@e0ipso/ai-task-manager 1.8.3 → 1.9.1

package/README.md

@@ -16,7 +16,7 @@ Unlike Plandex, Claude Task Master, and Conductor Tasks that require API keys wi
 ```bash
 # Initialize for your preferred AI assistant
 npx @e0ipso/ai-task-manager init --assistants claude
-npx @e0ipso/ai-task-manager init --assistants gemini  
+npx @e0ipso/ai-task-manager init --assistants gemini
 npx @e0ipso/ai-task-manager init --assistants opencode
 
 # Or configure multiple assistants
@@ -39,7 +39,7 @@ The documentation includes:
 ## 💡 Quick Workflow Preview
 
 1. **📝 Create a plan**: `/tasks:create-plan Create user authentication system`
-2. **📋 Generate tasks**: `/tasks:generate-tasks 1` 
+2. **📋 Generate tasks**: `/tasks:generate-tasks 1`
 3. **🚀 Execute blueprint**: `/tasks:execute-blueprint 1`
 
 ## 🤖 Supported Assistants
@@ -47,7 +47,7 @@ The documentation includes:
 | Assistant | Interface | Cost Model |
 |-----------|-----------|------------|
 | 🎭 **Claude** | [claude.ai/code](https://claude.ai/code) | Your existing subscription |
-| 💎 **Gemini** | Gemini CLI | Your existing subscription |  
+| 💎 **Gemini** | Gemini CLI | Your existing subscription |
 | 📝 **Open Code** | Open source | Free |
 
 ## 📄 License

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@e0ipso/ai-task-manager",
-  "version": "1.8.3",
+  "version": "1.9.1",
   "description": "Task management for AI coding assistants",
   "main": "dist/index.js",
   "bin": {

package/templates/ai-task-manager/config/hooks/POST_PHASE.md

@@ -1,5 +1,24 @@
+# POST_PHASE Hook
+
 Ensure that:
 
  - The code base is passing the linting requirements
- - All tests are run locally, and they are passing
  - A descriptive commit (using conventional commits with a subject and a description) for the phase was successfully created.
+
+### Execution Monitoring
+
+#### Progress Tracking
+
+Update the list of tasks from the plan document to add the status of each task
+and phase. Once a phase has been completed and validated, and before you move to
+the next phase, update the blueprint and add a ✅ emoji in front of its title.
+Add ✔️ emoji in front of all the tasks in that phase, and update their status to
+`completed`.
+
+#### Task Status Updates
+Valid status transitions:
+- `pending` → `in-progress` (when agent starts)
+- `in-progress` → `completed` (successful execution)
+- `in-progress` → `failed` (execution error)
+- `failed` → `in-progress` (retry attempt)
+

package/templates/ai-task-manager/config/hooks/POST_PLAN.md

@@ -1,136 +1,3 @@
 # POST_PLAN Hook
 
 This hook provides validation and update procedures to execute after plan creation, ensuring comprehensive context analysis and proper plan document structuring with dependency visualization.
-
-## Plan Validation and Clarification
-
-#### Step 1: Context Analysis
-Before creating any plan, analyze the user's request for:
-- **Objective**: What is the end goal?
-- **Scope**: What are the boundaries and constraints?
-- **Resources**: What tools, budget, or team are available?
-- **Success Criteria**: How will success be measured?
-- **Dependencies**: What prerequisites or blockers exist?
-- **Technical Requirements**: What technologies or skills are needed?
-
-#### Step 2: Clarification Phase
-If any critical context is missing:
-1. Identify specific gaps in the information provided
-2. Ask targeted follow-up questions grouped by category
-3. Wait for user responses before proceeding to planning
-4. Frame questions clearly with examples when helpful
-5. Be extra cautious. Users miss important context very often. Don't hesitate to ask for clarifications.
-
-Example clarifying questions:
-- "Q: What is your primary goal with [specific aspect]?"
-- "Q: Do you have any existing [resources/code/infrastructure] I should consider?"
-- "Q: What is your timeline for completing this?"
