docs: auto-update documentation based on changes in next branch

This PR was automatically generated to update documentation based on recent changes.

  Original commit: Merge pull request #1291 from eyaltoledano/raplh/chore/merge.main\n\n\n

  Co-authored-by: Claude <claude-assistant@anthropic.com>

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

@@ -0,0 +1,7 @@
+---
+"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/nice-ways-hope.md

@@ -0,0 +1,17 @@
+---
+"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/plain-falcons-serve.md

@@ -0,0 +1,7 @@
+---
+"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.

.taskmaster/templates/example_prd_rpg.txt

@@ -0,0 +1,511 @@
+<rpg-method>
+# Repository Planning Graph (RPG) Method - PRD Template
+
+This template teaches you (AI or human) how to create structured, dependency-aware PRDs using the RPG methodology from Microsoft Research. The key insight: separate WHAT (functional) from HOW (structural), then connect them with explicit dependencies.
+
+## Core Principles
+
+1. **Dual-Semantics**: Think functional (capabilities) AND structural (code organization) separately, then map them
+2. **Explicit Dependencies**: Never assume - always state what depends on what
+3. **Topological Order**: Build foundation first, then layers on top
+4. **Progressive Refinement**: Start broad, refine iteratively
+
+## How to Use This Template
+
+- Follow the instructions in each `<instruction>` block
+- Look at `<example>` blocks to see good vs bad patterns
+- Fill in the content sections with your project details
+- The AI reading this will learn the RPG method by following along
+- Task Master will parse the resulting PRD into dependency-aware tasks
+
+## Recommended Tools for Creating PRDs
+
+When using this template to **create** a PRD (not parse it), use **code-context-aware AI assistants** for best results:
+
+**Why?** The AI needs to understand your existing codebase to make good architectural decisions about modules, dependencies, and integration points.
+
+**Recommended tools:**
+- **Claude Code** (claude-code CLI) - Best for structured reasoning and large contexts
+- **Cursor/Windsurf** - IDE integration with full codebase context
+- **Gemini CLI** (gemini-cli) - Massive context window for large codebases
+- **Codex/Grok CLI** - Strong code generation with context awareness
+
+**Note:** Once your PRD is created, `task-master parse-prd` works with any configured AI model - it just needs to read the PRD text itself, not your codebase.
+</rpg-method>
+
+---
+
+<overview>
+<instruction>
+Start with the problem, not the solution. Be specific about:
+- What pain point exists?
+- Who experiences it?
+- Why existing solutions don't work?
+- What success looks like (measurable outcomes)?
+
+Keep this section focused - don't jump into implementation details yet.
+</instruction>
+
+## Problem Statement
+[Describe the core problem. Be concrete about user pain points.]
+
+## Target Users
+[Define personas, their workflows, and what they're trying to achieve.]
+
+## Success Metrics
+[Quantifiable outcomes. Examples: "80% task completion via autopilot", "< 5% manual intervention rate"]
+
+</overview>
+
+---
+
+<functional-decomposition>
+<instruction>
+Now think about CAPABILITIES (what the system DOES), not code structure yet.
+
+Step 1: Identify high-level capability domains
+- Think: "What major things does this system do?"
+- Examples: Data Management, Core Processing, Presentation Layer
+
+Step 2: For each capability, enumerate specific features
+- Use explore-exploit strategy:
+  * Exploit: What features are REQUIRED for core value?
+  * Explore: What features make this domain COMPLETE?
+
+Step 3: For each feature, define:
+- Description: What it does in one sentence
+- Inputs: What data/context it needs
+- Outputs: What it produces/returns
+- Behavior: Key logic or transformations
+
+<example type="good">
+Capability: Data Validation
+  Feature: Schema validation
+    - Description: Validate JSON payloads against defined schemas
+    - Inputs: JSON object, schema definition
+    - Outputs: Validation result (pass/fail) + error details
+    - Behavior: Iterate fields, check types, enforce constraints
+
+  Feature: Business rule validation
+    - Description: Apply domain-specific validation rules
+    - Inputs: Validated data object, rule set
+    - Outputs: Boolean + list of violated rules
+    - Behavior: Execute rules sequentially, short-circuit on failure
+</example>
+
+<example type="bad">
+Capability: validation.js
+  (Problem: This is a FILE, not a CAPABILITY. Mixing structure into functional thinking.)
+
+Capability: Validation
+  Feature: Make sure data is good
+  (Problem: Too vague. No inputs/outputs. Not actionable.)
+</example>
+</instruction>
+
+## Capability Tree
+
+### Capability: [Name]
+[Brief description of what this capability domain covers]
+
+#### Feature: [Name]
+- **Description**: [One sentence]
+- **Inputs**: [What it needs]
+- **Outputs**: [What it produces]
+- **Behavior**: [Key logic]
+
+#### Feature: [Name]
+- **Description**:
+- **Inputs**:
+- **Outputs**:
+- **Behavior**:
+
+### Capability: [Name]
+...
+
+</functional-decomposition>
+
+---
+
+<structural-decomposition>
+<instruction>
+NOW think about code organization. Map capabilities to actual file/folder structure.
+
+Rules:
+1. Each capability maps to a module (folder or file)
+2. Features within a capability map to functions/classes
+3. Use clear module boundaries - each module has ONE responsibility
+4. Define what each module exports (public interface)
+
+The goal: Create a clear mapping between "what it does" (functional) and "where it lives" (structural).
+
+<example type="good">
+Capability: Data Validation
+  → Maps to: src/validation/
+    ├── schema-validator.js      (Schema validation feature)
+    ├── rule-validator.js         (Business rule validation feature)
+    └── index.js                  (Public exports)
+
+Exports:
+  - validateSchema(data, schema)
+  - validateRules(data, rules)
+</example>
+
+<example type="bad">
+Capability: Data Validation
+  → Maps to: src/utils.js
+  (Problem: "utils" is not a clear module boundary. Where do I find validation logic?)
+
+Capability: Data Validation
+  → Maps to: src/validation/everything.js
+  (Problem: One giant file. Features should map to separate files for maintainability.)
+</example>
+</instruction>
+
+## Repository Structure
+
+```
+project-root/
+├── src/
+│   ├── [module-name]/       # Maps to: [Capability Name]
+│   │   ├── [file].js        # Maps to: [Feature Name]
+│   │   └── index.js         # Public exports
+│   └── [module-name]/
+├── tests/
+└── docs/
+```
+
+## Module Definitions
+
+### Module: [Name]
+- **Maps to capability**: [Capability from functional decomposition]
+- **Responsibility**: [Single clear purpose]
+- **File structure**:
+  ```
+  module-name/
+  ├── feature1.js
+  ├── feature2.js
+  └── index.js
+  ```
+- **Exports**:
+  - `functionName()` - [what it does]
+  - `ClassName` - [what it does]
+
+</structural-decomposition>
+
+---
+
+<dependency-graph>
+<instruction>
+This is THE CRITICAL SECTION for Task Master parsing.
+
+Define explicit dependencies between modules. This creates the topological order for task execution.
+
+Rules:
+1. List modules in dependency order (foundation first)
+2. For each module, state what it depends on
+3. Foundation modules should have NO dependencies
+4. Every non-foundation module should depend on at least one other module
+5. Think: "What must EXIST before I can build this module?"
+
+<example type="good">
+Foundation Layer (no dependencies):
+  - error-handling: No dependencies
+  - config-manager: No dependencies
+  - base-types: No dependencies
+
+Data Layer:
+  - schema-validator: Depends on [base-types, error-handling]
+  - data-ingestion: Depends on [schema-validator, config-manager]
+
+Core Layer:
+  - algorithm-engine: Depends on [base-types, error-handling]
+  - pipeline-orchestrator: Depends on [algorithm-engine, data-ingestion]
+</example>
+
+<example type="bad">
+- validation: Depends on API
+- API: Depends on validation
+(Problem: Circular dependency. This will cause build/runtime issues.)
+
+- user-auth: Depends on everything
+(Problem: Too many dependencies. Should be more focused.)
+</example>
+</instruction>
+
+## Dependency Chain
+
+### Foundation Layer (Phase 0)
+No dependencies - these are built first.
+
+- **[Module Name]**: [What it provides]
+- **[Module Name]**: [What it provides]
+
+### [Layer Name] (Phase 1)
+- **[Module Name]**: Depends on [[module-from-phase-0], [module-from-phase-0]]
+- **[Module Name]**: Depends on [[module-from-phase-0]]
+
+### [Layer Name] (Phase 2)
+- **[Module Name]**: Depends on [[module-from-phase-1], [module-from-foundation]]
+
+[Continue building up layers...]
+
+</dependency-graph>
+
+---
+
+<implementation-roadmap>
+<instruction>
+Turn the dependency graph into concrete development phases.
+
+Each phase should:
+1. Have clear entry criteria (what must exist before starting)
+2. Contain tasks that can be parallelized (no inter-dependencies within phase)
+3. Have clear exit criteria (how do we know phase is complete?)
+4. Build toward something USABLE (not just infrastructure)
+
+Phase ordering follows topological sort of dependency graph.
+
+<example type="good">
+Phase 0: Foundation
+  Entry: Clean repository
+  Tasks:
+    - Implement error handling utilities
+    - Create base type definitions
+    - Setup configuration system
+  Exit: Other modules can import foundation without errors
+
+Phase 1: Data Layer
+  Entry: Phase 0 complete
+  Tasks:
+    - Implement schema validator (uses: base types, error handling)
+    - Build data ingestion pipeline (uses: validator, config)
+  Exit: End-to-end data flow from input to validated output
+</example>
+
+<example type="bad">
+Phase 1: Build Everything
+  Tasks:
+    - API
+    - Database
+    - UI
+    - Tests
+  (Problem: No clear focus. Too broad. Dependencies not considered.)
+</example>
+</instruction>
+
+## Development Phases
+
+### Phase 0: [Foundation Name]
+**Goal**: [What foundational capability this establishes]
+
+**Entry Criteria**: [What must be true before starting]
+
+**Tasks**:
+- [ ] [Task name] (depends on: [none or list])
+  - Acceptance criteria: [How we know it's done]
+  - Test strategy: [What tests prove it works]
+
+- [ ] [Task name] (depends on: [none or list])
+
+**Exit Criteria**: [Observable outcome that proves phase complete]
+
+**Delivers**: [What can users/developers do after this phase?]
+
+---
+
+### Phase 1: [Layer Name]
+**Goal**:
+
+**Entry Criteria**: Phase 0 complete
+
+**Tasks**:
+- [ ] [Task name] (depends on: [[tasks-from-phase-0]])
+- [ ] [Task name] (depends on: [[tasks-from-phase-0]])
+
+**Exit Criteria**:
+
+**Delivers**:
+
+---
+
+[Continue with more phases...]
+
+</implementation-roadmap>
+
+---
+
+<test-strategy>
+<instruction>
+Define how testing will be integrated throughout development (TDD approach).
+
+Specify:
+1. Test pyramid ratios (unit vs integration vs e2e)
+2. Coverage requirements
+3. Critical test scenarios
+4. Test generation guidelines for Surgical Test Generator
+
+This section guides the AI when generating tests during the RED phase of TDD.
+
+<example type="good">
+Critical Test Scenarios for Data Validation module:
+  - Happy path: Valid data passes all checks
+  - Edge cases: Empty strings, null values, boundary numbers
+  - Error cases: Invalid types, missing required fields
+  - Integration: Validator works with ingestion pipeline
+</example>
+</instruction>
+
+## Test Pyramid
+
+```
+        /\
+       /E2E\       ← [X]% (End-to-end, slow, comprehensive)
+      /------\
+     /Integration\ ← [Y]% (Module interactions)
+    /------------\
+   /  Unit Tests  \ ← [Z]% (Fast, isolated, deterministic)
+  /----------------\
+```
+
+## Coverage Requirements
+- Line coverage: [X]% minimum
+- Branch coverage: [X]% minimum
+- Function coverage: [X]% minimum
+- Statement coverage: [X]% minimum
+
+## Critical Test Scenarios
+
+### [Module/Feature Name]
+**Happy path**:
+- [Scenario description]
+- Expected: [What should happen]
+
+**Edge cases**:
+- [Scenario description]
+- Expected: [What should happen]
+
+**Error cases**:
+- [Scenario description]
+- Expected: [How system handles failure]
+
+**Integration points**:
+- [What interactions to test]
+- Expected: [End-to-end behavior]
+
+## Test Generation Guidelines
+[Specific instructions for Surgical Test Generator about what to focus on, what patterns to follow, project-specific test conventions]
+
+</test-strategy>
+
+---
+
+<architecture>
+<instruction>
+Describe technical architecture, data models, and key design decisions.
+
+Keep this section AFTER functional/structural decomposition - implementation details come after understanding structure.
+</instruction>
+
+## System Components
+[Major architectural pieces and their responsibilities]
+
+## Data Models
+[Core data structures, schemas, database design]
+
+## Technology Stack
+[Languages, frameworks, key libraries]
+
+**Decision: [Technology/Pattern]**
+- **Rationale**: [Why chosen]
+- **Trade-offs**: [What we're giving up]
+- **Alternatives considered**: [What else we looked at]
+
+</architecture>
+
+---
+
+<risks>
+<instruction>
+Identify risks that could derail development and how to mitigate them.
+
+Categories:
+- Technical risks (complexity, unknowns)
+- Dependency risks (blocking issues)
+- Scope risks (creep, underestimation)
+</instruction>
+
+## Technical Risks
+**Risk**: [Description]
+- **Impact**: [High/Medium/Low - effect on project]
+- **Likelihood**: [High/Medium/Low]
+- **Mitigation**: [How to address]
+- **Fallback**: [Plan B if mitigation fails]
+
+## Dependency Risks
+[External dependencies, blocking issues]
+
+## Scope Risks
+[Scope creep, underestimation, unclear requirements]
+
+</risks>
+
+---
+
+<appendix>
+## References
+[Papers, documentation, similar systems]
+
+## Glossary
+[Domain-specific terms]
+
+## Open Questions
+[Things to resolve during development]
+</appendix>
+
+---
+
+<task-master-integration>
+# How Task Master Uses This PRD
+
+When you run `task-master parse-prd <file>.txt`, the parser:
+
+1. **Extracts capabilities** → Main tasks
+   - Each `### Capability:` becomes a top-level task
+
+2. **Extracts features** → Subtasks
+   - Each `#### Feature:` becomes a subtask under its capability
+
+3. **Parses dependencies** → Task dependencies
+   - `Depends on: [X, Y]` sets task.dependencies = ["X", "Y"]
+
+4. **Orders by phases** → Task priorities
+   - Phase 0 tasks = highest priority
+   - Phase N tasks = lower priority, properly sequenced
+
+5. **Uses test strategy** → Test generation context
+   - Feeds test scenarios to Surgical Test Generator during implementation
+
+**Result**: A dependency-aware task graph that can be executed in topological order.
+
+## Why RPG Structure Matters
+
+Traditional flat PRDs lead to:
+- ❌ Unclear task dependencies
+- ❌ Arbitrary task ordering
+- ❌ Circular dependencies discovered late
+- ❌ Poorly scoped tasks
+
+RPG-structured PRDs provide:
+- ✅ Explicit dependency chains
+- ✅ Topological execution order
+- ✅ Clear module boundaries
+- ✅ Validated task graph before implementation
+
+## Tips for Best Results
+
+1. **Spend time on dependency graph** - This is the most valuable section for Task Master
+2. **Keep features atomic** - Each feature should be independently testable
+3. **Progressive refinement** - Start broad, use `task-master expand` to break down complex tasks
+4. **Use research mode** - `task-master parse-prd --research` leverages AI for better task generation
+</task-master-integration>

