+
+			expect(retrieved).not.toBeNull();
+			expect(retrieved?.token).toBe('expired-token-default');
+		});
+	});
+
+	describe('Clock Skew Tolerance', () => {
+		it('should reject token expiring within 30-second buffer', () => {
+			// Token expires in 15 seconds (within 30-second buffer)
+			const almostExpiredCredentials: AuthCredentials = {
+				token: 'almost-expired-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 15000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(almostExpiredCredentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).toBeNull();
+		});
+
+		it('should accept token expiring outside 30-second buffer', () => {
+			// Token expires in 60 seconds (outside 30-second buffer)
+			const validCredentials: AuthCredentials = {
+				token: 'valid-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(validCredentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).not.toBeNull();
+			expect(retrieved?.token).toBe('valid-token');
+		});
+	});
+
+	describe('Timestamp Format Handling', () => {
+		it('should handle ISO string timestamps', () => {
+			const credentials: AuthCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 3600000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(credentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).not.toBeNull();
+			expect(typeof retrieved?.expiresAt).toBe('number'); // Normalized to number
+		});
+
+		it('should handle numeric timestamps', () => {
+			const credentials: AuthCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: Date.now() + 3600000,
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(credentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).not.toBeNull();
+			expect(typeof retrieved?.expiresAt).toBe('number');
+		});
+
+		it('should return null for invalid timestamp format', () => {
+			// Manually write invalid timestamp to file
+			const invalidCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: 'invalid-date',
+				savedAt: new Date().toISOString()
+			};
+
+			fs.writeFileSync(authFile, JSON.stringify(invalidCredentials), {
+				mode: 0o600
+			});
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).toBeNull();
+		});
+
+		it('should return null for missing expiresAt', () => {
+			const credentialsWithoutExpiry = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				savedAt: new Date().toISOString()
+			};
+
+			fs.writeFileSync(authFile, JSON.stringify(credentialsWithoutExpiry), {
+				mode: 0o600
+			});
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			expect(retrieved).toBeNull();
+		});
+	});
+
+	describe('Storage Persistence', () => {
+		it('should persist expiresAt as ISO string', () => {
+			const expiryTime = Date.now() + 3600000;
+			const credentials: AuthCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: expiryTime,
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(credentials);
+
+			// Read raw file to verify format
+			const fileContent = fs.readFileSync(authFile, 'utf-8');
+			const parsed = JSON.parse(fileContent);
+
+			// Should be stored as ISO string
+			expect(typeof parsed.expiresAt).toBe('string');
+			expect(parsed.expiresAt).toMatch(/^\d{4}-\d{2}-\d{2}T/); // ISO format
+		});
+
+		it('should normalize timestamp on retrieval', () => {
+			const credentials: AuthCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 3600000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(credentials);
+
+			const retrieved = credentialStore.getCredentials({ allowExpired: false });
+
+			// Should be normalized to number for runtime use
+			expect(typeof retrieved?.expiresAt).toBe('number');
+		});
+	});
+
+	describe('hasCredentials', () => {
+		it('should return true for expired credentials', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			expect(credentialStore.hasCredentials()).toBe(true);
+		});
+
+		it('should return true for valid credentials', () => {
+			const validCredentials: AuthCredentials = {
+				token: 'valid-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 3600000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(validCredentials);
+
+			expect(credentialStore.hasCredentials()).toBe(true);
+		});
+
+		it('should return false when no credentials exist', () => {
+			expect(credentialStore.hasCredentials()).toBe(false);
+		});
+	});
+});

packages/tm-core/src/auth/credential-store.test.ts

@@ -197,7 +197,7 @@ describe('CredentialStore', () => {
 				JSON.stringify(mockCredentials)
 			);
 
-			const result = store.getCredentials();
+			const result = store.getCredentials({ allowExpired: false });
 
 			expect(result).toBeNull();
 			expect(mockLogger.warn).toHaveBeenCalledWith(
@@ -226,6 +226,31 @@ describe('CredentialStore', () => {
 			expect(result).not.toBeNull();
 			expect(result?.token).toBe('expired-token');
 		});
+
+		it('should return expired tokens by default (allowExpired defaults to true)', () => {
+			const expiredTimestamp = Date.now() - 3600000; // 1 hour ago
+			const mockCredentials = {
+				token: 'expired-token-default',
+				userId: 'user-expired',
+				expiresAt: expiredTimestamp,
+				tokenType: 'standard',
+				savedAt: new Date().toISOString()
+			};
+
+			vi.mocked(fs.existsSync).mockReturnValue(true);
+			vi.mocked(fs.readFileSync).mockReturnValue(
+				JSON.stringify(mockCredentials)
+			);
+
+			// Call without options - should default to allowExpired: true
+			const result = store.getCredentials();
+
+			expect(result).not.toBeNull();
+			expect(result?.token).toBe('expired-token-default');
+			expect(mockLogger.warn).not.toHaveBeenCalledWith(
+				expect.stringContaining('Authentication token has expired')
+			);
+		});
 	});
 
 	describe('saveCredentials with timestamp normalization', () => {
@@ -451,7 +476,7 @@ describe('CredentialStore', () => {
 		});
 	});
 
-	describe('hasValidCredentials', () => {
+	describe('hasCredentials', () => {
 		it('should return true when valid unexpired credentials exist', () => {
 			const futureDate = new Date(Date.now() + 3600000); // 1 hour from now
 			const credentials = {
@@ -465,10 +490,10 @@ describe('CredentialStore', () => {
 			vi.mocked(fs.existsSync).mockReturnValue(true);
 			vi.mocked(fs.readFileSync).mockReturnValue(JSON.stringify(credentials));
 
-			expect(store.hasValidCredentials()).toBe(true);
+			expect(store.hasCredentials()).toBe(true);
 		});
 
-		it('should return false when credentials are expired', () => {
+		it('should return true when credentials are expired', () => {
 			const pastDate = new Date(Date.now() - 3600000); // 1 hour ago
 			const credentials = {
 				token: 'expired-token',
@@ -481,13 +506,13 @@ describe('CredentialStore', () => {
 			vi.mocked(fs.existsSync).mockReturnValue(true);
 			vi.mocked(fs.readFileSync).mockReturnValue(JSON.stringify(credentials));
 
-			expect(store.hasValidCredentials()).toBe(false);
+			expect(store.hasCredentials()).toBe(true);
 		});
 
 		it('should return false when no credentials exist', () => {
 			vi.mocked(fs.existsSync).mockReturnValue(false);
 
-			expect(store.hasValidCredentials()).toBe(false);
+			expect(store.hasCredentials()).toBe(false);
 		});
 
 		it('should return false when file contains invalid JSON', () => {
@@ -495,7 +520,7 @@ describe('CredentialStore', () => {
 			vi.mocked(fs.readFileSync).mockReturnValue('invalid json {');
 			vi.mocked(fs.renameSync).mockImplementation(() => undefined);
 
-			expect(store.hasValidCredentials()).toBe(false);
+			expect(store.hasCredentials()).toBe(false);
 		});
 
 		it('should return false for credentials without expiry', () => {
@@ -510,7 +535,7 @@ describe('CredentialStore', () => {
 			vi.mocked(fs.readFileSync).mockReturnValue(JSON.stringify(credentials));
 
 			// Credentials without expiry are considered invalid
-			expect(store.hasValidCredentials()).toBe(false);
+			expect(store.hasCredentials()).toBe(false);
 
 			// Should log warning about missing expiration
 			expect(mockLogger.warn).toHaveBeenCalledWith(
@@ -518,14 +543,14 @@ describe('CredentialStore', () => {
 			);
 		});
 
-		it('should use allowExpired=false by default', () => {
+		it('should use allowExpired=true', () => {
 			// Spy on getCredentials to verify it's called with correct params
 			const getCredentialsSpy = vi.spyOn(store, 'getCredentials');
 
 			vi.mocked(fs.existsSync).mockReturnValue(false);
-			store.hasValidCredentials();
+			store.hasCredentials();
 
-			expect(getCredentialsSpy).toHaveBeenCalledWith({ allowExpired: false });
+			expect(getCredentialsSpy).toHaveBeenCalledWith({ allowExpired: true });
 		});
 	});
 

packages/tm-core/src/auth/credential-store.ts

@@ -54,9 +54,12 @@ export class CredentialStore {
 
 	/**
 	 * Get stored authentication credentials
+	 * @param options.allowExpired - Whether to return expired credentials (default: true)
 	 * @returns AuthCredentials with expiresAt as number (milliseconds) for runtime use
 	 */
-	getCredentials(options?: { allowExpired?: boolean }): AuthCredentials | null {
+	getCredentials({
+		allowExpired = true
+	}: { allowExpired?: boolean } = {}): AuthCredentials | null {
 		try {
 			if (!fs.existsSync(this.config.configFile)) {
 				return null;
@@ -90,7 +93,6 @@ export class CredentialStore {
 