-- "Q: Are there specific constraints I should account for?"
-- "Q: Do you want me to write tests for this?"
-- "Q: Are there other systems, projects, or modules that perform a similar task?"
-
-Try to answer your own questions first by inspecting the codebase, docs, and assistant documents like CLAUDE.md, GEMINI.md, AGENTS.md ...
-
-## Update the plan document
-
-After creating all tasks with their dependencies, update the original plan document with two critical sections: a task dependency visualization and a phase-based execution blueprint.
-
-### Section 1: Dependency Visualization
-
-If any tasks have dependencies, create a Mermaid diagram showing the dependency graph:
-
-```mermaid
-graph TD
-    001[Task 001: Database Schema] --> 002[Task 002: API Endpoints]
-    001 --> 003[Task 003: Data Models]
-    002 --> 004[Task 004: Frontend Integration]
-    003 --> 004
-```
-
-Note: Ensure the graph is acyclic (no circular dependencies).
-
-### Section 2: Phase-Based Execution Blueprint
-
-#### Core Concept
-The execution blueprint organizes tasks into sequential phases where:
-- **Within a phase**: All tasks execute in parallel
-- **Between phases**: Execution is strictly sequential
-- **Phase progression**: Requires all tasks in current phase to complete AND validation gates to pass
-
-#### Phase Definition Rules
-1. **Phase 1**: Contains all tasks with zero dependencies
-2. **Phase N**: Contains tasks whose dependencies are ALL satisfied by tasks in phases 1 through N-1
-3. **Parallelism Priority**: Maximize the number of tasks that can run simultaneously in each phase
-4. **Completeness**: Every task must be assigned to exactly one phase
-
-#### Blueprint Structure
-
-```markdown
-## Execution Blueprint
-
-**Validation Gates:**
-- Reference: `@.ai/task-manager/config/hooks/POST_PHASE.md`
-
-### Phase 1: [Descriptive Phase Name]
-**Parallel Tasks:**
-- Task 001: [Description]
-- Task 005: [Description]
-- Task 009: [Description]
-
-### Phase 2: [Descriptive Phase Name]
-**Parallel Tasks:**
-- Task 002: [Description] (depends on: 001)
-- Task 003: [Description] (depends on: 001)
-- Task 006: [Description] (depends on: 005)
-
-[Continue for all phases...]
-
-### Post-phase Actions
-
-### Execution Summary
-- Total Phases: X
-- Total Tasks: Y
-- Maximum Parallelism: Z tasks (in Phase N)
-- Critical Path Length: X phases
-```
-
-### Validation Requirements
-
-#### Phase Transition Rules
-1. All tasks in the current phase must have status: "completed"
-2. All validation gates defined in `@.ai/task-manager/config/hooks/POST_PHASE.md` for the current phase must pass
-3. No task in a future phase can begin until these conditions are met
-
-#### Blueprint Verification
-Before finalizing, ensure:
-- [ ] Every task appears in exactly one phase
-- [ ] No task appears in a phase before all its dependencies
-- [ ] Phase 1 contains only tasks with no dependencies
-- [ ] Each phase maximizes parallel execution opportunities
-- [ ] All phases reference their validation gates
-- [ ] The execution summary accurately reflects the blueprint
-
-### Important Notes
-
-#### Parallel Execution
-- Tasks within a phase have no interdependencies and can run simultaneously
-- This enables efficient resource utilization and faster completion
-- AI agents can be assigned to multiple tasks within the same phase
-
-#### Sequential Phases
-- Phases execute in strict numerical order
-- Phase N+1 cannot begin until Phase N is fully complete and validated
-- This ensures dependency integrity and systematic progress
--
-
-#### Validation Gates
-- Each phase has associated validation criteria defined externally
-- Gates ensure quality and correctness before progression
-- Failed validations require task remediation before phase completion
-
-### Error Handling
-
-If dependency analysis reveals issues:
-- **Circular dependencies**: Document the cycle and mark affected tasks for review
-- **Orphaned tasks**: Tasks that cannot be scheduled due to missing dependencies
-- **Ambiguous dependencies**: Note assumptions made and flag for clarification

package/templates/ai-task-manager/config/hooks/POST_TASK_GENERATION_ALL.md

@@ -1,6 +1,11 @@
-[Post-task generation validation and refinement]
+# POST_TASK_GENERATION_ALL Hook
 
-## Step 3.1: Complexity Analysis & Refinement
+After all tasks have been generated use your internal Todo task to execute:
+
+- [ ] Complexity Analysis & Refinement
+- [ ] Update plan document with Blueprint information
+
+## Complexity Analysis & Refinement
 
 ### Complexity Scoring Matrix (1-10 scale)
 
@@ -94,3 +99,64 @@ Original: 8.2 → Round 1 → [4.1, 3.8, 4.5] → PASSED
 - No unresolved errors
 - Iterations documented
 - Validation complete
+
+## Update plan document with Blueprint information
+
+After creating all tasks with their dependencies, update the original plan document with two critical sections: a task dependency visualization and a phase-based execution blueprint.