apps/cli/src/utils/auto-update.ts

@@ -12,6 +12,7 @@ export interface UpdateInfo {
 	currentVersion: string;
 	latestVersion: string;
 	needsUpdate: boolean;
+	highlights?: string[];
 }
 
 /**
@@ -59,6 +60,116 @@ export function compareVersions(v1: string, v2: string): number {
 	return a.pre < b.pre ? -1 : 1; // basic prerelease tie-break
 }
 
+/**
+ * Fetch CHANGELOG.md from GitHub and extract highlights for a specific version
+ */
+async function fetchChangelogHighlights(version: string): Promise<string[]> {
+	return new Promise((resolve) => {
+		const options = {
+			hostname: 'raw.githubusercontent.com',
+			path: '/eyaltoledano/claude-task-master/main/CHANGELOG.md',
+			method: 'GET',
+			headers: {
+				'User-Agent': `task-master-ai/${version}`
+			}
+		};
+
+		const req = https.request(options, (res) => {
+			let data = '';
+
+			res.on('data', (chunk) => {
+				data += chunk;
+			});
+
+			res.on('end', () => {
+				try {
+					if (res.statusCode !== 200) {
+						resolve([]);
+						return;
+					}
+
+					const highlights = parseChangelogHighlights(data, version);
+					resolve(highlights);
+				} catch (error) {
+					resolve([]);
+				}
+			});
+		});
+
+		req.on('error', () => {
+			resolve([]);
+		});
+
+		req.setTimeout(3000, () => {
+			req.destroy();
+			resolve([]);
+		});
+
+		req.end();
+	});
+}
+
+/**
+ * Parse changelog markdown to extract Minor Changes for a specific version
+ * @internal - Exported for testing purposes only
+ */
+export function parseChangelogHighlights(
+	changelog: string,
+	version: string
+): string[] {
+	try {
+		// Validate version format (basic semver pattern) to prevent ReDoS
+		if (!/^\d+\.\d+\.\d+(-[a-zA-Z0-9.-]+)?$/.test(version)) {
+			return [];
+		}
+
+		// Find the version section
+		const versionRegex = new RegExp(
+			`## ${version.replace(/\./g, '\\.')}\\s*\\n`,
+			'i'
+		);
+		const versionMatch = changelog.match(versionRegex);
+
+		if (!versionMatch) {
+			return [];
+		}
+
+		// Extract content from this version to the next version heading
+		const startIdx = versionMatch.index! + versionMatch[0].length;
+		const nextVersionIdx = changelog.indexOf('\n## ', startIdx);
+		const versionContent =
+			nextVersionIdx > 0
+				? changelog.slice(startIdx, nextVersionIdx)
+				: changelog.slice(startIdx);
+
+		// Find Minor Changes section
+		const minorChangesMatch = versionContent.match(
+			/### Minor Changes\s*\n([\s\S]*?)(?=\n###|\n##|$)/i
+		);
+
+		if (!minorChangesMatch) {
+			return [];
+		}
+
+		const minorChangesContent = minorChangesMatch[1];
+		const highlights: string[] = [];
+
+		// Extract all bullet points (lines starting with -)
+		// Format: - [#PR](...) Thanks [@author]! - Description
+		const bulletRegex = /^-\s+\[#\d+\][^\n]*?!\s+-\s+(.+?)$/gm;
+		let match;
+
+		while ((match = bulletRegex.exec(minorChangesContent)) !== null) {
+			const desc = match[1].trim();
+			highlights.push(desc);
+		}
+
+		return highlights;
+	} catch (error) {
+		return [];
+	}
+}
+
 /**
  * Check for newer version of task-master-ai
  */
@@ -85,7 +196,7 @@ export async function checkForUpdate(
 				data += chunk;
 			});
 
-			res.on('end', () => {
+			res.on('end', async () => {
 				try {
 					if (res.statusCode !== 200)
 						throw new Error(`npm registry status ${res.statusCode}`);
@@ -95,10 +206,17 @@ export async function checkForUpdate(
 					const needsUpdate =
 						compareVersions(currentVersion, latestVersion) < 0;
 