 			// Check if the token has expired (with clock skew tolerance)
 			const now = Date.now();
-			const allowExpired = options?.allowExpired ?? false;
 			if (now >= expiresAtMs - this.CLOCK_SKEW_MS && !allowExpired) {
 				this.logger.warn(
 					'Authentication token has expired or is about to expire',
@@ -103,7 +105,7 @@ export class CredentialStore {
 				return null;
 			}
 
-			// Return valid token
+			// Return credentials (even if expired) to enable refresh flows
 			return authData;
 		} catch (error) {
 			this.logger.error(
@@ -199,10 +201,11 @@ export class CredentialStore {
 	}
 
 	/**
-	 * Check if credentials exist and are valid
+	 * Check if credentials exist (regardless of expiration status)
+	 * @returns true if credentials are stored, including expired credentials
 	 */
-	hasValidCredentials(): boolean {
+	hasCredentials(): boolean {
-		const credentials = this.getCredentials({ allowExpired: false });
+		const credentials = this.getCredentials({ allowExpired: true });
 		return credentials !== null;
 	}
 

packages/tm-core/src/auth/oauth-service.ts

@@ -281,15 +281,26 @@ export class OAuthService {
 				// Exchange code for session using PKCE
 				const session = await this.supabaseClient.exchangeCodeForSession(code);
 
+				// Calculate expiration - can be overridden with TM_TOKEN_EXPIRY_MINUTES
+				let expiresAt: string | undefined;
+				const tokenExpiryMinutes = process.env.TM_TOKEN_EXPIRY_MINUTES;
+				if (tokenExpiryMinutes) {
+					const minutes = parseInt(tokenExpiryMinutes);
+					expiresAt = new Date(Date.now() + minutes * 60 * 1000).toISOString();
+					this.logger.warn(`Token expiry overridden to ${minutes} minute(s)`);
+				} else {
+					expiresAt = session.expires_at
+						? new Date(session.expires_at * 1000).toISOString()
+						: undefined;
+				}
+
 				// Save authentication data
 				const authData: AuthCredentials = {
 					token: session.access_token,
 					refreshToken: session.refresh_token,
 					userId: session.user.id,
 					email: session.user.email,
-					expiresAt: session.expires_at
+					expiresAt,
-						? new Date(session.expires_at * 1000).toISOString()
-						: undefined,
 					tokenType: 'standard',
 					savedAt: new Date().toISOString()
 				};
@@ -340,10 +351,18 @@ export class OAuthService {
 				// Get user info from the session
 				const user = await this.supabaseClient.getUser();
 
-				// Calculate expiration time
+				// Calculate expiration time - can be overridden with TM_TOKEN_EXPIRY_MINUTES
-				const expiresAt = expiresIn
+				let expiresAt: string | undefined;
-					? new Date(Date.now() + parseInt(expiresIn) * 1000).toISOString()
+				const tokenExpiryMinutes = process.env.TM_TOKEN_EXPIRY_MINUTES;
-					: undefined;
+				if (tokenExpiryMinutes) {
+					const minutes = parseInt(tokenExpiryMinutes);
+					expiresAt = new Date(Date.now() + minutes * 60 * 1000).toISOString();
+					this.logger.warn(`Token expiry overridden to ${minutes} minute(s)`);
+				} else {
+					expiresAt = expiresIn
+						? new Date(Date.now() + parseInt(expiresIn) * 1000).toISOString()
+						: undefined;
+				}
 
 				// Save authentication data
 				const authData: AuthCredentials = {
@@ -351,7 +370,7 @@ export class OAuthService {
 					refreshToken: refreshToken || undefined,
 					userId: user?.id || 'unknown',
 					email: user?.email,
-					expiresAt: expiresAt,
+					expiresAt,
 					tokenType: 'standard',
 					savedAt: new Date().toISOString()
 				};

packages/tm-core/src/auth/supabase-session-storage.ts

@@ -98,11 +98,11 @@ export class SupabaseSessionStorage implements SupportedStorage {
 		// Only handle Supabase session keys
 		if (key === STORAGE_KEY || key.includes('auth-token')) {
 			try {
+				this.logger.info('Supabase called setItem - storing refreshed session');
+
 				// Parse the session and update our credentials
 				const sessionUpdates = this.parseSessionToCredentials(value);
-				const existingCredentials = this.store.getCredentials({
+				const existingCredentials = this.store.getCredentials();
-					allowExpired: true
-				});
 
 				if (sessionUpdates.token) {
 					const updatedCredentials: AuthCredentials = {
@@ -113,6 +113,9 @@ export class SupabaseSessionStorage implements SupportedStorage {
 					} as AuthCredentials;
 
 					this.store.saveCredentials(updatedCredentials);
+					this.logger.info(
+						'Successfully saved refreshed credentials from Supabase'
+					);
 				}
 			} catch (error) {
 				this.logger.error('Error setting session:', error);

packages/tm-core/src/clients/supabase-client.ts

@@ -17,10 +17,11 @@ export class SupabaseAuthClient {
 	private client: SupabaseJSClient | null = null;
 	private sessionStorage: SupabaseSessionStorage;
 	private logger = getLogger('SupabaseAuthClient');
+	private credentialStore: CredentialStore;
 
 	constructor() {
-		const credentialStore = CredentialStore.getInstance();
+		this.credentialStore = CredentialStore.getInstance();
-		this.sessionStorage = new SupabaseSessionStorage(credentialStore);
+		this.sessionStorage = new SupabaseSessionStorage(this.credentialStore);
 	}
 
 	/**

packages/tm-core/src/repositories/supabase/supabase-task-repository.ts

@@ -47,8 +47,8 @@ export class SupabaseTaskRepository {
 	 * Gets the current brief ID from auth context
 	 * @throws {Error} If no brief is selected
 	 */
-	private getBriefIdOrThrow(): string {
+	private async getBriefIdOrThrow(): Promise<string> {
-		const context = this.authManager.getContext();
+		const context = await this.authManager.getContext();
 		if (!context?.briefId) {
 			throw new Error(
 				'No brief selected. Please select a brief first using: tm context brief'
@@ -61,7 +61,7 @@ export class SupabaseTaskRepository {
 		_projectId?: string,
 		options?: LoadTasksOptions
 	): Promise<Task[]> {
-		const briefId = this.getBriefIdOrThrow();
+		const briefId = await this.getBriefIdOrThrow();
 
 		// Build query with filters
 		let query = this.supabase
@@ -114,7 +114,7 @@ export class SupabaseTaskRepository {
 	}
 
 	async getTask(_projectId: string, taskId: string): Promise<Task | null> {
-		const briefId = this.getBriefIdOrThrow();
+		const briefId = await this.getBriefIdOrThrow();
 
 		const { data, error } = await this.supabase
 			.from('tasks')
@@ -157,7 +157,7 @@ export class SupabaseTaskRepository {
 		taskId: string,
 		updates: Partial<Task>
 	): Promise<Task> {
-		const briefId = this.getBriefIdOrThrow();
+		const briefId = await this.getBriefIdOrThrow();
 
 		// Validate updates using Zod schema
 		try {

packages/tm-core/src/services/export.service.ts

@@ -105,7 +105,7 @@ export class ExportService {
 		}
 
 		// Get current context
-		const context = this.authManager.getContext();
+		const context = await this.authManager.getContext();
 
 		// Determine org and brief IDs
 		let orgId = options.orgId || context?.orgId;
@@ -232,7 +232,7 @@ export class ExportService {
 		hasBrief: boolean;
 		context: UserContext | null;
 	}> {
-		const context = this.authManager.getContext();
+		const context = await this.authManager.getContext();
 
 		return {
 			hasOrg: !!context?.orgId,
@@ -362,7 +362,7 @@ export class ExportService {
 
 		if (useAPIEndpoint) {
 			// Use the new bulk import API endpoint
-			const apiUrl = `${process.env.TM_PUBLIC_BASE_DOMAIN}/ai/api/v1/briefs/${briefId}/tasks/bulk`;
+			const apiUrl = `${process.env.TM_PUBLIC_BASE_DOMAIN}/ai/api/v1/briefs/${briefId}/tasks`;
 