+
+### Section 1: Dependency Visualization
+
+If any tasks have dependencies, create a Mermaid diagram showing the dependency graph:
+
+```mermaid
+graph TD
+    001[Task 001: Database Schema] --> 002[Task 002: API Endpoints]
+    001 --> 003[Task 003: Data Models]
+    002 --> 004[Task 004: Frontend Integration]
+    003 --> 004
+```
+
+Note: Ensure the graph is acyclic (no circular dependencies).
+
+### Section 2: Phase-Based Execution Blueprint
+
+#### Core Concept
+The execution blueprint organizes tasks into sequential phases where:
+- **Within a phase**: All tasks execute in parallel
+- **Between phases**: Execution is strictly sequential
+- **Phase progression**: Requires all tasks in current phase to complete AND validation gates to pass
+
+#### Phase Definition Rules
+1. **Phase 1**: Contains all tasks with zero dependencies
+2. **Phase N**: Contains tasks whose dependencies are ALL satisfied by tasks in phases 1 through N-1
+3. **Parallelism Priority**: Maximize the number of tasks that can run simultaneously in each phase
+4. **Completeness**: Every task must be assigned to exactly one phase
+
+#### Blueprint Structure
+
+Use the template in .ai/task-manager/config/templates/BLUEPRINT_TEMPLATE.md for the execution blueprint structure.
+
+### Validation Requirements
+
+#### Phase Transition Rules
+1. All tasks in the current phase must have status: "completed"
+2. All validation gates defined in `/config/hooks/POST_PHASE.md` for the current phase must pass
+3. No task in a future phase can begin until these conditions are met
+
+#### Blueprint Verification
+Before finalizing, ensure:
+- [ ] Every task appears in exactly one phase
+- [ ] No task appears in a phase before all its dependencies
+- [ ] Phase 1 contains only tasks with no dependencies
+- [ ] Each phase maximizes parallel execution opportunities
+- [ ] All phases reference their validation gates
+- [ ] The execution summary accurately reflects the blueprint
+
+### Important Notes
+
+### Error Handling
+
+If dependency analysis reveals issues:
+- **Circular dependencies**: Document the cycle and mark affected tasks for review
+- **Orphaned tasks**: Tasks that cannot be scheduled due to missing dependencies
+- **Ambiguous dependencies**: Note assumptions made and flag for clarification

package/templates/ai-task-manager/config/hooks/PRE_PHASE.md

@@ -17,7 +17,7 @@ If there are unstaged changes in the `main` branch, do not create a feature bran
         ```bash
         # For each task in current phase
         for TASK_ID in $PHASE_TASKS; do
-            if ! node .ai/task-manager/config/scripts/check-task-dependencies.js "$1" "$TASK_ID"; then
+            if ! node .ai/task-manager/config/scripts/check-task-dependencies.cjs "$1" "$TASK_ID"; then
                 echo "ERROR: Task $TASK_ID has unresolved dependencies - cannot proceed with phase execution"
                 echo "Please resolve dependencies before continuing with blueprint execution"
                 exit 1

package/templates/ai-task-manager/config/hooks/PRE_PLAN.md

@@ -0,0 +1,43 @@
+# PRE_PLAN Hook
+
+This hook provides pre-planning guidance to ensure scope control, simplicity principles, and proper validation requirements are established before comprehensive plan creation.