+					// Fetch highlights if update is needed
+					let highlights: string[] | undefined;
+					if (needsUpdate) {
+						highlights = await fetchChangelogHighlights(latestVersion);
+					}
+
 					resolve({
 						currentVersion,
 						latestVersion,
-						needsUpdate
+						needsUpdate,
+						highlights
 					});
 				} catch (error) {
 					resolve({
@@ -136,18 +254,29 @@ export async function checkForUpdate(
  */
 export function displayUpgradeNotification(
 	currentVersion: string,
-	latestVersion: string
+	latestVersion: string,
+	highlights?: string[]
 ) {
-	const message = boxen(
-		`${chalk.blue.bold('Update Available!')} ${chalk.dim(currentVersion)} → ${chalk.green(latestVersion)}\n\n` +
-			`Auto-updating to the latest version with new features and bug fixes...`,
-		{
+	let content = `${chalk.blue.bold('Update Available!')} ${chalk.dim(currentVersion)} → ${chalk.green(latestVersion)}`;
+
+	if (highlights && highlights.length > 0) {
+		content += '\n\n' + chalk.bold("What's New:");
+		for (const highlight of highlights) {
+			content += '\n' + chalk.cyan('• ') + highlight;
+		}
+		content += '\n\n' + 'Auto-updating to the latest version...';
+	} else {
+		content +=
+			'\n\n' +
+			'Auto-updating to the latest version with new features and bug fixes...';
+	}
+
+	const message = boxen(content, {
 		padding: 1,
 		margin: { top: 1, bottom: 1 },
 		borderColor: 'yellow',
 		borderStyle: 'round'
-		}
-	);
+	});
 
 	console.log(message);
 }

apps/docs/archive/cursor-setup.mdx

@@ -6,10 +6,28 @@ description: "Learn how to set up and use Task Master with Cursor AI"
 ## Setting up Cursor AI Integration
 
 <Check>
-  Task Master is designed to work seamlessly with [Cursor AI](https://www.cursor.so/), providing a structured workflow for AI-driven development.
+  Task Master is designed to work seamlessly with [Cursor AI](https://www.cursor.so/), providing a structured workflow for AI-driven development. As of version 0.28.0, Task Master automatically sets up custom slash commands in Cursor IDE.
 </Check>
 
 <AccordionGroup>
+  <Accordion title="Cursor Custom Slash Commands (New in 0.28.0)" icon="terminal">
+    Task Master now automatically configures custom slash commands in Cursor IDE when adding a profile. These commands provide quick access to Task Master functionality:
+
+    ### Available Slash Commands
+    - `/tm-list` - View all tasks with their status
+    - `/tm-next` - Get the next available task to work on  
+    - `/tm-show` - Show detailed task information
+    - `/tm-add` - Add a new task with AI assistance
+    - `/tm-status` - Set task status (pending, in-progress, done, etc.)
+    - `/tm-expand` - Expand a task into subtasks
+    - `/tm-complexity` - Analyze task complexity
+
+    ### Automatic Setup
+    When you run `task-master profiles add cursor`, the slash commands are automatically copied to `.cursor/commands/`. If you remove the profile with `task-master profiles remove cursor`, the commands are cleaned up automatically.
+
+    ### Manual Setup
+    If you need to manually set up the commands, they're available in the `assets/claude/commands/` directory of your Task Master installation.
+  </Accordion>
   <Accordion title="Using Cursor with MCP (Recommended)" icon="sparkles">
     If you've already set up Task Master with MCP in Cursor, the integration is automatic. You can simply use natural language to interact with Task Master:
 

apps/docs/capabilities/mcp.mdx

@@ -66,3 +66,36 @@ The MCP tools can be categorized in the same way as the core functionalities:
 -   **`use_tag`**: Switches to a different tag.
 -   **`rename_tag`**: Renames a tag.
 -   **`copy_tag`**: Copies a tag.
+
+## Configuration and Performance
+
+### Timeout Configuration
+
+As of version 0.28.0, Task Master automatically configures appropriate timeouts for MCP operations to handle long-running AI tasks. The Roo Code profile now includes a 300-second timeout (increased from the default 60 seconds) to accommodate complex operations like:
+
+- `parse_prd` - PRD parsing and task generation
+- `expand_all` - Expanding multiple tasks into subtasks
+- `analyze_project_complexity` - Project-wide complexity analysis
+- Research-enabled operations with the `--research` flag
+
+### MCP Server Configuration
+
+The recommended MCP server configuration automatically includes these timeout settings:
+
+```json
+{
+  "mcpServers": {
+    "task-master-ai": {
+      "command": "npx",
+      "args": ["-y", "task-master-ai"],
+      "timeout": 300000,
+      "env": {
+        "ANTHROPIC_API_KEY": "your-key-here",
+        "PERPLEXITY_API_KEY": "your-key-here"
+      }
+    }
+  }
+}
+```
+
+This configuration is automatically generated when using Task Master profiles with Roo Code and other AI coding assistants.

apps/docs/capabilities/rpg-method.mdx

@@ -0,0 +1,326 @@
+---
+title: RPG Method for PRD Creation
+sidebarTitle: "RPG Method"
+---
+
+# Repository Planning Graph (RPG) Method
+
+The RPG (Repository Planning Graph) method is an advanced approach to creating Product Requirements Documents that generate highly-structured, dependency-aware task graphs. It's based on Microsoft Research's methodology for scalable codebase generation.
+
+## When to Use RPG
+
+Use the RPG template (`example_prd_rpg.txt`) for:
+
+- **Complex multi-module systems** with intricate dependencies
+- **Large-scale codebases** being built from scratch
+- **Projects requiring explicit architecture** and clear module boundaries
+- **Teams needing dependency visibility** for parallel development
+
+For simpler features or smaller projects, the standard `example_prd.txt` template may be more appropriate.
+
+---
+
+## Core Principles
+
+### 1. Dual-Semantics
+
+Separate **functional** thinking (WHAT) from **structural** thinking (HOW):
+
+```
+Functional: "Data Validation capability with schema checking and rule enforcement"
+                    ↓
+Structural: "src/validation/ with schema-validator.js and rule-validator.js"
+```
+
+This separation prevents mixing concerns and creates clearer module boundaries.
+
+### 2. Explicit Dependencies
+
+Never assume dependencies - always state them explicitly:
+
+```
+Good:
+  Module: data-ingestion
+  Depends on: [schema-validator, config-manager]
+
+Bad:
+  Module: data-ingestion
+  (Assumes schema-validator exists somewhere)
+```
+
+Explicit dependencies enable:
+- Topological ordering of implementation
+- Parallel development of independent modules
+- Clear build/test order
+- Early detection of circular dependencies
+
+### 3. Topological Order
+
+Build foundation layers before higher layers:
+
+```
+Phase 0 (Foundation): error-handling, base-types, config
+                ↓
+Phase 1 (Data): validation, ingestion (depend on Phase 0)
+                ↓
+Phase 2 (Core): algorithms, pipelines (depend on Phase 1)
+                ↓
+Phase 3 (API): routes, handlers (depend on Phase 2)
+```
+
+Task Master automatically orders tasks based on this dependency chain.
+
+### 4. Progressive Refinement
+
+Start broad, refine iteratively:
+
+1. High-level capabilities → Main tasks
+2. Features per capability → Subtasks
+3. Implementation details → Expanded subtasks
+
+---
+
+## Template Structure
+
+The RPG template guides you through 7 key sections:
+
+### 1. Overview
+- Problem statement
+- Target users
+- Success metrics
+
+### 2. Functional Decomposition (WHAT)
+- High-level capability domains
+- Features per capability
+- Inputs/outputs/behavior for each feature
+
+**Example:**
+```
+Capability: Data Management
+  Feature: Schema validation
+    Description: Validate JSON against defined schemas
+    Inputs: JSON object, schema definition
+    Outputs: Validation result + error details
+    Behavior: Iterate fields, check types, enforce constraints
+```
+
+### 3. Structural Decomposition (HOW)
+- Repository folder structure
+- Module-to-capability mapping
+- File organization
+- Public interfaces/exports
+
+**Example:**
+```
+Capability: Data Management
+  → Maps to: src/data/
+    ├── schema-validator.js    (Schema validation feature)
+    ├── rule-validator.js      (Rule validation feature)
+    └── index.js               (Exports)
+```
+
+### 4. Dependency Graph (CRITICAL)
+- Foundation layer (no dependencies)
+- Each subsequent layer's dependencies
+- Explicit "depends on" declarations
+
+**Example:**
+```
+Foundation Layer (Phase 0):
+  - error-handling: No dependencies
+  - base-types: No dependencies
+
+Data Layer (Phase 1):
+  - schema-validator: Depends on [base-types, error-handling]
+  - data-ingestion: Depends on [schema-validator]
+```
+
+### 5. Implementation Roadmap
+- Phases with entry/exit criteria
+- Tasks grouped by phase
+- Clear deliverables per phase
+
+### 6. Test Strategy
+- Test pyramid ratios
+- Coverage requirements
+- Critical test scenarios per module
+- Guidelines for test generation
+
+### 7. Architecture & Risks
+- Technical architecture
+- Data models
+- Technology decisions
+- Risk mitigation strategies
+
+---
+
+## Using RPG with Task Master
+
+### Step 1: Create PRD with RPG Template
+
+Use a code-context-aware tool to fill out the template:
+
+```bash
+# In Claude Code, Cursor, or similar
+"Create a PRD using @.taskmaster/templates/example_prd_rpg.txt for [your project]"
+```
+
+**Why code context matters:** The AI needs to understand your existing codebase to make informed decisions about:
+- Module boundaries
+- Dependency relationships
+- Integration points
+- Naming conventions
+
+**Recommended tools:**
+- Claude Code (claude-code CLI)
+- Cursor/Windsurf
+- Gemini CLI (large contexts)
+- Codex/Grok CLI
+
+### Step 2: Parse PRD into Tasks
+
+```bash
+task-master parse-prd .taskmaster/docs/your-prd.txt --research
+```
+
+Task Master will:
+1. Extract capabilities → Main tasks
+2. Extract features → Subtasks
+3. Parse dependencies → Task dependencies
+4. Order by phases → Task priorities
+
+**Result:** A dependency-aware task graph ready for topological execution.
+
+### Step 3: Analyze Complexity
+
+```bash
+task-master analyze-complexity --research
+```
+
+Review the complexity report to identify tasks that need expansion.
+
+### Step 4: Expand Tasks
+
+```bash
+task-master expand --all --research
+```
+
+Break down complex tasks into manageable subtasks while preserving dependency chains.
+
+---
+
+## RPG Benefits
+
+### For Solo Developers
+- Clear roadmap for implementing complex features
+- Prevents architectural mistakes early
+- Explicit dependency tracking avoids integration issues
+- Enables resuming work after interruptions
+
+### For Teams
+- Parallel development of independent modules
+- Clear contracts between modules (explicit dependencies)
+- Reduced merge conflicts (proper module boundaries)
+- Onboarding aid (architectural overview in PRD)
+
+### For AI Agents
+- Structured context for code generation
+- Clear scope boundaries per task
+- Dependency awareness prevents incomplete implementations
+- Test strategy guidance for TDD workflows
+
+---
+
+## RPG vs Standard Template
+
+| Aspect | Standard Template | RPG Template |
+|--------|------------------|--------------|
+| **Best for** | Simple features | Complex systems |
+| **Dependency handling** | Implicit | Explicit graph |
+| **Structure guidance** | Minimal | Step-by-step |
+| **Examples** | Few | Inline good/bad examples |
+| **Module boundaries** | Vague | Precise mapping |
+| **Task ordering** | Manual | Automatic (topological) |
+| **Learning curve** | Low | Medium |
+| **Resulting task quality** | Good | Excellent |
+
+---
+
+## Tips for Best Results
+
+### 1. Spend Time on Dependencies
+The dependency graph section is the most valuable. List all dependencies explicitly, even if they seem obvious.
+
+### 2. Keep Features Atomic
+Each feature should be independently testable. If a feature description is vague ("handle data"), break it into specific features.
+
+### 3. Progressive Refinement
+Don't try to get everything perfect on the first pass:
+1. Fill out high-level sections
+2. Review and refine
+3. Add detail where needed
+4. Let `task-master expand` break down complex tasks further
+
+### 4. Use Research Mode
+```bash
+task-master parse-prd --research
+```
+The `--research` flag leverages AI to enhance task generation with domain knowledge.
+
+### 5. Validate Early
+```bash
+task-master validate-dependencies
+```
+Check for circular dependencies or orphaned modules before starting implementation.
+
+---
+
+## Common Pitfalls
+
+### ❌ Mixing Functional and Structural
+```
+Bad: "Capability: validation.js"
+Good: "Capability: Data Validation" → maps to "src/validation/"
+```
+
+### ❌ Vague Module Boundaries
+```
+Bad: "Module: utils"
+Good: "Module: string-utilities" with clear exports
+```
+
+### ❌ Implicit Dependencies
+```
+Bad: "Module: API handlers (needs validation)"
+Good: "Module: API handlers, Depends on: [validation, error-handling]"
+```
+
+### ❌ Skipping Test Strategy
+Without test strategy, the AI won't know what to test during implementation.
+
+---
+
+## Example Workflow
+
+1. **Discuss idea with AI**: Explain your project concept
+2. **Reference RPG template**: Show AI the `example_prd_rpg.txt`
+3. **Co-create PRD**: Work through each section with AI guidance
+4. **Save to docs**: Place in `.taskmaster/docs/your-project.txt`
+5. **Parse PRD**: `task-master parse-prd .taskmaster/docs/your-project.txt --research`
+6. **Analyze**: `task-master analyze-complexity --research`
+7. **Expand**: `task-master expand --all --research`
+8. **Start work**: `task-master next`
+
+---
+
+## Further Reading
+
+- [PRD Creation and Parsing Guide](/getting-started/quick-start/prd-quick)
+- [Task Structure Documentation](/capabilities/task-structure)
+- [Microsoft Research RPG Paper](https://arxiv.org/abs/2410.21376) (Original methodology)
+
+---
+
+<Tip>
+The RPG template includes inline `<instruction>` and `<example>` blocks that teach the method as you use it. Read these sections carefully - they provide valuable guidance at each decision point.
+</Tip>