 			// Transform tasks to flat structure for API
 			const flatTasks = this.transformTasksForBulkImport(tasks);
@@ -370,16 +370,16 @@ export class ExportService {
 			// Prepare request body
 			const requestBody = {
 				source: 'task-master-cli',
-				accountId: orgId,
 				options: {
 					dryRun: false,
 					stopOnError: false
 				},
+				accountId: orgId,
 				tasks: flatTasks
 			};
 
 			// Get auth token
-			const credentials = this.authManager.getCredentials();
+			const credentials = await this.authManager.getCredentials();
 			if (!credentials || !credentials.token) {
 				throw new Error('Not authenticated');
 			}

packages/tm-core/src/storage/api-storage.ts

@@ -119,7 +119,7 @@ export class ApiStorage implements IStorage {
 	private async loadTagsIntoCache(): Promise<void> {
 		try {
 			const authManager = AuthManager.getInstance();
-			const context = authManager.getContext();
+			const context = await authManager.getContext();
 
 			// If we have a selected brief, create a virtual "tag" for it
 			if (context?.briefId) {
@@ -152,7 +152,7 @@ export class ApiStorage implements IStorage {
 
 		try {
 			const authManager = AuthManager.getInstance();
-			const context = authManager.getContext();
+			const context = await authManager.getContext();
 
 			// If no brief is selected in context, throw an error
 			if (!context?.briefId) {
@@ -318,7 +318,7 @@ export class ApiStorage implements IStorage {
 
 		try {
 			const authManager = AuthManager.getInstance();
-			const context = authManager.getContext();
+			const context = await authManager.getContext();
 
 			// In our API-based system, we only have one "tag" at a time - the current brief
 			if (context?.briefId) {

packages/tm-core/src/storage/storage-factory.ts

@@ -72,7 +72,7 @@ export class StorageFactory {
 							{ storageType: 'api', missing }
 						);
 					}
-					// Use auth token from AuthManager
+					// Use auth token from AuthManager (synchronous - no auto-refresh here)
 					const credentials = authManager.getCredentials();
 					if (credentials) {
 						// Merge with existing storage config, ensuring required fields

packages/tm-core/tests/auth/auth-refresh.test.ts

@@ -0,0 +1,139 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import fs from 'fs';
+import os from 'os';
+import path from 'path';
+import type { Session } from '@supabase/supabase-js';
+import { AuthManager } from '../../src/auth/auth-manager';
+import { CredentialStore } from '../../src/auth/credential-store';
+import type { AuthCredentials } from '../../src/auth/types';
+
+describe('AuthManager Token Refresh', () => {
+	let authManager: AuthManager;
+	let credentialStore: CredentialStore;
+	let tmpDir: string;
+	let authFile: string;
+
+	beforeEach(() => {
+		// Reset singletons
+		AuthManager.resetInstance();
+		CredentialStore.resetInstance();
+
+		// Create temporary directory for test isolation
+		tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'tm-auth-refresh-'));
+		authFile = path.join(tmpDir, 'auth.json');
+
+		// Initialize AuthManager with test config (this will create CredentialStore internally)
+		authManager = AuthManager.getInstance({
+			configDir: tmpDir,
+			configFile: authFile
+		});
+
+		// Get the CredentialStore instance that AuthManager created
+		credentialStore = CredentialStore.getInstance();
+		credentialStore.clearCredentials();
+	});
+
+	afterEach(() => {
+		// Clean up
+		try {
+			credentialStore.clearCredentials();
+		} catch {
+			// Ignore cleanup errors
+		}
+		AuthManager.resetInstance();
+		CredentialStore.resetInstance();
+		vi.restoreAllMocks();
+
+		// Remove temporary directory
+		if (tmpDir && fs.existsSync(tmpDir)) {
+			fs.rmSync(tmpDir, { recursive: true, force: true });
+		}
+	});
+
+	it('should return expired credentials to enable refresh flows', () => {
+		// Set up expired credentials with refresh token
+		const expiredCredentials: AuthCredentials = {
+			token: 'expired_access_token',
+			refreshToken: 'valid_refresh_token',
+			userId: 'test-user-id',
+			email: 'test@example.com',
+			expiresAt: new Date(Date.now() - 1000).toISOString(), // Expired 1 second ago
+			savedAt: new Date().toISOString()
+		};
+
+		credentialStore.saveCredentials(expiredCredentials);
+
+		// Get credentials should return them even if expired
+		// Refresh will be handled by explicit calls or client operations
+		const credentials = authManager.getCredentials();
+
+		expect(credentials).not.toBeNull();
+		expect(credentials?.token).toBe('expired_access_token');
+		expect(credentials?.refreshToken).toBe('valid_refresh_token');
+	});
+
+	it('should return valid credentials', () => {
+		// Set up valid (non-expired) credentials
+		const validCredentials: AuthCredentials = {
+			token: 'valid_access_token',
+			refreshToken: 'valid_refresh_token',
+			userId: 'test-user-id',
+			email: 'test@example.com',
+			expiresAt: new Date(Date.now() + 3600000).toISOString(), // Expires in 1 hour
+			savedAt: new Date().toISOString()
+		};
+
+		credentialStore.saveCredentials(validCredentials);
+
+		const credentials = authManager.getCredentials();
+
+		expect(credentials?.token).toBe('valid_access_token');
+	});
+
+	it('should return expired credentials even without refresh token', () => {
+		// Set up expired credentials WITHOUT refresh token
+		// We still return them - it's up to the caller to handle
+		const expiredCredentials: AuthCredentials = {
+			token: 'expired_access_token',
+			refreshToken: undefined,
+			userId: 'test-user-id',
+			email: 'test@example.com',
+			expiresAt: new Date(Date.now() - 1000).toISOString(), // Expired 1 second ago
+			savedAt: new Date().toISOString()
+		};
+
+		credentialStore.saveCredentials(expiredCredentials);
+
+		const credentials = authManager.getCredentials();
+
+		// Returns credentials even if expired
+		expect(credentials).not.toBeNull();
+		expect(credentials?.token).toBe('expired_access_token');
+	});
+
+	it('should return null if no credentials exist', () => {
+		const credentials = authManager.getCredentials();
+		expect(credentials).toBeNull();
+	});
+
+	it('should return credentials regardless of refresh token validity', () => {
+		// Set up expired credentials with refresh token
+		const expiredCredentials: AuthCredentials = {
+			token: 'expired_access_token',
+			refreshToken: 'invalid_refresh_token',
+			userId: 'test-user-id',
+			email: 'test@example.com',
+			expiresAt: new Date(Date.now() - 1000).toISOString(),
+			savedAt: new Date().toISOString()
+		};
+
+		credentialStore.saveCredentials(expiredCredentials);
+
+		const credentials = authManager.getCredentials();
+
+		// Returns credentials - refresh will be attempted by the client which will handle failure
+		expect(credentials).not.toBeNull();
+		expect(credentials?.token).toBe('expired_access_token');
+		expect(credentials?.refreshToken).toBe('invalid_refresh_token');
+	});
+});