+
+## Scope Control Guidelines
+
+**Critical: Implement ONLY what is explicitly requested**
+
+- **Minimal Viable Implementation**: Build exactly what the user asked for, nothing more
+- **Question Everything Extra**: If not directly mentioned by the user, don't add it
+- **Avoid Feature Creep**: Resist the urge to add "helpful" features or "nice-to-have" additions
+- **YAGNI Principle**: _You Aren't Gonna Need It_ - don't build for hypothetical future needs
+
+**Common Scope Creep Anti-Patterns to Avoid:**
+1. Adding extra commands or features "for completeness"
+2. Creating infrastructure for future features that weren't requested
+3. Building abstractions or frameworks when simple solutions suffice
+4. Adding configuration options not specifically mentioned
+5. Implementing error handling beyond what's necessary for the core request
+6. Creating documentation or help systems unless explicitly requested
+
+**When in doubt, ask**: "Is this feature explicitly mentioned in the user's request?"
+
+## Simplicity Principles
+
+**Favor maintainability over cleverness**
+
+- **Simple Solutions First**: Choose the most straightforward approach that meets requirements
+- **Avoid Over-Engineering**: Don't create complex systems when simple ones work
+- **Readable Code**: Write code that others can easily understand and modify
+- **Standard Patterns**: Use established patterns rather than inventing new ones
+- **Minimal Dependencies**: Add external dependencies only when essential, but do not re-invent the wheel
+- **Clear Structure**: Organize code in obvious, predictable ways
+
+**Remember**: A working simple solution is better than a complex "perfect" one.
+
+## Critical Notes
+
+- Never generate a partial or assumed plan without adequate context
+- Prioritize accuracy over speed
+- Consider both technical and non-technical aspects
+- Use the plan template in .ai/task-manager/config/templates/PLAN_TEMPLATE.md
+- DO NOT create or list any tasks or phases during the plan creation. This will be done in a later step. Stick to writing the PRD (Project Requirements Document).

package/templates/ai-task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md

@@ -1,4 +1,4 @@
-# Pre-Task Assignment Hook
+# PRE_TASK_ASSIGNMENT Hook
 
 This hook executes before task assignment to determine the most appropriate agent for each task based on skill requirements and available sub-agents.
 

package/templates/ai-task-manager/config/scripts/{check-task-dependencies.js → check-task-dependencies.cjs}

@@ -1,9 +1,9 @@
 #!/usr/bin/env node
 
 /**
- * Script: check-task-dependencies.js
+ * Script: check-task-dependencies.cjs
  * Purpose: Check if a task has all of its dependencies resolved (completed)
- * Usage: node check-task-dependencies.js <plan-id> <task-id>
+ * Usage: node check-task-dependencies.cjs <plan-id> <task-id>
  * Returns: 0 if all dependencies are resolved, 1 if not
  */
 
@@ -17,7 +17,7 @@ let chalkInstance = null;
 // Initialize chalk instance dynamically
 async function initChalk() {
     if (chalkInstance) return chalkInstance;
-    
+
     try {
         const { default: chalk } = await import('chalk');
         chalkInstance = chalk;
@@ -25,7 +25,7 @@ async function initChalk() {
         // Chalk not available, will fall back to plain console output
         chalkInstance = null;
     }
-    
+
     return chalkInstance;
 }
 
@@ -65,7 +65,7 @@ const findPlanDirectory = (planId) => {
 // Function to find task file with padded/unpadded ID handling
 const findTaskFile = (planDir, taskId) => {
     const taskDir = path.join(planDir, 'tasks');
-    
+
     if (!fs.existsSync(taskDir)) {
         return null;
     }
@@ -76,7 +76,7 @@ const findTaskFile = (planDir, taskId) => {