apps/docs/getting-started/api-keys.mdx

@@ -42,6 +42,20 @@ PERPLEXITY_API_KEY="pplx-your-key-here"
 OPENAI_API_KEY="sk-proj-your-key-here"
 ```
 
+### OPENAI_CODEX_API_KEY (New)
+- **Provider**: Codex CLI (GPT-5 and GPT-5-Codex models)
+- **Format**: Various formats
+- **Required**: ❌ **No** (OAuth-first authentication via `codex login`)
+- **Models**: GPT-5, GPT-5-Codex (272K input / 128K output context)
+- **Authentication**: Primary authentication is OAuth via `codex login` command
+- **Features**: Codebase analysis capabilities automatically enabled
+- **Get Access**: Follow Codex CLI setup instructions
+
+```bash
+# Optional - OAuth via 'codex login' is preferred
+OPENAI_CODEX_API_KEY="your-codex-api-key-here"
+```
+
 ### GOOGLE_API_KEY
 - **Provider**: Google Gemini models
 - **Format**: Various formats
@@ -197,16 +211,20 @@ For Claude Code integration, configure keys in `.mcp.json`:
     "task-master-ai": {
       "command": "npx",
       "args": ["-y", "task-master-ai"],
+      "timeout": 300000,
       "env": {
         "ANTHROPIC_API_KEY": "your-key-here",
         "PERPLEXITY_API_KEY": "your-key-here",
-        "OPENAI_API_KEY": "your-key-here"
+        "OPENAI_API_KEY": "your-key-here",
+        "OPENAI_CODEX_API_KEY": "your-codex-key-here"
       }
     }
   }
 }
 ```
 
+**Note**: The `timeout: 300000` (300 seconds) setting is recommended for long-running AI operations like PRD parsing and complexity analysis.
+
 ## Key Requirements
 
 ### Minimum Requirements

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

@@ -32,7 +32,11 @@ The more context you give the model, the better the breakdown and results.
 
 ## Writing a PRD for Task Master
 
-<Note>An example PRD can be found in .taskmaster/templates/example_prd.txt</Note>
+<Note>
+Two example PRD templates are available in `.taskmaster/templates/`:
+- `example_prd.txt` - Simple template for straightforward projects
+- `example_prd_rpg.txt` - Advanced RPG (Repository Planning Graph) template for complex projects with dependencies
+</Note>
 
 
 You can co-write your PRD with an LLM model using the following workflow:
@@ -43,6 +47,29 @@ You can co-write your PRD with an LLM model using the following workflow:
 
 This approach works great in Cursor, or anywhere you use a chat-based LLM.
 
+### Choosing Between Templates
+
+**Use `example_prd.txt` when:**
+- Building straightforward features
+- Working on smaller projects
+- Dependencies are simple and obvious
+
+**Use `example_prd_rpg.txt` when:**
+- Building complex systems with multiple modules
+- Need explicit dependency management
+- Want structured guidance on architecture decisions
+- Planning a large codebase from scratch
+
+The RPG template teaches you to think about:
+1. **Functional decomposition** (WHAT the system does)
+2. **Structural decomposition** (HOW it's organized in code)
+3. **Explicit dependencies** (WHAT depends on WHAT)
+4. **Topological ordering** (build foundation first, then layers)
+
+<Tip>
+For complex projects, using the RPG template with a code-context-aware ai agent produces the best results because the AI can understand your existing codebase structure. [Learn more about the RPG method →](/capabilities/rpg-method)
+</Tip>
+
 ---
 
 ## Where to Save Your PRD

apps/docs/whats-new.mdx

@@ -3,4 +3,58 @@ title: "What's New"
 sidebarTitle: "What's New"
 ---
 
-An easy way to see the latest releases
+# What's New in Task Master
+
+## Version 0.28.0 - Latest Release
+
+### 🚀 New Features
+
+#### Codex CLI Provider Support
+- Added support for GPT-5 and GPT-5-Codex models via Codex CLI
+- OAuth-first authentication - no API key required (just run `codex login`)
+- 272K input / 128K output context windows
+- Codebase analysis capabilities automatically enabled
+- Optional `OPENAI_CODEX_API_KEY` support for API-based usage
+
+#### Cursor IDE Slash Commands
+- Automatically installs custom slash commands when adding Cursor profile
+- Quick access to Task Master functionality directly in Cursor IDE
+- Commands include `/tm-list`, `/tm-next`, `/tm-show`, `/tm-add`, and more
+- Automatic cleanup when removing Cursor profile
+
+#### Enhanced MCP Configuration
+- Improved timeout configuration for long-running AI operations
+- 300-second timeout for complex tasks like PRD parsing and task expansion
+- Programmatic MCP configuration generation for better reliability
+- Enhanced support for Roo Code and other AI coding assistants
+
+### 🔧 Technical Improvements
+
+#### AI SDK v5 Migration
+- Migrated to AI SDK v5 for better compatibility with modern AI providers
+- Improved support for Claude Code and Gemini CLI integration
+- Better structured output generation with `generateObject`
+- Enhanced JSON mode support for supported providers
+
+#### Structured Data Generation
+- All AI services now use `generateObject` for more reliable responses
+- Integrated Zod schemas for automatic validation
+- Reduced parsing errors and improved data consistency
+- Better subtask ID generation (fixes numbering inconsistencies)
+
+### 🐛 Bug Fixes
+- Fixed MCP connection errors from deprecated function calls
+- Fixed MCP server errors when file parameters not provided
+- Corrected complexity scores display in `task-master show` and `list`
+- Fixed Perplexity Sonar Deep Research model naming
+- Improved parent task status handling when all subtasks are pending
+
+### 📖 Documentation Updates
+- New comprehensive API keys configuration guide
+- Enhanced Cursor IDE integration documentation  
+- Improved MCP timeout configuration documentation
+- Updated examples and configuration snippets
+
+---
+
+For detailed release notes and full changelog, visit our [GitHub releases page](https://github.com/eyaltoledano/claude-task-master/releases).