packages/tm-core/tests/integration/auth-token-refresh.test.ts

@@ -0,0 +1,336 @@
+/**
+ * @fileoverview Integration tests for JWT token auto-refresh functionality
+ *
+ * These tests verify that expired tokens are automatically refreshed
+ * when making API calls through AuthManager.
+ */
+
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+import fs from 'fs';
+import os from 'os';
+import path from 'path';
+import type { Session } from '@supabase/supabase-js';
+import { AuthManager } from '../../src/auth/auth-manager';
+import { CredentialStore } from '../../src/auth/credential-store';
+import type { AuthCredentials } from '../../src/auth/types';
+
+describe('AuthManager - Token Auto-Refresh Integration', () => {
+	let authManager: AuthManager;
+	let credentialStore: CredentialStore;
+	let tmpDir: string;
+	let authFile: string;
+
+	// Mock Supabase session that will be returned on refresh
+	const mockRefreshedSession: Session = {
+		access_token: 'new-access-token-xyz',
+		refresh_token: 'new-refresh-token-xyz',
+		token_type: 'bearer',
+		expires_at: Math.floor(Date.now() / 1000) + 3600, // 1 hour from now
+		expires_in: 3600,
+		user: {
+			id: 'test-user-id',
+			email: 'test@example.com',
+			aud: 'authenticated',
+			role: 'authenticated',
+			app_metadata: {},
+			user_metadata: {},
+			created_at: new Date().toISOString()
+		}
+	};
+
+	beforeEach(() => {
+		// Reset singletons
+		AuthManager.resetInstance();
+		CredentialStore.resetInstance();
+
+		// Create temporary directory for test isolation
+		tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'tm-auth-integration-'));
+		authFile = path.join(tmpDir, 'auth.json');
+
+		// Initialize AuthManager with test config (this will create CredentialStore internally)
+		authManager = AuthManager.getInstance({
+			configDir: tmpDir,
+			configFile: authFile
+		});
+
+		// Get the CredentialStore instance that AuthManager created
+		credentialStore = CredentialStore.getInstance();
+		credentialStore.clearCredentials();
+	});
+
+	afterEach(() => {
+		// Clean up
+		try {
+			credentialStore.clearCredentials();
+		} catch {
+			// Ignore cleanup errors
+		}
+		AuthManager.resetInstance();
+		CredentialStore.resetInstance();
+		vi.restoreAllMocks();
+
+		// Remove temporary directory
+		if (tmpDir && fs.existsSync(tmpDir)) {
+			fs.rmSync(tmpDir, { recursive: true, force: true });
+		}
+	});
+
+	describe('Expired Token Detection', () => {
+		it('should return expired token for Supabase to refresh', () => {
+			// Set up expired credentials
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(), // 1 minute ago
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			// Get credentials returns them even if expired
+			const credentials = authManager.getCredentials();
+
+			expect(credentials).not.toBeNull();
+			expect(credentials?.token).toBe('expired-token');
+			expect(credentials?.refreshToken).toBe('valid-refresh-token');
+		});
+
+		it('should return valid token', () => {
+			// Set up valid credentials
+			const validCredentials: AuthCredentials = {
+				token: 'valid-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 3600000).toISOString(), // 1 hour from now
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(validCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			const credentials = authManager.getCredentials();
+
+			expect(credentials?.token).toBe('valid-token');
+		});
+	});
+
+	describe('Token Refresh Flow', () => {
+		it('should manually refresh expired token and save new credentials', async () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'old-token',
+				refreshToken: 'old-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date(Date.now() - 3600000).toISOString(),
+				selectedContext: {
+					orgId: 'test-org',
+					briefId: 'test-brief',
+					updatedAt: new Date().toISOString()
+				}
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			vi.spyOn(
+				authManager['supabaseClient'],
+				'refreshSession'
+			).mockResolvedValue(mockRefreshedSession);
+
+			// Explicitly call refreshToken() method
+			const refreshedCredentials = await authManager.refreshToken();
+
+			expect(refreshedCredentials).not.toBeNull();
+			expect(refreshedCredentials.token).toBe('new-access-token-xyz');
+			expect(refreshedCredentials.refreshToken).toBe('new-refresh-token-xyz');
+
+			// Verify context was preserved
+			expect(refreshedCredentials.selectedContext?.orgId).toBe('test-org');
+			expect(refreshedCredentials.selectedContext?.briefId).toBe('test-brief');
+
+			// Verify new expiration is in the future
+			const newExpiry = new Date(refreshedCredentials.expiresAt!).getTime();
+			const now = Date.now();
+			expect(newExpiry).toBeGreaterThan(now);
+		});
+
+		it('should throw error if manual refresh fails', async () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'invalid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			// Mock refresh to fail
+			vi.spyOn(
+				authManager['supabaseClient'],
+				'refreshSession'
+			).mockRejectedValue(new Error('Refresh token expired'));
+
+			// Explicit refreshToken() call should throw
+			await expect(authManager.refreshToken()).rejects.toThrow();
+		});
+
+		it('should return expired credentials even without refresh token', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				// No refresh token
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			const credentials = authManager.getCredentials();
+
+			// Credentials are returned even without refresh token
+			expect(credentials).not.toBeNull();
+			expect(credentials?.token).toBe('expired-token');
+			expect(credentials?.refreshToken).toBeUndefined();
+		});
+
+		it('should return null if credentials missing expiresAt', () => {
+			const credentialsWithoutExpiry: AuthCredentials = {
+				token: 'test-token',
+				refreshToken: 'refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				// Missing expiresAt - invalid token
+				savedAt: new Date().toISOString()
+			} as any;
+
+			credentialStore.saveCredentials(credentialsWithoutExpiry);
+
+			authManager = AuthManager.getInstance();
+
+			const credentials = authManager.getCredentials();
+
+			// Tokens without valid expiration are considered invalid
+			expect(credentials).toBeNull();
+		});
+	});
+
+	describe('Clock Skew Tolerance', () => {
+		it('should return credentials within 30-second expiry window', () => {
+			// Token expires in 15 seconds (within 30-second buffer)
+			// Supabase will handle refresh automatically
+			const almostExpiredCredentials: AuthCredentials = {
+				token: 'almost-expired-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 15000).toISOString(), // 15 seconds from now
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(almostExpiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			const credentials = authManager.getCredentials();
+
+			// Credentials are returned (Supabase handles auto-refresh in background)
+			expect(credentials).not.toBeNull();
+			expect(credentials?.token).toBe('almost-expired-token');
+			expect(credentials?.refreshToken).toBe('valid-refresh-token');
+		});
+
+		it('should return valid token well before expiry', () => {
+			// Token expires in 5 minutes
+			const validCredentials: AuthCredentials = {
+				token: 'valid-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() + 300000).toISOString(), // 5 minutes
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(validCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			const credentials = authManager.getCredentials();
+
+			// Valid credentials are returned as-is
+			expect(credentials).not.toBeNull();
+			expect(credentials?.token).toBe('valid-token');
+			expect(credentials?.refreshToken).toBe('valid-refresh-token');
+		});
+	});
+
+	describe('Synchronous vs Async Methods', () => {
+		it('getCredentials should return expired credentials', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			// Returns credentials even if expired - Supabase will handle refresh
+			const credentials = authManager.getCredentials();
+
+			expect(credentials).not.toBeNull();
+			expect(credentials?.token).toBe('expired-token');
+			expect(credentials?.refreshToken).toBe('valid-refresh-token');
+		});
+	});
+
+	describe('Multiple Concurrent Calls', () => {
+		it('should handle concurrent getCredentials calls gracefully', () => {
+			const expiredCredentials: AuthCredentials = {
+				token: 'expired-token',
+				refreshToken: 'valid-refresh-token',
+				userId: 'test-user-id',
+				email: 'test@example.com',
+				expiresAt: new Date(Date.now() - 60000).toISOString(),
+				savedAt: new Date().toISOString()
+			};
+
+			credentialStore.saveCredentials(expiredCredentials);
+
+			authManager = AuthManager.getInstance();
+
+			// Make multiple concurrent calls (synchronous now)
+			const creds1 = authManager.getCredentials();
+			const creds2 = authManager.getCredentials();
+			const creds3 = authManager.getCredentials();
+
+			// All should get the same credentials (even if expired)
+			expect(creds1?.token).toBe('expired-token');
+			expect(creds2?.token).toBe('expired-token');
+			expect(creds3?.token).toBe('expired-token');
+
+			// All include refresh token for Supabase to use
+			expect(creds1?.refreshToken).toBe('valid-refresh-token');
+			expect(creds2?.refreshToken).toBe('valid-refresh-token');
+			expect(creds3?.refreshToken).toBe('valid-refresh-token');
+		});
+	});
+});

scripts/modules/commands.js

@@ -2441,57 +2441,6 @@ ${result.result}
 			}
 		});
 
-	// next command
-	programInstance
-		.command('next')
-		.description(
-			`Show the next task to work on based on dependencies and status${chalk.reset('')}`
-		)
-		.option(
-			'-f, --file <file>',
-			'Path to the tasks file',
-			TASKMASTER_TASKS_FILE
-		)
-		.option(
-			'-r, --report <report>',
-			'Path to the complexity report file',
-			COMPLEXITY_REPORT_FILE
-		)
-		.option('--tag <tag>', 'Specify tag context for task operations')
-		.action(async (options) => {
-			const initOptions = {
-				tasksPath: options.file || true,
-				tag: options.tag
-			};
-
-			if (options.report && options.report !== COMPLEXITY_REPORT_FILE) {
-				initOptions.complexityReportPath = options.report;
-			}
-
-			// Initialize TaskMaster
-			const taskMaster = initTaskMaster({
-				tasksPath: options.file || true,
-				tag: options.tag,
-				complexityReportPath: options.report || false
-			});
-
-			const tag = taskMaster.getCurrentTag();
-
-			const context = {
-				projectRoot: taskMaster.getProjectRoot(),
-				tag
-			};
-
-			// Show current tag context
-			displayCurrentTagIndicator(tag);
-
-			await displayNextTask(
-				taskMaster.getTasksPath(),
-				taskMaster.getComplexityReportPath(),
-				context
-			);
-		});
-
 	// add-dependency command
 	programInstance
 		.command('add-dependency')

scripts/modules/config-manager.js

@@ -307,6 +307,20 @@ function validateProviderModelCombination(providerName, modelId) {
 	);
 }
 