         const regex = new RegExp(`^${taskId}--.*\\.md$`);
         return regex.test(file);
     });
-    
+
     if (files.length > 0) {
         return path.join(taskDir, files[0]);
     }
@@ -89,7 +89,7 @@ const findTaskFile = (planDir, taskId) => {
             const regex = new RegExp(`^${paddedTaskId}--.*\\.md$`);
             return regex.test(file);
         });
-        
+
         if (files.length > 0) {
             return path.join(taskDir, files[0]);
         }
@@ -103,7 +103,7 @@ const findTaskFile = (planDir, taskId) => {
             const regex = new RegExp(`^${unpaddedTaskId}--.*\\.md$`);
             return regex.test(file);
         });
-        
+
         if (files.length > 0) {
             return path.join(taskDir, files[0]);
         }
@@ -115,7 +115,7 @@ const findTaskFile = (planDir, taskId) => {
             const regex = new RegExp(`^${repaddedTaskId}--.*\\.md$`);
             return regex.test(file);
         });
-        
+
         if (files.length > 0) {
             return path.join(taskDir, files[0]);
         }
@@ -143,7 +143,7 @@ const parseFrontmatter = (content) => {
                 break;
             }
         }
-        
+
         if (inFrontmatter && !frontmatterEnd) {
             frontmatterLines.push(line);
         }
@@ -160,11 +160,11 @@ const extractDependencies = (frontmatter) => {
 
     for (let i = 0; i < lines.length; i++) {
         const line = lines[i];
-        
+
         // Check for dependencies line
         if (line.match(/^dependencies:/)) {
             inDependenciesSection = true;
-            
+
             // Check if dependencies are on the same line (array syntax)
             const arrayMatch = line.match(/\[(.*)\]/);
             if (arrayMatch) {
@@ -198,13 +198,13 @@ const extractDependencies = (frontmatter) => {
 // Function to extract status from frontmatter
 const extractStatus = (frontmatter) => {
     const lines = frontmatter.split('\n');
-    
+
     for (const line of lines) {
         if (line.match(/^status:/)) {
             return line.replace(/^status:[ \t]*/, '').replace(/^["']/, '').replace(/["']$/, '').trim();
         }
     }
-    
+
     return null;
 };
 
@@ -212,12 +212,12 @@ const extractStatus = (frontmatter) => {
 const main = async () => {
     // Initialize chalk
     const chalk = await initChalk();
-    
+
     // Check arguments
     if (process.argv.length !== 4) {
         printError('Invalid number of arguments', chalk);
-        console.log('Usage: node check-task-dependencies.js <plan-id> <task-id>');
-        console.log('Example: node check-task-dependencies.js 16 03');
+        console.log('Usage: node check-task-dependencies.cjs <plan-id> <task-id>');
+        console.log('Example: node check-task-dependencies.cjs 16 03');
         process.exit(1);
     }
 
@@ -226,7 +226,7 @@ const main = async () => {
 
     // Find the plan directory
     const planDir = findPlanDirectory(planId);
-    
+
     if (!planDir) {
         printError(`Plan with ID ${planId} not found`, chalk);
         process.exit(1);

package/templates/ai-task-manager/config/scripts/{get-next-plan-id.js → get-next-plan-id.cjs}

@@ -10,7 +10,7 @@ const path = require('path');
 function findTaskManagerRoot() {
   let currentPath = process.cwd();
   const root = path.parse(currentPath).root;
-  
+
   while (currentPath !== root) {
     const taskManagerPath = path.join(currentPath, '.ai', 'task-manager', 'plans');
     if (fs.existsSync(taskManagerPath)) {
@@ -18,13 +18,13 @@ function findTaskManagerRoot() {
     }
     currentPath = path.dirname(currentPath);
   }
-  
+
   // Check root directory as well