assets/example_prd_rpg.txt

@@ -0,0 +1,511 @@
+<rpg-method>
+# Repository Planning Graph (RPG) Method - PRD Template
+
+This template teaches you (AI or human) how to create structured, dependency-aware PRDs using the RPG methodology from Microsoft Research. The key insight: separate WHAT (functional) from HOW (structural), then connect them with explicit dependencies.
+
+## Core Principles
+
+1. **Dual-Semantics**: Think functional (capabilities) AND structural (code organization) separately, then map them
+2. **Explicit Dependencies**: Never assume - always state what depends on what
+3. **Topological Order**: Build foundation first, then layers on top
+4. **Progressive Refinement**: Start broad, refine iteratively
+
+## How to Use This Template
+
+- Follow the instructions in each `<instruction>` block
+- Look at `<example>` blocks to see good vs bad patterns
+- Fill in the content sections with your project details
+- The AI reading this will learn the RPG method by following along
+- Task Master will parse the resulting PRD into dependency-aware tasks
+
+## Recommended Tools for Creating PRDs
+
+When using this template to **create** a PRD (not parse it), use **code-context-aware AI assistants** for best results:
+
+**Why?** The AI needs to understand your existing codebase to make good architectural decisions about modules, dependencies, and integration points.
+
+**Recommended tools:**
+- **Claude Code** (claude-code CLI) - Best for structured reasoning and large contexts
+- **Cursor/Windsurf** - IDE integration with full codebase context
+- **Gemini CLI** (gemini-cli) - Massive context window for large codebases
+- **Codex/Grok CLI** - Strong code generation with context awareness
+
+**Note:** Once your PRD is created, `task-master parse-prd` works with any configured AI model - it just needs to read the PRD text itself, not your codebase.
+</rpg-method>
+
+---
+
+<overview>
+<instruction>
+Start with the problem, not the solution. Be specific about:
+- What pain point exists?
+- Who experiences it?
+- Why existing solutions don't work?
+- What success looks like (measurable outcomes)?
+
+Keep this section focused - don't jump into implementation details yet.
+</instruction>
+
+## Problem Statement
+[Describe the core problem. Be concrete about user pain points.]
+
+## Target Users
+[Define personas, their workflows, and what they're trying to achieve.]
+
+## Success Metrics
+[Quantifiable outcomes. Examples: "80% task completion via autopilot", "< 5% manual intervention rate"]
+
+</overview>
+
+---
+
+<functional-decomposition>
+<instruction>
+Now think about CAPABILITIES (what the system DOES), not code structure yet.
+
+Step 1: Identify high-level capability domains
+- Think: "What major things does this system do?"
+- Examples: Data Management, Core Processing, Presentation Layer
+
+Step 2: For each capability, enumerate specific features
+- Use explore-exploit strategy:
+  * Exploit: What features are REQUIRED for core value?
+  * Explore: What features make this domain COMPLETE?
+
+Step 3: For each feature, define:
+- Description: What it does in one sentence
+- Inputs: What data/context it needs
+- Outputs: What it produces/returns
+- Behavior: Key logic or transformations
+
+<example type="good">
+Capability: Data Validation
+  Feature: Schema validation
+    - Description: Validate JSON payloads against defined schemas
+    - Inputs: JSON object, schema definition
+    - Outputs: Validation result (pass/fail) + error details
+    - Behavior: Iterate fields, check types, enforce constraints
+
+  Feature: Business rule validation
+    - Description: Apply domain-specific validation rules
+    - Inputs: Validated data object, rule set
+    - Outputs: Boolean + list of violated rules
+    - Behavior: Execute rules sequentially, short-circuit on failure
+</example>
+
+<example type="bad">
+Capability: validation.js
+  (Problem: This is a FILE, not a CAPABILITY. Mixing structure into functional thinking.)
+
+Capability: Validation
+  Feature: Make sure data is good
+  (Problem: Too vague. No inputs/outputs. Not actionable.)
+</example>
+</instruction>
+
+## Capability Tree
+
+### Capability: [Name]
+[Brief description of what this capability domain covers]
+
+#### Feature: [Name]
+- **Description**: [One sentence]
+- **Inputs**: [What it needs]
+- **Outputs**: [What it produces]
+- **Behavior**: [Key logic]
+
+#### Feature: [Name]
+- **Description**:
+- **Inputs**:
+- **Outputs**:
+- **Behavior**:
+
+### Capability: [Name]
+...
+
+</functional-decomposition>
+
+---
+
+<structural-decomposition>
+<instruction>
+NOW think about code organization. Map capabilities to actual file/folder structure.
+
+Rules:
+1. Each capability maps to a module (folder or file)
+2. Features within a capability map to functions/classes
+3. Use clear module boundaries - each module has ONE responsibility
+4. Define what each module exports (public interface)
+
+The goal: Create a clear mapping between "what it does" (functional) and "where it lives" (structural).
+
+<example type="good">
+Capability: Data Validation
+  → Maps to: src/validation/
+    ├── schema-validator.js      (Schema validation feature)
+    ├── rule-validator.js         (Business rule validation feature)
+    └── index.js                  (Public exports)
+
+Exports:
+  - validateSchema(data, schema)
+  - validateRules(data, rules)
+</example>
+
+<example type="bad">
+Capability: Data Validation
+  → Maps to: src/utils.js
+  (Problem: "utils" is not a clear module boundary. Where do I find validation logic?)
+
+Capability: Data Validation
+  → Maps to: src/validation/everything.js
+  (Problem: One giant file. Features should map to separate files for maintainability.)
+</example>
+</instruction>
+
+## Repository Structure
+
+```
+project-root/
+├── src/
+│   ├── [module-name]/       # Maps to: [Capability Name]
+│   │   ├── [file].js        # Maps to: [Feature Name]
+│   │   └── index.js         # Public exports
+│   └── [module-name]/
+├── tests/
+└── docs/
+```
+
+## Module Definitions
+
+### Module: [Name]
+- **Maps to capability**: [Capability from functional decomposition]
+- **Responsibility**: [Single clear purpose]
+- **File structure**:
+  ```
+  module-name/
+  ├── feature1.js
+  ├── feature2.js
+  └── index.js
+  ```
+- **Exports**:
+  - `functionName()` - [what it does]
+  - `ClassName` - [what it does]
+
+</structural-decomposition>
+
+---
+
+<dependency-graph>
+<instruction>
+This is THE CRITICAL SECTION for Task Master parsing.
+
+Define explicit dependencies between modules. This creates the topological order for task execution.
+
+Rules:
+1. List modules in dependency order (foundation first)
+2. For each module, state what it depends on
+3. Foundation modules should have NO dependencies
+4. Every non-foundation module should depend on at least one other module
+5. Think: "What must EXIST before I can build this module?"
+
+<example type="good">
+Foundation Layer (no dependencies):
+  - error-handling: No dependencies
+  - config-manager: No dependencies
+  - base-types: No dependencies
+
+Data Layer:
+  - schema-validator: Depends on [base-types, error-handling]
+  - data-ingestion: Depends on [schema-validator, config-manager]
+
+Core Layer:
+  - algorithm-engine: Depends on [base-types, error-handling]
+  - pipeline-orchestrator: Depends on [algorithm-engine, data-ingestion]
+</example>
+
+<example type="bad">
+- validation: Depends on API
+- API: Depends on validation
+(Problem: Circular dependency. This will cause build/runtime issues.)
+
+- user-auth: Depends on everything
+(Problem: Too many dependencies. Should be more focused.)
+</example>
+</instruction>
+
+## Dependency Chain
+
+### Foundation Layer (Phase 0)
+No dependencies - these are built first.
+
+- **[Module Name]**: [What it provides]
+- **[Module Name]**: [What it provides]
+
+### [Layer Name] (Phase 1)
+- **[Module Name]**: Depends on [[module-from-phase-0], [module-from-phase-0]]
+- **[Module Name]**: Depends on [[module-from-phase-0]]
+
+### [Layer Name] (Phase 2)
+- **[Module Name]**: Depends on [[module-from-phase-1], [module-from-foundation]]
+
+[Continue building up layers...]
+
+</dependency-graph>
+
+---
+
+<implementation-roadmap>
+<instruction>
+Turn the dependency graph into concrete development phases.
+
+Each phase should:
+1. Have clear entry criteria (what must exist before starting)
+2. Contain tasks that can be parallelized (no inter-dependencies within phase)
+3. Have clear exit criteria (how do we know phase is complete?)
+4. Build toward something USABLE (not just infrastructure)
+
+Phase ordering follows topological sort of dependency graph.
+
+<example type="good">
+Phase 0: Foundation
+  Entry: Clean repository
+  Tasks:
+    - Implement error handling utilities
+    - Create base type definitions
+    - Setup configuration system
+  Exit: Other modules can import foundation without errors
+
+Phase 1: Data Layer
+  Entry: Phase 0 complete
+  Tasks:
+    - Implement schema validator (uses: base types, error handling)
+    - Build data ingestion pipeline (uses: validator, config)
+  Exit: End-to-end data flow from input to validated output
+</example>
+
+<example type="bad">
+Phase 1: Build Everything
+  Tasks:
+    - API
+    - Database
+    - UI
+    - Tests
+  (Problem: No clear focus. Too broad. Dependencies not considered.)
+</example>
+</instruction>
+
+## Development Phases
+
+### Phase 0: [Foundation Name]
+**Goal**: [What foundational capability this establishes]
+
+**Entry Criteria**: [What must be true before starting]
+
+**Tasks**:
+- [ ] [Task name] (depends on: [none or list])
+  - Acceptance criteria: [How we know it's done]
+  - Test strategy: [What tests prove it works]
+
+- [ ] [Task name] (depends on: [none or list])
+
+**Exit Criteria**: [Observable outcome that proves phase complete]
+
+**Delivers**: [What can users/developers do after this phase?]
+
+---
+
+### Phase 1: [Layer Name]
+**Goal**:
+
+**Entry Criteria**: Phase 0 complete
+
+**Tasks**:
+- [ ] [Task name] (depends on: [[tasks-from-phase-0]])
+- [ ] [Task name] (depends on: [[tasks-from-phase-0]])
+
+**Exit Criteria**:
+
+**Delivers**:
+
+---
+
+[Continue with more phases...]
+
+</implementation-roadmap>
+
+---
+
+<test-strategy>
+<instruction>
+Define how testing will be integrated throughout development (TDD approach).
+
+Specify:
+1. Test pyramid ratios (unit vs integration vs e2e)
+2. Coverage requirements
+3. Critical test scenarios
+4. Test generation guidelines for Surgical Test Generator
+
+This section guides the AI when generating tests during the RED phase of TDD.
+
+<example type="good">
+Critical Test Scenarios for Data Validation module:
+  - Happy path: Valid data passes all checks
+  - Edge cases: Empty strings, null values, boundary numbers
+  - Error cases: Invalid types, missing required fields
+  - Integration: Validator works with ingestion pipeline
+</example>
+</instruction>
+
+## Test Pyramid
+
+```
+        /\
+       /E2E\       ← [X]% (End-to-end, slow, comprehensive)
+      /------\
+     /Integration\ ← [Y]% (Module interactions)
+    /------------\
+   /  Unit Tests  \ ← [Z]% (Fast, isolated, deterministic)
+  /----------------\
+```
+
+## Coverage Requirements
+- Line coverage: [X]% minimum
+- Branch coverage: [X]% minimum
+- Function coverage: [X]% minimum
+- Statement coverage: [X]% minimum
+
+## Critical Test Scenarios
+
+### [Module/Feature Name]
+**Happy path**:
+- [Scenario description]
+- Expected: [What should happen]
+
+**Edge cases**:
+- [Scenario description]
+- Expected: [What should happen]
+
+**Error cases**:
+- [Scenario description]
+- Expected: [How system handles failure]
+
+**Integration points**:
+- [What interactions to test]
+- Expected: [End-to-end behavior]
+
+## Test Generation Guidelines
+[Specific instructions for Surgical Test Generator about what to focus on, what patterns to follow, project-specific test conventions]
+
+</test-strategy>
+
+---
+
+<architecture>
+<instruction>
+Describe technical architecture, data models, and key design decisions.
+
+Keep this section AFTER functional/structural decomposition - implementation details come after understanding structure.
+</instruction>
+
+## System Components
+[Major architectural pieces and their responsibilities]
+
+## Data Models
+[Core data structures, schemas, database design]
+
+## Technology Stack
+[Languages, frameworks, key libraries]
+
+**Decision: [Technology/Pattern]**
+- **Rationale**: [Why chosen]
+- **Trade-offs**: [What we're giving up]
+- **Alternatives considered**: [What else we looked at]
+
+</architecture>
+
+---
+
+<risks>
+<instruction>
+Identify risks that could derail development and how to mitigate them.
+
+Categories:
+- Technical risks (complexity, unknowns)
+- Dependency risks (blocking issues)
+- Scope risks (creep, underestimation)
+</instruction>
+
+## Technical Risks
+**Risk**: [Description]
+- **Impact**: [High/Medium/Low - effect on project]
+- **Likelihood**: [High/Medium/Low]
+- **Mitigation**: [How to address]
+- **Fallback**: [Plan B if mitigation fails]
+
+## Dependency Risks
+[External dependencies, blocking issues]
+
+## Scope Risks
+[Scope creep, underestimation, unclear requirements]
+
+</risks>
+
+---
+
+<appendix>
+## References
+[Papers, documentation, similar systems]
+
+## Glossary
+[Domain-specific terms]
+
+## Open Questions
+[Things to resolve during development]
+</appendix>
+
+---
+
+<task-master-integration>
+# How Task Master Uses This PRD
+
+When you run `task-master parse-prd <file>.txt`, the parser:
+
+1. **Extracts capabilities** → Main tasks
+   - Each `### Capability:` becomes a top-level task
+
+2. **Extracts features** → Subtasks
+   - Each `#### Feature:` becomes a subtask under its capability
+
+3. **Parses dependencies** → Task dependencies
+   - `Depends on: [X, Y]` sets task.dependencies = ["X", "Y"]
+
+4. **Orders by phases** → Task priorities
+   - Phase 0 tasks = highest priority
+   - Phase N tasks = lower priority, properly sequenced
+
+5. **Uses test strategy** → Test generation context
+   - Feeds test scenarios to Surgical Test Generator during implementation
+
+**Result**: A dependency-aware task graph that can be executed in topological order.
+
+## Why RPG Structure Matters
+
+Traditional flat PRDs lead to:
+- ❌ Unclear task dependencies
+- ❌ Arbitrary task ordering
+- ❌ Circular dependencies discovered late
+- ❌ Poorly scoped tasks
+
+RPG-structured PRDs provide:
+- ✅ Explicit dependency chains
+- ✅ Topological execution order
+- ✅ Clear module boundaries
+- ✅ Validated task graph before implementation
+
+## Tips for Best Results
+
+1. **Spend time on dependency graph** - This is the most valuable section for Task Master
+2. **Keep features atomic** - Each feature should be independently testable
+3. **Progressive refinement** - Start broad, use `task-master expand` to break down complex tasks
+4. **Use research mode** - `task-master parse-prd --research` leverages AI for better task generation
+</task-master-integration>