+/**
+ * Gets the list of supported model IDs for a given provider from supported-models.json
+ * @param {string} providerName - The name of the provider (e.g., 'claude-code', 'anthropic')
+ * @returns {string[]} Array of supported model IDs, or empty array if provider not found
+ */
+export function getSupportedModelsForProvider(providerName) {
+	if (!MODEL_MAP[providerName]) {
+		return [];
+	}
+	return MODEL_MAP[providerName]
+		.filter((model) => model.supported !== false)
+		.map((model) => model.id);
+}
+
 /**
  * Validates Claude Code AI provider custom settings
  * @param {object} settings The settings to validate

scripts/modules/supported-models.json

@@ -43,6 +43,28 @@
 			"allowed_roles": ["main", "fallback"],
 			"max_tokens": 8192,
 			"supported": true
+		},
+		{
+			"id": "claude-sonnet-4-5-20250929",
+			"swe_score": 0.73,
+			"cost_per_1m_tokens": {
+				"input": 3.0,
+				"output": 15.0
+			},
+			"allowed_roles": ["main", "fallback"],
+			"max_tokens": 64000,
+			"supported": true
+		},
+		{
+			"id": "claude-haiku-4-5-20251001",
+			"swe_score": 0.45,
+			"cost_per_1m_tokens": {
+				"input": 1.0,
+				"output": 5.0
+			},
+			"allowed_roles": ["main", "fallback"],
+			"max_tokens": 200000,
+			"supported": true
 		}
 	],
 	"claude-code": [
@@ -67,6 +89,17 @@
 			"allowed_roles": ["main", "fallback", "research"],
 			"max_tokens": 64000,
 			"supported": true
+		},
+		{
+			"id": "haiku",
+			"swe_score": 0.45,
+			"cost_per_1m_tokens": {
+				"input": 0,
+				"output": 0
+			},
+			"allowed_roles": ["main", "fallback", "research"],
+			"max_tokens": 200000,
+			"supported": true
 		}
 	],
 	"codex-cli": [

src/ai-providers/claude-code.js

@@ -12,7 +12,10 @@
 
 import { createClaudeCode } from 'ai-sdk-provider-claude-code';
 import { BaseAIProvider } from './base-provider.js';
-import { getClaudeCodeSettingsForCommand } from '../../scripts/modules/config-manager.js';
+import {
+	getClaudeCodeSettingsForCommand,
+	getSupportedModelsForProvider
+} from '../../scripts/modules/config-manager.js';
 import { execSync } from 'child_process';
 import { log } from '../../scripts/modules/utils.js';
 
@@ -24,14 +27,24 @@ let _claudeCliAvailable = null;
  *
  * Features:
  * - No API key required (uses local Claude Code CLI)
- * - Supports 'sonnet' and 'opus' models
+ * - Supported models loaded from supported-models.json
  * - Command-specific configuration support
  */
 export class ClaudeCodeProvider extends BaseAIProvider {
 	constructor() {
 		super();
 		this.name = 'Claude Code';
-		this.supportedModels = ['sonnet', 'opus'];
+		// Load supported models from supported-models.json
+		this.supportedModels = getSupportedModelsForProvider('claude-code');
+
+		// Validate that models were loaded successfully
+		if (this.supportedModels.length === 0) {
+			log(
+				'warn',
+				'No supported models found for claude-code provider. Check supported-models.json configuration.'
+			);
+		}
+
 		// Claude Code requires explicit JSON schema mode
 		this.needsExplicitJsonSchema = true;
 		// Claude Code does not support temperature parameter

src/ai-providers/codex-cli.js

@@ -10,7 +10,10 @@ import { createCodexCli } from 'ai-sdk-provider-codex-cli';
 import { BaseAIProvider } from './base-provider.js';
 import { execSync } from 'child_process';
 import { log } from '../../scripts/modules/utils.js';
-import { getCodexCliSettingsForCommand } from '../../scripts/modules/config-manager.js';
+import {
+	getCodexCliSettingsForCommand,
+	getSupportedModelsForProvider
+} from '../../scripts/modules/config-manager.js';
 
 export class CodexCliProvider extends BaseAIProvider {
 	constructor() {
@@ -20,8 +23,17 @@ export class CodexCliProvider extends BaseAIProvider {
 		this.needsExplicitJsonSchema = false;
 		// Codex CLI does not support temperature parameter
 		this.supportsTemperature = false;
-		// Restrict to supported models for OAuth subscription usage
+		// Load supported models from supported-models.json
-		this.supportedModels = ['gpt-5', 'gpt-5-codex'];
+		this.supportedModels = getSupportedModelsForProvider('codex-cli');
+
+		// Validate that models were loaded successfully
+		if (this.supportedModels.length === 0) {
+			log(
+				'warn',
+				'No supported models found for codex-cli provider. Check supported-models.json configuration.'
+			);
+		}
+
 		// CLI availability check cache
 		this._codexCliChecked = false;
 		this._codexCliAvailable = null;

src/utils/path-utils.js

@@ -47,21 +47,33 @@ export function normalizeProjectRoot(projectRoot) {
 
 /**
  * Find the project root directory by looking for project markers
- * @param {string} startDir - Directory to start searching from
+ * Traverses upwards from startDir until a project marker is found or filesystem root is reached
- * @returns {string|null} - Project root path or null if not found
+ * Limited to 50 parent directory levels to prevent excessive traversal
+ * @param {string} startDir - Directory to start searching from (defaults to process.cwd())
+ * @returns {string} - Project root path (falls back to current directory if no markers found)
  */
 export function findProjectRoot(startDir = process.cwd()) {
+	// Define project markers that indicate a project root
+	// Prioritize Task Master specific markers first
 	const projectMarkers = [
-		'.taskmaster',
+		'.taskmaster', // Task Master directory (highest priority)
-		TASKMASTER_TASKS_FILE,
+		TASKMASTER_CONFIG_FILE, // .taskmaster/config.json
-		'tasks.json',
+		TASKMASTER_TASKS_FILE, // .taskmaster/tasks/tasks.json
-		LEGACY_TASKS_FILE,
+		LEGACY_CONFIG_FILE, // .taskmasterconfig (legacy)
-		'.git',
+		LEGACY_TASKS_FILE, // tasks/tasks.json (legacy)
-		'.svn',
+		'tasks.json', // Root tasks.json (legacy)
-		'package.json',
+		'.git', // Git repository
-		'yarn.lock',
+		'.svn', // SVN repository
-		'package-lock.json',
+		'package.json', // Node.js project
-		'pnpm-lock.yaml'
+		'yarn.lock', // Yarn project
+		'package-lock.json', // npm project
+		'pnpm-lock.yaml', // pnpm project
+		'Cargo.toml', // Rust project
+		'go.mod', // Go project
+		'pyproject.toml', // Python project
+		'requirements.txt', // Python project
+		'Gemfile', // Ruby project
+		'composer.json' // PHP project
 	];
 
 	let currentDir = path.resolve(startDir);
@@ -69,19 +81,36 @@ export function findProjectRoot(startDir = process.cwd()) {
 	const maxDepth = 50; // Reasonable limit to prevent infinite loops
 	let depth = 0;
 
+	// Traverse upwards looking for project markers
 	while (currentDir !== rootDir && depth < maxDepth) {
 		// Check if current directory contains any project markers
 		for (const marker of projectMarkers) {
 			const markerPath = path.join(currentDir, marker);
-			if (fs.existsSync(markerPath)) {
+			try {
-				return currentDir;
+				if (fs.existsSync(markerPath)) {
+					// Found a project marker - return this directory as project root
+					return currentDir;
+				}
+			} catch (error) {
+				// Ignore permission errors and continue searching
+				continue;
 			}
 		}
-		currentDir = path.dirname(currentDir);
+
+		// Move up one directory level
+		const parentDir = path.dirname(currentDir);
+
+		// Safety check: if dirname returns the same path, we've hit the root
+		if (parentDir === currentDir) {
+			break;
+		}
+
+		currentDir = parentDir;
 		depth++;
 	}
 
 	// Fallback to current working directory if no project root found
+	// This ensures the function always returns a valid path
 	return process.cwd();
 }
 

tests/helpers/tool-counts.js

@@ -0,0 +1,123 @@
+/**
+ * tool-counts.js
+ * Shared helper for validating tool counts across tests and validation scripts
+ */
+
+import {
+	getToolCounts,
+	getToolCategories
+} from '../../mcp-server/src/tools/tool-registry.js';
+
+/**
+ * Expected tool counts - update these when tools are added/removed
+ * These serve as the canonical source of truth for expected counts
+ */
+export const EXPECTED_TOOL_COUNTS = {
+	core: 7,
+	standard: 15,
+	total: 36
+};
+
+/**
+ * Expected core tools list for validation
+ */
+export const EXPECTED_CORE_TOOLS = [
+	'get_tasks',
+	'next_task',
+	'get_task',
+	'set_task_status',
+	'update_subtask',
+	'parse_prd',
+	'expand_task'
+];
+
+/**
+ * Validate that actual tool counts match expected counts
+ * @returns {Object} Validation result with isValid flag and details
+ */
+export function validateToolCounts() {
+	const actual = getToolCounts();
+	const expected = EXPECTED_TOOL_COUNTS;
+
+	const isValid =
+		actual.core === expected.core &&
+		actual.standard === expected.standard &&
+		actual.total === expected.total;
+
+	return {
+		isValid,
+		actual,
+		expected,
+		differences: {
+			core: actual.core - expected.core,
+			standard: actual.standard - expected.standard,
+			total: actual.total - expected.total
+		}
+	};
+}
+
+/**
+ * Validate that tool categories have correct structure and content
+ * @returns {Object} Validation result
+ */
+export function validateToolStructure() {
+	const categories = getToolCategories();
+	const counts = getToolCounts();
+
+	// Check that core tools are subset of standard tools
+	const coreInStandard = categories.core.every((tool) =>
+		categories.standard.includes(tool)
+	);
+
+	// Check that standard tools are subset of all tools
+	const standardInAll = categories.standard.every((tool) =>
+		categories.all.includes(tool)
+	);
+
+	// Check that expected core tools match actual
+	const expectedCoreMatch =
+		EXPECTED_CORE_TOOLS.every((tool) => categories.core.includes(tool)) &&
+		categories.core.every((tool) => EXPECTED_CORE_TOOLS.includes(tool));
+
+	// Check array lengths match counts
+	const lengthsMatch =
+		categories.core.length === counts.core &&
+		categories.standard.length === counts.standard &&
+		categories.all.length === counts.total;
+
+	return {
+		isValid:
+			coreInStandard && standardInAll && expectedCoreMatch && lengthsMatch,
+		details: {
+			coreInStandard,
+			standardInAll,
+			expectedCoreMatch,
+			lengthsMatch
+		},
+		categories,
+		counts
+	};
+}
+
+/**
+ * Get a detailed report of all tool information
+ * @returns {Object} Comprehensive tool information
+ */
+export function getToolReport() {
+	const counts = getToolCounts();
+	const categories = getToolCategories();
+	const validation = validateToolCounts();
+	const structure = validateToolStructure();
+
+	return {
+		counts,
+		categories,
+		validation,
+		structure,
+		summary: {
+			totalValid: validation.isValid && structure.isValid,
+			countsValid: validation.isValid,
+			structureValid: structure.isValid
+		}
+	};
+}

tests/integration/claude-code-error-handling.test.js

@@ -43,9 +43,9 @@ describe('Claude Code Error Handling', () => {
 
 		// These should work even if CLI is not available
 		expect(provider.name).toBe('Claude Code');
-		expect(provider.getSupportedModels()).toEqual(['sonnet', 'opus']);
+		expect(provider.getSupportedModels()).toEqual(['opus', 'sonnet', 'haiku']);
 		expect(provider.isModelSupported('sonnet')).toBe(true);
-		expect(provider.isModelSupported('haiku')).toBe(false);
+		expect(provider.isModelSupported('haiku')).toBe(true);
 		expect(provider.isRequiredApiKey()).toBe(false);
 		expect(() => provider.validateAuth()).not.toThrow();
 	});

tests/integration/claude-code-optional.test.js

@@ -40,14 +40,14 @@ describe('Claude Code Integration (Optional)', () => {
 	it('should create a working provider instance', () => {
 		const provider = new ClaudeCodeProvider();
 		expect(provider.name).toBe('Claude Code');
-		expect(provider.getSupportedModels()).toEqual(['sonnet', 'opus']);
+		expect(provider.getSupportedModels()).toEqual(['opus', 'sonnet', 'haiku']);
 	});
 
 	it('should support model validation', () => {
 		const provider = new ClaudeCodeProvider();
 		expect(provider.isModelSupported('sonnet')).toBe(true);
 		expect(provider.isModelSupported('opus')).toBe(true);
-		expect(provider.isModelSupported('haiku')).toBe(false);
+		expect(provider.isModelSupported('haiku')).toBe(true);
 		expect(provider.isModelSupported('unknown')).toBe(false);
 	});
 

tests/unit/ai-providers/claude-code.test.js

@@ -28,6 +28,14 @@ jest.unstable_mockModule('../../../src/ai-providers/base-provider.js', () => ({
 	}
 }));
 
+// Mock config getters
+jest.unstable_mockModule('../../../scripts/modules/config-manager.js', () => ({
+	getClaudeCodeSettingsForCommand: jest.fn(() => ({})),
+	getSupportedModelsForProvider: jest.fn(() => ['opus', 'sonnet', 'haiku']),
+	getDebugFlag: jest.fn(() => false),
+	getLogLevel: jest.fn(() => 'info')
+}));
+
 // Import after mocking
 const { ClaudeCodeProvider } = await import(
 	'../../../src/ai-providers/claude-code.js'
@@ -96,13 +104,13 @@ describe('ClaudeCodeProvider', () => {
 	describe('model support', () => {
 		it('should return supported models', () => {
 			const models = provider.getSupportedModels();
-			expect(models).toEqual(['sonnet', 'opus']);
+			expect(models).toEqual(['opus', 'sonnet', 'haiku']);
 		});
 
 		it('should check if model is supported', () => {
 			expect(provider.isModelSupported('sonnet')).toBe(true);
 			expect(provider.isModelSupported('opus')).toBe(true);
-			expect(provider.isModelSupported('haiku')).toBe(false);
+			expect(provider.isModelSupported('haiku')).toBe(true);
 			expect(provider.isModelSupported('unknown')).toBe(false);
 		});
 	});

tests/unit/ai-providers/codex-cli.test.js

@@ -20,6 +20,7 @@ jest.unstable_mockModule('ai-sdk-provider-codex-cli', () => ({
 // Mock config getters
 jest.unstable_mockModule('../../../scripts/modules/config-manager.js', () => ({
 	getCodexCliSettingsForCommand: jest.fn(() => ({ allowNpx: true })),
+	getSupportedModelsForProvider: jest.fn(() => ['gpt-5', 'gpt-5-codex']),
 	// Provide commonly imported getters to satisfy other module imports if any
 	getDebugFlag: jest.fn(() => false),
 	getLogLevel: jest.fn(() => 'info')