package.json

@@ -118,7 +118,13 @@
 	"bugs": {
 		"url": "https://github.com/eyaltoledano/claude-task-master/issues"
 	},
-	"files": ["dist/**", "README-task-master.md", "README.md", "LICENSE"],
+	"files": [
+		"dist/**",
+		"README-task-master.md",
+		"README.md",
+		"LICENSE",
+		"CHANGELOG.md"
+	],
 	"overrides": {
 		"node-fetch": "^2.6.12",
 		"whatwg-url": "^11.0.0"

scripts/init.js

@@ -628,6 +628,12 @@ function createProjectStructure(
 	// Copy example_prd.txt to NEW location
 	copyTemplateFile('example_prd.txt', path.join(targetDir, EXAMPLE_PRD_FILE));
 
+	// Copy example_prd_rpg.txt to templates directory
+	copyTemplateFile(
+		'example_prd_rpg.txt',
+		path.join(targetDir, TASKMASTER_TEMPLATES_DIR, 'example_prd_rpg.txt')
+	);
+
 	// Initialize git repository if git is available
 	try {
 		if (initGit === false) {
@@ -856,10 +862,10 @@ function createProjectStructure(
 				)}\n${chalk.white('   ├─ ')}${chalk.dim('Models: Use `task-master models` commands')}\n${chalk.white('   └─ ')}${chalk.dim(
 					'Keys: Add provider API keys to .env (or inside the MCP config file i.e. .cursor/mcp.json)'
 				)}\n${chalk.white('2. ')}${chalk.yellow(
-					'Discuss your idea with AI and ask for a PRD using example_prd.txt, and save it to scripts/PRD.txt'
-				)}\n${chalk.white('3. ')}${chalk.yellow(
+					'Discuss your idea with AI and ask for a PRD, and save it to .taskmaster/docs/prd.txt'
+				)}\n${chalk.white('   ├─ ')}${chalk.dim('Simple projects: Use ')}${chalk.cyan('example_prd.txt')}${chalk.dim(' template')}\n${chalk.white('   └─ ')}${chalk.dim('Complex systems: Use ')}${chalk.cyan('example_prd_rpg.txt')}${chalk.dim(' template (for dependency-aware task graphs)')}\n${chalk.white('3. ')}${chalk.yellow(
 					'Ask Cursor Agent (or run CLI) to parse your PRD and generate initial tasks:'
-				)}\n${chalk.white('   └─ ')}${chalk.dim('MCP Tool: ')}${chalk.cyan('parse_prd')}${chalk.dim(' | CLI: ')}${chalk.cyan('task-master parse-prd scripts/prd.txt')}\n${chalk.white('4. ')}${chalk.yellow(
+				)}\n${chalk.white('   └─ ')}${chalk.dim('MCP Tool: ')}${chalk.cyan('parse_prd')}${chalk.dim(' | CLI: ')}${chalk.cyan('task-master parse-prd .taskmaster/docs/prd.txt')}\n${chalk.white('4. ')}${chalk.yellow(
 					'Ask Cursor to analyze the complexity of the tasks in your PRD using research'
 				)}\n${chalk.white('   └─ ')}${chalk.dim('MCP Tool: ')}${chalk.cyan('analyze_project_complexity')}${chalk.dim(' | CLI: ')}${chalk.cyan('task-master analyze-complexity')}\n${chalk.white('5. ')}${chalk.yellow(
 					'Ask Cursor to expand all of your tasks using the complexity analysis'

scripts/modules/commands.js

@@ -5111,7 +5111,8 @@ async function runCLI(argv = process.argv) {
 			// Display the upgrade notification first
 			displayUpgradeNotification(
 				updateInfo.currentVersion,
-				updateInfo.latestVersion
+				updateInfo.latestVersion,
+				updateInfo.highlights
 			);
 
 			// Then automatically perform the update

scripts/modules/dependency-manager.js

@@ -312,18 +312,23 @@ async function removeDependency(tasksPath, taskId, dependencyId, context = {}) {
 
 	// Check if the dependency exists by comparing string representations
 	const dependencyIndex = targetTask.dependencies.findIndex((dep) => {
-		// Convert both to strings for comparison
-		let depStr = String(dep);
-
-		// Special handling for numeric IDs that might be subtask references
-		if (typeof dep === 'number' && dep < 100 && isSubtask) {
-			// It's likely a reference to another subtask in the same parent task
-			// Convert to full format for comparison (e.g., 2 -> "1.2" for a subtask in task 1)
-			const [parentId] = formattedTaskId.split('.');
-			depStr = `${parentId}.${dep}`;
+		// Direct string comparison (handles both numeric IDs and dot notation)
+		const depStr = String(dep);
+		if (depStr === normalizedDependencyId) {
+			return true;
 		}
 