tests/unit/mcp/tools/tool-registration.test.js

@@ -0,0 +1,410 @@
+/**
+ * tool-registration.test.js
+ * Comprehensive unit tests for the Task Master MCP tool registration system
+ * Tests environment variable control system covering all configuration modes and edge cases
+ */
+
+import {
+	describe,
+	it,
+	expect,
+	beforeEach,
+	afterEach,
+	jest
+} from '@jest/globals';
+
+import {
+	EXPECTED_TOOL_COUNTS,
+	EXPECTED_CORE_TOOLS,
+	validateToolCounts,
+	validateToolStructure
+} from '../../../helpers/tool-counts.js';
+
+import { registerTaskMasterTools } from '../../../../mcp-server/src/tools/index.js';
+import {
+	toolRegistry,
+	coreTools,
+	standardTools
+} from '../../../../mcp-server/src/tools/tool-registry.js';
+
+// Derive constants from imported registry to avoid brittle magic numbers
+const ALL_COUNT = Object.keys(toolRegistry).length;
+const CORE_COUNT = coreTools.length;
+const STANDARD_COUNT = standardTools.length;
+
+describe('Task Master Tool Registration System', () => {
+	let mockServer;
+	let originalEnv;
+
+	beforeEach(() => {
+		originalEnv = process.env.TASK_MASTER_TOOLS;
+
+		mockServer = {
+			tools: [],
+			addTool: jest.fn((tool) => {
+				mockServer.tools.push(tool);
+				return tool;
+			})
+		};
+
+		delete process.env.TASK_MASTER_TOOLS;
+	});
+
+	afterEach(() => {
+		if (originalEnv !== undefined) {
+			process.env.TASK_MASTER_TOOLS = originalEnv;
+		} else {
+			delete process.env.TASK_MASTER_TOOLS;
+		}
+
+		jest.clearAllMocks();
+	});
+
+	describe('Test Environment Setup', () => {
+		it('should have properly configured mock server', () => {
+			expect(mockServer).toBeDefined();
+			expect(typeof mockServer.addTool).toBe('function');
+			expect(Array.isArray(mockServer.tools)).toBe(true);
+			expect(mockServer.tools.length).toBe(0);
+		});
+
+		it('should have correct tool registry structure', () => {
+			const validation = validateToolCounts();
+			expect(validation.isValid).toBe(true);
+
+			if (!validation.isValid) {
+				console.error('Tool count validation failed:', validation);
+			}
+
+			expect(validation.actual.total).toBe(EXPECTED_TOOL_COUNTS.total);
+			expect(validation.actual.core).toBe(EXPECTED_TOOL_COUNTS.core);
+			expect(validation.actual.standard).toBe(EXPECTED_TOOL_COUNTS.standard);
+		});
+
+		it('should have correct core tools', () => {
+			const structure = validateToolStructure();
+			expect(structure.isValid).toBe(true);
+
+			if (!structure.isValid) {
+				console.error('Tool structure validation failed:', structure);
+			}
+
+			expect(coreTools).toEqual(expect.arrayContaining(EXPECTED_CORE_TOOLS));
+			expect(coreTools.length).toBe(EXPECTED_TOOL_COUNTS.core);
+		});
+
+		it('should have correct standard tools that include all core tools', () => {
+			const structure = validateToolStructure();
+			expect(structure.details.coreInStandard).toBe(true);
+			expect(standardTools.length).toBe(EXPECTED_TOOL_COUNTS.standard);
+
+			coreTools.forEach((tool) => {
+				expect(standardTools).toContain(tool);
+			});
+		});
+
+		it('should have all expected tools in registry', () => {
+			const expectedTools = [
+				'initialize_project',
+				'models',
+				'research',
+				'add_tag',
+				'delete_tag',
+				'get_tasks',
+				'next_task',
+				'get_task'
+			];
+			expectedTools.forEach((tool) => {
+				expect(toolRegistry).toHaveProperty(tool);
+			});
+		});
+	});
+
+	describe('Configuration Modes', () => {
+		it(`should register all tools (${ALL_COUNT}) when TASK_MASTER_TOOLS is not set (default behavior)`, () => {
+			delete process.env.TASK_MASTER_TOOLS;
+
+			registerTaskMasterTools(mockServer);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(
+				EXPECTED_TOOL_COUNTS.total
+			);
+		});
+
+		it(`should register all tools (${ALL_COUNT}) when TASK_MASTER_TOOLS=all`, () => {
+			process.env.TASK_MASTER_TOOLS = 'all';
+
+			registerTaskMasterTools(mockServer);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+		});
+
+		it(`should register exactly ${CORE_COUNT} core tools when TASK_MASTER_TOOLS=core`, () => {
+			process.env.TASK_MASTER_TOOLS = 'core';
+
+			registerTaskMasterTools(mockServer, 'core');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(
+				EXPECTED_TOOL_COUNTS.core
+			);
+		});
+
+		it(`should register exactly ${STANDARD_COUNT} standard tools when TASK_MASTER_TOOLS=standard`, () => {
+			process.env.TASK_MASTER_TOOLS = 'standard';
+
+			registerTaskMasterTools(mockServer, 'standard');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(
+				EXPECTED_TOOL_COUNTS.standard
+			);
+		});
+
+		it(`should treat lean as alias for core mode (${CORE_COUNT} tools)`, () => {
+			process.env.TASK_MASTER_TOOLS = 'lean';
+
+			registerTaskMasterTools(mockServer, 'lean');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(CORE_COUNT);
+		});
+
+		it('should handle case insensitive configuration values', () => {
+			process.env.TASK_MASTER_TOOLS = 'CORE';
+
+			registerTaskMasterTools(mockServer, 'CORE');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(CORE_COUNT);
+		});
+	});
+
+	describe('Custom Tool Selection and Edge Cases', () => {
+		it('should register specific tools from comma-separated list', () => {
+			process.env.TASK_MASTER_TOOLS = 'get_tasks,next_task,get_task';
+
+			registerTaskMasterTools(mockServer, 'get_tasks,next_task,get_task');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(3);
+		});
+
+		it('should handle mixed valid and invalid tool names gracefully', () => {
+			process.env.TASK_MASTER_TOOLS =
+				'invalid_tool,get_tasks,fake_tool,next_task';
+
+			registerTaskMasterTools(
+				mockServer,
+				'invalid_tool,get_tasks,fake_tool,next_task'
+			);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(2);
+		});
+
+		it('should default to all tools with completely invalid input', () => {
+			process.env.TASK_MASTER_TOOLS = 'completely_invalid';
+
+			registerTaskMasterTools(mockServer);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+		});
+
+		it('should handle empty string environment variable', () => {
+			process.env.TASK_MASTER_TOOLS = '';
+
+			registerTaskMasterTools(mockServer);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+		});
+
+		it('should handle whitespace in comma-separated lists', () => {
+			process.env.TASK_MASTER_TOOLS = ' get_tasks , next_task , get_task ';
+
+			registerTaskMasterTools(mockServer, ' get_tasks , next_task , get_task ');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(3);
+		});
+
+		it('should ignore duplicate tools in list', () => {
+			process.env.TASK_MASTER_TOOLS = 'get_tasks,get_tasks,next_task,get_tasks';
+
+			registerTaskMasterTools(
+				mockServer,
+				'get_tasks,get_tasks,next_task,get_tasks'
+			);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(2);
+		});
+
+		it('should handle only commas and empty entries', () => {
+			process.env.TASK_MASTER_TOOLS = ',,,';
+
+			registerTaskMasterTools(mockServer);
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+		});
+
+		it('should handle single tool selection', () => {
+			process.env.TASK_MASTER_TOOLS = 'get_tasks';
+
+			registerTaskMasterTools(mockServer, 'get_tasks');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(1);
+		});
+	});
+
+	describe('Coverage Analysis and Integration Tests', () => {
+		it('should provide 100% code coverage for environment control logic', () => {
+			const testCases = [
+				{
+					env: undefined,
+					expectedCount: ALL_COUNT,
+					description: 'undefined env (all)'
+				},
+				{
+					env: '',
+					expectedCount: ALL_COUNT,
+					description: 'empty string (all)'
+				},
+				{ env: 'all', expectedCount: ALL_COUNT, description: 'all mode' },
+				{ env: 'core', expectedCount: CORE_COUNT, description: 'core mode' },
+				{
+					env: 'lean',
+					expectedCount: CORE_COUNT,
+					description: 'lean mode (alias)'
+				},
+				{
+					env: 'standard',
+					expectedCount: STANDARD_COUNT,
+					description: 'standard mode'
+				},
+				{
+					env: 'get_tasks,next_task',
+					expectedCount: 2,
+					description: 'custom list'
+				},
+				{
+					env: 'invalid_tool',
+					expectedCount: ALL_COUNT,
+					description: 'invalid fallback'
+				}
+			];
+
+			testCases.forEach((testCase) => {
+				delete process.env.TASK_MASTER_TOOLS;
+				if (testCase.env !== undefined) {
+					process.env.TASK_MASTER_TOOLS = testCase.env;
+				}
+
+				mockServer.tools = [];
+				mockServer.addTool.mockClear();
+
+				registerTaskMasterTools(mockServer, testCase.env || 'all');
+
+				expect(mockServer.addTool).toHaveBeenCalledTimes(
+					testCase.expectedCount
+				);
+			});
+		});
+
+		it('should have optimal performance characteristics', () => {
+			const startTime = Date.now();
+
+			process.env.TASK_MASTER_TOOLS = 'all';
+
+			registerTaskMasterTools(mockServer);
+
+			const endTime = Date.now();
+			const executionTime = endTime - startTime;
+
+			expect(executionTime).toBeLessThan(100);
+			expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+		});
+
+		it('should validate token reduction claims', () => {
+			expect(coreTools.length).toBeLessThan(standardTools.length);
+			expect(standardTools.length).toBeLessThan(
+				Object.keys(toolRegistry).length
+			);
+
+			expect(coreTools.length).toBe(CORE_COUNT);
+			expect(standardTools.length).toBe(STANDARD_COUNT);
+			expect(Object.keys(toolRegistry).length).toBe(ALL_COUNT);
+
+			const allToolsCount = Object.keys(toolRegistry).length;
+			const coreReduction =
+				((allToolsCount - coreTools.length) / allToolsCount) * 100;
+			const standardReduction =
+				((allToolsCount - standardTools.length) / allToolsCount) * 100;
+
+			expect(coreReduction).toBeGreaterThan(80);
+			expect(standardReduction).toBeGreaterThan(50);
+		});
+
+		it('should maintain referential integrity of tool registry', () => {
+			coreTools.forEach((tool) => {
+				expect(standardTools).toContain(tool);
+			});
+
+			standardTools.forEach((tool) => {
+				expect(toolRegistry).toHaveProperty(tool);
+			});
+
+			Object.keys(toolRegistry).forEach((tool) => {
+				expect(typeof toolRegistry[tool]).toBe('function');
+			});
+		});
+
+		it('should handle concurrent registration attempts', () => {
+			process.env.TASK_MASTER_TOOLS = 'core';
+
+			registerTaskMasterTools(mockServer, 'core');
+			registerTaskMasterTools(mockServer, 'core');
+			registerTaskMasterTools(mockServer, 'core');
+
+			expect(mockServer.addTool).toHaveBeenCalledTimes(CORE_COUNT * 3);
+		});
+
+		it('should validate all documented tool categories exist', () => {
+			const allTools = Object.keys(toolRegistry);
+
+			const projectSetupTools = allTools.filter((tool) =>
+				['initialize_project', 'models', 'rules', 'parse_prd'].includes(tool)
+			);
+			expect(projectSetupTools.length).toBeGreaterThan(0);
+
+			const taskManagementTools = allTools.filter((tool) =>
+				['get_tasks', 'get_task', 'next_task', 'set_task_status'].includes(tool)
+			);
+			expect(taskManagementTools.length).toBeGreaterThan(0);
+
+			const analysisTools = allTools.filter((tool) =>
+				['analyze_project_complexity', 'complexity_report'].includes(tool)
+			);
+			expect(analysisTools.length).toBeGreaterThan(0);
+
+			const tagManagementTools = allTools.filter((tool) =>
+				['add_tag', 'delete_tag', 'list_tags', 'use_tag'].includes(tool)
+			);
+			expect(tagManagementTools.length).toBeGreaterThan(0);
+		});
+
+		it('should handle error conditions gracefully', () => {
+			const problematicInputs = [
+				'null',
+				'undefined',
+				'   ',
+				'\n\t',
+				'special!@#$%^&*()characters',
+				'very,very,very,very,very,very,very,long,comma,separated,list,with,invalid,tools,that,should,fallback,to,all'
+			];
+
+			problematicInputs.forEach((input) => {
+				mockServer.tools = [];
+				mockServer.addTool.mockClear();
+
+				process.env.TASK_MASTER_TOOLS = input;
+
+				expect(() => registerTaskMasterTools(mockServer)).not.toThrow();
+
+				expect(mockServer.addTool).toHaveBeenCalledTimes(ALL_COUNT);
+			});
+		});
+	});
+});

tests/unit/path-utils-find-project-root.test.js

@@ -0,0 +1,223 @@
+/**
+ * Unit tests for findProjectRoot() function
+ * Tests the parent directory traversal functionality
+ */
+
+import { jest } from '@jest/globals';
+import path from 'path';
+import fs from 'fs';
+
+// Import the function to test
+import { findProjectRoot } from '../../src/utils/path-utils.js';
+
+describe('findProjectRoot', () => {
+	describe('Parent Directory Traversal', () => {
+		test('should find .taskmaster in parent directory', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				// .taskmaster exists only at /project
+				return normalized === path.normalize('/project/.taskmaster');
+			});
+
+			const result = findProjectRoot('/project/subdir');
+
+			expect(result).toBe('/project');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should find .git in parent directory', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				return normalized === path.normalize('/project/.git');
+			});
+
+			const result = findProjectRoot('/project/subdir');
+
+			expect(result).toBe('/project');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should find package.json in parent directory', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				return normalized === path.normalize('/project/package.json');
+			});
+
+			const result = findProjectRoot('/project/subdir');
+
+			expect(result).toBe('/project');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should traverse multiple levels to find project root', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				// Only exists at /project, not in any subdirectories
+				return normalized === path.normalize('/project/.taskmaster');
+			});
+
+			const result = findProjectRoot('/project/subdir/deep/nested');
+
+			expect(result).toBe('/project');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should return current directory as fallback when no markers found', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			// No project markers exist anywhere
+			mockExistsSync.mockReturnValue(false);
+
+			const result = findProjectRoot('/some/random/path');
+
+			// Should fall back to process.cwd()
+			expect(result).toBe(process.cwd());
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should find markers at current directory before checking parent', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				// .git exists at /project/subdir, .taskmaster exists at /project
+				if (normalized.includes('/project/subdir/.git')) return true;
+				if (normalized.includes('/project/.taskmaster')) return true;
+				return false;
+			});
+
+			const result = findProjectRoot('/project/subdir');
+
+			// Should find /project/subdir first because .git exists there,
+			// even though .taskmaster is earlier in the marker array
+			expect(result).toBe('/project/subdir');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should handle permission errors gracefully', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				const normalized = path.normalize(checkPath);
+				// Throw permission error for checks in /project/subdir
+				if (normalized.startsWith('/project/subdir/')) {
+					throw new Error('EACCES: permission denied');
+				}
+				// Return true only for .taskmaster at /project
+				return normalized.includes('/project/.taskmaster');
+			});
+
+			const result = findProjectRoot('/project/subdir');
+
+			// Should handle permission errors in subdirectory and traverse to parent
+			expect(result).toBe('/project');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should detect filesystem root correctly', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			// No markers exist
+			mockExistsSync.mockReturnValue(false);
+
+			const result = findProjectRoot('/');
+
+			// Should stop at root and fall back to process.cwd()
+			expect(result).toBe(process.cwd());
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should recognize various project markers', () => {
+			const projectMarkers = [
+				'.taskmaster',
+				'.git',
+				'package.json',
+				'Cargo.toml',
+				'go.mod',
+				'pyproject.toml',
+				'requirements.txt',
+				'Gemfile',
+				'composer.json'
+			];
+
+			projectMarkers.forEach((marker) => {
+				const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+				mockExistsSync.mockImplementation((checkPath) => {
+					const normalized = path.normalize(checkPath);
+					return normalized.includes(`/project/${marker}`);
+				});
+
+				const result = findProjectRoot('/project/subdir');
+
+				expect(result).toBe('/project');
+
+				mockExistsSync.mockRestore();
+			});
+		});
+	});
+
+	describe('Edge Cases', () => {
+		test('should handle empty string as startDir', () => {
+			const result = findProjectRoot('');
+
+			// Should use process.cwd() or fall back appropriately
+			expect(typeof result).toBe('string');
+			expect(result.length).toBeGreaterThan(0);
+		});
+
+		test('should handle relative paths', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			mockExistsSync.mockImplementation((checkPath) => {
+				// Simulate .git existing in the resolved path
+				return checkPath.includes('.git');
+			});
+
+			const result = findProjectRoot('./subdir');
+
+			expect(typeof result).toBe('string');
+
+			mockExistsSync.mockRestore();
+		});
+
+		test('should not exceed max depth limit', () => {
+			const mockExistsSync = jest.spyOn(fs, 'existsSync');
+
+			// Track how many times existsSync is called
+			let callCount = 0;
+			mockExistsSync.mockImplementation(() => {
+				callCount++;
+				return false; // Never find a marker
+			});
+
+			// Create a very deep path
+			const deepPath = '/a/'.repeat(100) + 'deep';
+			const result = findProjectRoot(deepPath);
+
+			// Should stop after max depth (50) and not check 100 levels
+			// Each level checks multiple markers, so callCount will be high but bounded
+			expect(callCount).toBeLessThan(1000); // Reasonable upper bound
+			// With 18 markers and max depth of 50, expect around 900 calls maximum
+			expect(callCount).toBeLessThanOrEqual(50 * 18);
+
+			mockExistsSync.mockRestore();
+		});
+	});
+});