-		return depStr === normalizedDependencyId;
+		// For subtasks: handle numeric dependencies that might be references to other subtasks
+		// in the same parent (e.g., subtask 1.2 depending on subtask 1.1 stored as just "1")
+		if (typeof dep === 'number' && dep < 100 && isSubtask) {
+			const [parentId] = formattedTaskId.split('.');
+			const fullSubtaskRef = `${parentId}.${dep}`;
+			if (fullSubtaskRef === normalizedDependencyId) {
+				return true;
+			}
+		}
+
+		return false;
 	});
 
 	if (dependencyIndex === -1) {
@@ -396,8 +401,9 @@ function isCircularDependency(tasks, taskId, chain = []) {
 			task = parentTask.subtasks.find((st) => st.id === subtaskId);
 		}
 	} else {
-		// Regular task
-		task = tasks.find((t) => String(t.id) === taskIdStr);
+		// Regular task - handle both string and numeric task IDs
+		const taskIdNum = parseInt(taskIdStr, 10);
+		task = tasks.find((t) => t.id === taskIdNum || String(t.id) === taskIdStr);
 	}
 
 	if (!task) {

tests/fixture/test-tasks.json

@@ -1,14 +0,0 @@
-{
-  "tasks": [
-    {
-      "id": 1,
-      "dependencies": [],
-      "subtasks": [
-        {
-          "id": 1,
-          "dependencies": []
-        }
-      ]
-    }
-  ]
-}

tests/fixtures/sample-tasks.js

@@ -88,3 +88,38 @@ export const emptySampleTasks = {
 	},
 	tasks: []
 };
+
+export const crossLevelDependencyTasks = {
+	tasks: [
+		{
+			id: 2,
+			title: 'Task 2 with subtasks',
+			description: 'Parent task',
+			status: 'pending',
+			dependencies: [],
+			subtasks: [
+				{
+					id: 1,
+					title: 'Subtask 2.1',
+					description: 'First subtask',
+					status: 'pending',
+					dependencies: []
+				},
+				{
+					id: 2,
+					title: 'Subtask 2.2',
+					description: 'Second subtask that should depend on Task 11',
+					status: 'pending',
+					dependencies: []
+				}
+			]
+		},
+		{
+			id: 11,
+			title: 'Task 11',
+			description: 'Top-level task that 2.2 should depend on',
+			status: 'done',
+			dependencies: []
+		}
+	]
+};

tests/unit/commands.test.js

@@ -279,12 +279,14 @@ describe('Version comparison utility', () => {
 
 describe('Update check functionality', () => {
 	let displayUpgradeNotification;
+	let parseChangelogHighlights;
 	let consoleLogSpy;
 
 	beforeAll(async () => {
 		// Import from @tm/cli instead of commands.js
 		const cliModule = await import('../../apps/cli/src/utils/auto-update.js');
 		displayUpgradeNotification = cliModule.displayUpgradeNotification;
+		parseChangelogHighlights = cliModule.parseChangelogHighlights;
 	});
 
 	beforeEach(() => {
@@ -302,6 +304,61 @@ describe('Update check functionality', () => {
 		expect(consoleLogSpy.mock.calls[0][0]).toContain('1.0.0');
 		expect(consoleLogSpy.mock.calls[0][0]).toContain('1.1.0');
 	});
+
+	test('displays upgrade notification with highlights when provided', () => {
+		const highlights = [
+			'Add Codex CLI provider with OAuth authentication',
+			'Cursor IDE custom slash command support',
+			'Move to AI SDK v5'
+		];
+		displayUpgradeNotification('1.0.0', '1.1.0', highlights);
+		expect(consoleLogSpy).toHaveBeenCalled();
+		const output = consoleLogSpy.mock.calls[0][0];
+		expect(output).toContain('Update Available!');
+		expect(output).toContain('1.0.0');
+		expect(output).toContain('1.1.0');
+		expect(output).toContain("What's New:");
+		expect(output).toContain(
+			'Add Codex CLI provider with OAuth authentication'
+		);
+		expect(output).toContain('Cursor IDE custom slash command support');
+		expect(output).toContain('Move to AI SDK v5');
+	});
+
+	test('displays upgrade notification without highlights section when empty array', () => {
+		displayUpgradeNotification('1.0.0', '1.1.0', []);
+		expect(consoleLogSpy).toHaveBeenCalled();
+		const output = consoleLogSpy.mock.calls[0][0];
+		expect(output).toContain('Update Available!');
+		expect(output).not.toContain("What's New:");
+		expect(output).toContain(
+			'Auto-updating to the latest version with new features and bug fixes'
+		);
+	});
+
+	test('parseChangelogHighlights validates version format to prevent ReDoS', () => {
+		const mockChangelog = `
+## 1.0.0
+
+### Minor Changes
+
+- [#123](https://example.com) Thanks [@user](https://example.com)! - Test feature
+		`;
+
+		// Valid versions should work
+		expect(parseChangelogHighlights(mockChangelog, '1.0.0')).toEqual([
+			'Test feature'
+		]);
+		expect(parseChangelogHighlights(mockChangelog, '1.0.0-rc.1')).toEqual([]);
+
+		// Invalid versions should return empty array (ReDoS protection)
+		expect(parseChangelogHighlights(mockChangelog, 'invalid')).toEqual([]);
+		expect(parseChangelogHighlights(mockChangelog, '1.0')).toEqual([]);
+		expect(parseChangelogHighlights(mockChangelog, 'a.b.c')).toEqual([]);
+		expect(
+			parseChangelogHighlights(mockChangelog, '((((((((((((((((((((((((((((((a')
+		).toEqual([]);
+	});
 });
 
 // -----------------------------------------------------------------------------

tests/unit/dependency-manager.test.js

@@ -4,18 +4,47 @@
 
 import { jest } from '@jest/globals';
 import {
-	validateTaskDependencies,
-	isCircularDependency,
-	removeDuplicateDependencies,
-	cleanupSubtaskDependencies,
-	ensureAtLeastOneIndependentSubtask,
-	validateAndFixDependencies,
-	canMoveWithDependencies
-} from '../../scripts/modules/dependency-manager.js';
-import * as utils from '../../scripts/modules/utils.js';
-import { sampleTasks } from '../fixtures/sample-tasks.js';
+	sampleTasks,
+	crossLevelDependencyTasks
+} from '../fixtures/sample-tasks.js';
+
+// Create mock functions that we can control in tests
+const mockTaskExists = jest.fn();
+const mockFormatTaskId = jest.fn();
+const mockFindCycles = jest.fn();
+const mockLog = jest.fn();
+const mockReadJSON = jest.fn();
+const mockWriteJSON = jest.fn();
+
+// Mock the utils module using the same pattern as move-task-cross-tag.test.js
+jest.mock('../../scripts/modules/utils.js', () => ({
+	log: mockLog,
+	readJSON: mockReadJSON,
+	writeJSON: mockWriteJSON,
+	taskExists: mockTaskExists,
+	formatTaskId: mockFormatTaskId,
+	findCycles: mockFindCycles,
+	traverseDependencies: jest.fn(() => []),
+	isSilentMode: jest.fn(() => true),
+	findProjectRoot: jest.fn(() => '/test'),
+	resolveEnvVariable: jest.fn(() => undefined),
+	isEmpty: jest.fn((v) =>
+		v == null
+			? true
+			: Array.isArray(v)
+				? v.length === 0
+				: typeof v === 'object'
+					? Object.keys(v).length === 0
+					: false
+	),
+	// Common extras
+	enableSilentMode: jest.fn(),
+	disableSilentMode: jest.fn(),
+	getTaskManager: jest.fn(async () => ({})),
+	getTagAwareFilePath: jest.fn((basePath, _tag, projectRoot = '.') => basePath),
+	readComplexityReport: jest.fn(() => null)
+}));
 
-// Mock dependencies
 jest.mock('path');
 jest.mock('chalk', () => ({
 	green: jest.fn((text) => `<green>${text}</green>`),
@@ -27,22 +56,16 @@ jest.mock('chalk', () => ({
 
 jest.mock('boxen', () => jest.fn((text) => `[boxed: ${text}]`));
 
-// Mock utils module
-const mockTaskExists = jest.fn();
-const mockFormatTaskId = jest.fn();
-const mockFindCycles = jest.fn();
-const mockLog = jest.fn();
-const mockReadJSON = jest.fn();
-const mockWriteJSON = jest.fn();
-
-jest.mock('../../scripts/modules/utils.js', () => ({
-	log: mockLog,
-	readJSON: mockReadJSON,
-	writeJSON: mockWriteJSON,
-	taskExists: mockTaskExists,
-	formatTaskId: mockFormatTaskId,
-	findCycles: mockFindCycles
-}));
+// Now import SUT after mocks are in place
+import {
+	validateTaskDependencies,
+	isCircularDependency,
+	removeDuplicateDependencies,
+	cleanupSubtaskDependencies,
+	ensureAtLeastOneIndependentSubtask,
+	validateAndFixDependencies,
+	canMoveWithDependencies
+} from '../../scripts/modules/dependency-manager.js';
 
 jest.mock('../../scripts/modules/ui.js', () => ({
 	displayBanner: jest.fn()
@@ -52,8 +75,8 @@ jest.mock('../../scripts/modules/task-manager.js', () => ({
 	generateTaskFiles: jest.fn()
 }));
 
-// Create a path for test files
-const TEST_TASKS_PATH = 'tests/fixture/test-tasks.json';
+// Use a temporary path for test files - Jest will clean up the temp directory
+const TEST_TASKS_PATH = '/tmp/jest-test-tasks.json';
 
 describe('Dependency Manager Module', () => {
 	beforeEach(() => {
@@ -684,6 +707,8 @@ describe('Dependency Manager Module', () => {
 			// IMPORTANT: Verify no calls to writeJSON with actual tasks.json
 			expect(mockWriteJSON).not.toHaveBeenCalledWith(
 				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
 				expect.anything()
 			);
 		});
@@ -737,6 +762,8 @@ describe('Dependency Manager Module', () => {
 			// IMPORTANT: Verify no calls to writeJSON with actual tasks.json
 			expect(mockWriteJSON).not.toHaveBeenCalledWith(
 				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
 				expect.anything()
 			);
 		});
@@ -750,6 +777,8 @@ describe('Dependency Manager Module', () => {
 			// IMPORTANT: Verify no calls to writeJSON with actual tasks.json
 			expect(mockWriteJSON).not.toHaveBeenCalledWith(
 				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
 				expect.anything()
 			);
 		});
@@ -803,6 +832,8 @@ describe('Dependency Manager Module', () => {
 			// IMPORTANT: Verify no calls to writeJSON with actual tasks.json
 			expect(mockWriteJSON).not.toHaveBeenCalledWith(
 				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
 				expect.anything()
 			);
 		});
@@ -916,4 +947,297 @@ describe('Dependency Manager Module', () => {
 			expect(result.conflicts).toEqual([]);
 		});
 	});
+
+	describe('Cross-level dependency tests (Issue #542)', () => {
+		let originalExit;
+
+		beforeEach(async () => {
+			// Ensure a fresh module instance so ESM mocks apply to dynamic imports
+			jest.resetModules();
+			originalExit = process.exit;
+			process.exit = jest.fn();
+
+			// For ESM dynamic imports, use the same pattern
+			await jest.unstable_mockModule('../../scripts/modules/utils.js', () => ({
+				log: mockLog,
+				readJSON: mockReadJSON,
+				writeJSON: mockWriteJSON,
+				taskExists: mockTaskExists,
+				formatTaskId: mockFormatTaskId,
+				findCycles: mockFindCycles,
+				traverseDependencies: jest.fn(() => []),
+				isSilentMode: jest.fn(() => true),
+				findProjectRoot: jest.fn(() => '/test'),
+				resolveEnvVariable: jest.fn(() => undefined),
+				isEmpty: jest.fn((v) =>
+					v == null
+						? true
+						: Array.isArray(v)
+							? v.length === 0
+							: typeof v === 'object'
+								? Object.keys(v).length === 0
+								: false
+				),
+				enableSilentMode: jest.fn(),
+				disableSilentMode: jest.fn(),
+				getTaskManager: jest.fn(async () => ({})),
+				getTagAwareFilePath: jest.fn(
+					(basePath, _tag, projectRoot = '.') => basePath
+				),
+				readComplexityReport: jest.fn(() => null)
+			}));
+
+			// Also mock transitive imports to keep dependency surface minimal
+			await jest.unstable_mockModule('../../scripts/modules/ui.js', () => ({
+				displayBanner: jest.fn()
+			}));
+			await jest.unstable_mockModule(
+				'../../scripts/modules/task-manager/generate-task-files.js',
+				() => ({ default: jest.fn() })
+			);
+			// Set up test data that matches the issue report
+			// Clone fixture data before each test to prevent mutation issues
+			mockReadJSON.mockImplementation(() =>
+				structuredClone(crossLevelDependencyTasks)
+			);
+
+			// Configure mockTaskExists to properly validate cross-level dependencies
+			mockTaskExists.mockImplementation((tasks, taskId) => {
+				if (typeof taskId === 'string' && taskId.includes('.')) {
+					const [parentId, subtaskId] = taskId.split('.').map(Number);
+					const task = tasks.find((t) => t.id === parentId);
+					return (
+						task &&
+						task.subtasks &&
+						task.subtasks.some((st) => st.id === subtaskId)
+					);
+				}
+
+				const numericId =
+					typeof taskId === 'string' ? parseInt(taskId, 10) : taskId;
+				return tasks.some((task) => task.id === numericId);
+			});
+
+			mockFormatTaskId.mockImplementation((id) => {
+				if (typeof id === 'string' && id.includes('.')) return id; // keep dot notation
+				return parseInt(id, 10); // normalize top-level task IDs to number
+			});
+		});
+
+		afterEach(() => {
+			process.exit = originalExit;
+		});
+
+		test('should allow subtask to depend on top-level task', async () => {
+			const { addDependency } = await import(
+				'../../scripts/modules/dependency-manager.js'
+			);
+
+			// Test the specific scenario from Issue #542: subtask 2.2 depending on task 11
+			await addDependency(TEST_TASKS_PATH, '2.2', 11, { projectRoot: '/test' });
+
+			// Verify we wrote to the test path (and not the real tasks.json)
+			expect(mockWriteJSON).toHaveBeenCalledWith(
+				TEST_TASKS_PATH,
+				expect.anything(),
+				'/test',
+				undefined
+			);
+			expect(mockWriteJSON).not.toHaveBeenCalledWith(
+				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
+				expect.anything()
+			);
+			// Get the specific write call for TEST_TASKS_PATH
+			const writeCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(writeCall).toBeDefined();
+			const savedData = writeCall[1];
+			const parent2 = savedData.tasks.find((t) => t.id === 2);
+			const subtask22 = parent2.subtasks.find((st) => st.id === 2);
+
+			// Verify the dependency was actually added to subtask 2.2
+			expect(subtask22.dependencies).toContain(11);
+			// Also verify a success log was emitted
+			const successCall = mockLog.mock.calls.find(
+				([level]) => level === 'success'
+			);
+			expect(successCall).toBeDefined();
+			expect(successCall[1]).toContain('2.2');
+			expect(successCall[1]).toContain('11');
+		});
+
+		test('should allow top-level task to depend on subtask', async () => {
+			const { addDependency } = await import(
+				'../../scripts/modules/dependency-manager.js'
+			);
+
+			// Test reverse scenario: task 11 depending on subtask 2.1
+			await addDependency(TEST_TASKS_PATH, 11, '2.1', { projectRoot: '/test' });
+
+			// Stronger assertions for writeJSON call and locating the correct task
+			expect(mockWriteJSON).toHaveBeenCalledWith(
+				TEST_TASKS_PATH,
+				expect.anything(),
+				'/test',
+				undefined
+			);
+			expect(mockWriteJSON).not.toHaveBeenCalledWith(
+				'tasks/tasks.json',
+				expect.anything(),
+				expect.anything(),
+				expect.anything()
+			);
+			const writeCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(writeCall).toBeDefined();
+			const savedData = writeCall[1];
+			const task11 = savedData.tasks.find((t) => t.id === 11);
+
+			// Verify the dependency was actually added to task 11
+			expect(task11.dependencies).toContain('2.1');
+			// Verify a success log was emitted mentioning both task 11 and subtask 2.1
+			const successCall = mockLog.mock.calls.find(
+				([level]) => level === 'success'
+			);
+			expect(successCall).toBeDefined();
+			expect(successCall[1]).toContain('11');
+			expect(successCall[1]).toContain('2.1');
+		});
+
+		test('should properly validate cross-level dependencies exist', async () => {
+			// Test that validation correctly identifies when a cross-level dependency target doesn't exist
+			mockTaskExists.mockImplementation((tasks, taskId) => {
+				// Simulate task 99 not existing
+				if (taskId === '99' || taskId === 99) {
+					return false;
+				}
+
+				if (typeof taskId === 'string' && taskId.includes('.')) {
+					const [parentId, subtaskId] = taskId.split('.').map(Number);
+					const task = tasks.find((t) => t.id === parentId);
+					return (
+						task &&
+						task.subtasks &&
+						task.subtasks.some((st) => st.id === subtaskId)
+					);
+				}
+
+				const numericId =
+					typeof taskId === 'string' ? parseInt(taskId, 10) : taskId;
+				return tasks.some((task) => task.id === numericId);
+			});
+
+			const { addDependency } = await import(
+				'../../scripts/modules/dependency-manager.js'
+			);
+
+			const exitError = new Error('process.exit invoked');
+			process.exit.mockImplementation(() => {
+				throw exitError;
+			});
+
+			await expect(
+				addDependency(TEST_TASKS_PATH, '2.2', 99, { projectRoot: '/test' })
+			).rejects.toBe(exitError);
+
+			expect(process.exit).toHaveBeenCalledWith(1);
+			expect(mockWriteJSON).not.toHaveBeenCalled();
+			// Verify that an error was reported to the user
+			expect(mockLog).toHaveBeenCalled();
+		});
+
+		test('should remove top-level task dependency from a subtask', async () => {
+			const { addDependency, removeDependency } = await import(
+				'../../scripts/modules/dependency-manager.js'
+			);
+
+			// Start with cloned data and add 11 to 2.2
+			await addDependency(TEST_TASKS_PATH, '2.2', 11, { projectRoot: '/test' });
+
+			// Get the saved data from the add operation
+			const addWriteCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(addWriteCall).toBeDefined();
+			const dataWithDep = addWriteCall[1];
+
+			// Verify the dependency was added
+			const subtask22AfterAdd = dataWithDep.tasks
+				.find((t) => t.id === 2)
+				.subtasks.find((st) => st.id === 2);
+			expect(subtask22AfterAdd.dependencies).toContain(11);
+
+			// Clear mocks and re-setup mockReadJSON with the modified data
+			jest.clearAllMocks();
+			mockReadJSON.mockImplementation(() => structuredClone(dataWithDep));
+
+			await removeDependency(TEST_TASKS_PATH, '2.2', 11, {
+				projectRoot: '/test'
+			});
+
+			const writeCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(writeCall).toBeDefined();
+			const saved = writeCall[1];
+			const subtask22 = saved.tasks
+				.find((t) => t.id === 2)
+				.subtasks.find((st) => st.id === 2);
+			expect(subtask22.dependencies).not.toContain(11);
+			// Verify success log was emitted
+			const successCall = mockLog.mock.calls.find(
+				([level]) => level === 'success'
+			);
+			expect(successCall).toBeDefined();
+			expect(successCall[1]).toContain('2.2');
+			expect(successCall[1]).toContain('11');
+		});
+
+		test('should remove subtask dependency from a top-level task', async () => {
+			const { addDependency, removeDependency } = await import(
+				'../../scripts/modules/dependency-manager.js'
+			);
+
+			// Add subtask dependency to task 11
+			await addDependency(TEST_TASKS_PATH, 11, '2.1', { projectRoot: '/test' });
+
+			// Get the saved data from the add operation
+			const addWriteCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(addWriteCall).toBeDefined();
+			const dataWithDep = addWriteCall[1];
+
+			// Verify the dependency was added
+			const task11AfterAdd = dataWithDep.tasks.find((t) => t.id === 11);
+			expect(task11AfterAdd.dependencies).toContain('2.1');
+
+			// Clear mocks and re-setup mockReadJSON with the modified data
+			jest.clearAllMocks();
+			mockReadJSON.mockImplementation(() => structuredClone(dataWithDep));
+
+			await removeDependency(TEST_TASKS_PATH, 11, '2.1', {
+				projectRoot: '/test'
+			});
+
+			const writeCall = mockWriteJSON.mock.calls.find(
+				([p]) => p === TEST_TASKS_PATH
+			);
+			expect(writeCall).toBeDefined();
+			const saved = writeCall[1];
+			const task11 = saved.tasks.find((t) => t.id === 11);
+			expect(task11.dependencies).not.toContain('2.1');
+			// Verify success log was emitted
+			const successCall = mockLog.mock.calls.find(
+				([level]) => level === 'success'
+			);
+			expect(successCall).toBeDefined();
+			expect(successCall[1]).toContain('11');
+			expect(successCall[1]).toContain('2.1');
+		});
+	});
 });