   const rootTaskManager = path.join(root, '.ai', 'task-manager', 'plans');
   if (fs.existsSync(rootTaskManager)) {
     return path.join(root, '.ai', 'task-manager');
   }
-  
+
   return null;
 }
 
@@ -36,9 +36,9 @@ function findTaskManagerRoot() {
 function extractIdFromFrontmatter(content) {
   const frontmatterMatch = content.match(/^---\s*\n([\s\S]*?)\n---/);
   if (!frontmatterMatch) return null;
-  
+
   const frontmatterText = frontmatterMatch[1];
-  
+
   // Handle various YAML formats for id field using regex:
   // id: 5
   // id: "5"
@@ -52,7 +52,7 @@ function extractIdFromFrontmatter(content) {
     /^\s*id\s*:\s*"(\d+)"\s*$/m,                     // Double quoted
     /^\s*id\s*:\s*'(\d+)'\s*$/m,                     // Single quoted
   ];
-  
+
   for (const pattern of patterns) {
     const match = frontmatterText.match(pattern);
     if (match) {
@@ -60,7 +60,7 @@ function extractIdFromFrontmatter(content) {
       if (!isNaN(id)) return id;
     }
   }
-  
+
   return null;
 }
 
@@ -70,25 +70,25 @@ function extractIdFromFrontmatter(content) {
  */
 function getNextPlanId() {
   const taskManagerRoot = findTaskManagerRoot();
-  
+
   if (!taskManagerRoot) {
     console.error('Error: No .ai/task-manager/plans directory found in current directory or any parent directory.');
     console.error('Please ensure you are in a project with task manager initialized.');
     process.exit(1);
   }
-  
+
   const plansDir = path.join(taskManagerRoot, 'plans');
   const archiveDir = path.join(taskManagerRoot, 'archive');
-  
+
   let maxId = 0;
-  
+
   // Scan both plans and archive directories
   [plansDir, archiveDir].forEach(dir => {
     if (!fs.existsSync(dir)) return;
-    
+
     try {
       const entries = fs.readdirSync(dir, { withFileTypes: true });
-      
+
       entries.forEach(entry => {
         if (entry.isFile() && entry.name.match(/^plan-\d+--.*\.md$/)) {
           // Extract ID from filename as fallback
@@ -97,13 +97,13 @@ function getNextPlanId() {
             const id = parseInt(filenameMatch[1], 10);
             if (!isNaN(id) && id > maxId) maxId = id;
           }
-          
+
           // Also check frontmatter for more reliable ID
           try {
             const filePath = path.join(dir, entry.name);
             const content = fs.readFileSync(filePath, 'utf8');
             const id = extractIdFromFrontmatter(content);
-            
+
             if (id !== null && id > maxId) {
               maxId = id;
             }
@@ -116,7 +116,7 @@ function getNextPlanId() {
       // Skip directories that can't be read
     }
   });
-  
+
   return maxId + 1;
 }
 

package/templates/ai-task-manager/config/scripts/{get-next-task-id.js → get-next-task-id.cjs}

@@ -10,7 +10,7 @@ const path = require('path');
 function findTaskManagerRoot() {
   let currentPath = process.cwd();
   const root = path.parse(currentPath).root;
-  
+
   while (currentPath !== root) {
     const taskManagerPath = path.join(currentPath, '.ai', 'task-manager', 'plans');
     if (fs.existsSync(taskManagerPath)) {
@@ -18,13 +18,13 @@ function findTaskManagerRoot() {
     }
     currentPath = path.dirname(currentPath);
   }
-  
+
   // Check root directory as well
   const rootTaskManager = path.join(root, '.ai', 'task-manager', 'plans');
   if (fs.existsSync(rootTaskManager)) {
     return path.join(root, '.ai', 'task-manager');
   }
-  
+
   return null;
 }
 
@@ -36,9 +36,9 @@ function findTaskManagerRoot() {
 function extractIdFromFrontmatter(content) {
   const frontmatterMatch = content.match(/^---\s*\n([\s\S]*?)\n---/);
   if (!frontmatterMatch) return null;
-  
+
   const frontmatterText = frontmatterMatch[1];
-  
+
   // Handle various YAML formats for id field using regex:
   // id: 5
   // id: "5"
@@ -52,7 +52,7 @@ function extractIdFromFrontmatter(content) {
     /^\s*id\s*:\s*"(\d+)"\s*$/m,                     // Double quoted
     /^\s*id\s*:\s*'(\d+)'\s*$/m,                     // Single quoted
   ];
-  
+
   for (const pattern of patterns) {
     const match = frontmatterText.match(pattern);
     if (match) {
@@ -60,7 +60,7 @@ function extractIdFromFrontmatter(content) {
       if (!isNaN(id)) return id;
     }
   }
-  
+
   return null;
 }
 
@@ -74,30 +74,30 @@ function getNextTaskId(planId) {
     console.error('Error: Plan ID is required');
     process.exit(1);
   }
-  
+
   const taskManagerRoot = findTaskManagerRoot();
-  
+
   if (!taskManagerRoot) {
     console.error('Error: No .ai/task-manager/plans directory found in current directory or any parent directory.');
     console.error('Please ensure you are in a project with task manager initialized.');
     process.exit(1);
   }
-  
+
   const plansDir = path.join(taskManagerRoot, 'plans');
-  
+
   // Find the plan directory (supports both padded and unpadded formats)
   const paddedPlanId = String(planId).padStart(2, '0');
-  
+
   let planDir = null;
-  
+
   // Optimization: 90% of the time there are no tasks, so check if plans directory exists first
   if (!fs.existsSync(plansDir)) {
     return 1; // No plans directory = no tasks = start with ID 1
   }
-  
+
   try {
     const entries = fs.readdirSync(plansDir, { withFileTypes: true });
-    
+
     // Look for directory matching the plan ID pattern
     for (const entry of entries) {
       if (entry.isDirectory()) {
@@ -117,29 +117,29 @@ function getNextTaskId(planId) {
   } catch (err) {
     // Directory doesn't exist or can't be read
   }
-  
+
   // Optimization: If no tasks directory exists, return 1 immediately (90% case)
   if (!planDir) {
     return 1;
   }
-  
+
   let maxId = 0;
-  
+
   try {
     const entries = fs.readdirSync(planDir, { withFileTypes: true });
-    
+
     // Another optimization: If directory is empty, return 1 immediately
     if (entries.length === 0) {
       return 1;
     }
-    
+
     entries.forEach(entry => {
       if (entry.isFile() && entry.name.endsWith('.md')) {
         try {
           const filePath = path.join(planDir, entry.name);
           const content = fs.readFileSync(filePath, 'utf8');
           const id = extractIdFromFrontmatter(content);
-          
+
           if (id !== null && id > maxId) {
             maxId = id;
           }
@@ -151,7 +151,7 @@ function getNextTaskId(planId) {
   } catch (err) {
     // Skip directories that can't be read
   }
-  
+
   return maxId + 1;
 }
 

package/templates/ai-task-manager/config/templates/BLUEPRINT_TEMPLATE.md

@@ -0,0 +1,26 @@
+## Execution Blueprint
+
+**Validation Gates:**
+- Reference: `/config/hooks/POST_PHASE.md`
+
+### Phase 1: [Descriptive Phase Name]
+**Parallel Tasks:**
+- Task 001: [Description]
+- Task 005: [Description]
+- Task 009: [Description]
+
+### Phase 2: [Descriptive Phase Name]
+**Parallel Tasks:**
+- Task 002: [Description] (depends on: 001)
+- Task 003: [Description] (depends on: 001)
+- Task 006: [Description] (depends on: 005)
+
+[Continue for all phases...]
+
+### Post-phase Actions
+
+### Execution Summary
+- Total Phases: X
+- Total Tasks: Y
+- Maximum Parallelism: Z tasks (in Phase N)
+- Critical Path Length: X phases

package/templates/ai-task-manager/config/templates/EXECUTION_SUMMARY_TEMPLATE.md

@@ -0,0 +1,13 @@
+## Execution Summary
+
+**Status**: ✅ Completed Successfully
+**Completed Date**: [YYYY-MM-DD]
+
+### Results
+[Brief summary of execution results and key deliverables]
+
+### Noteworthy Events
+[Highlight any unexpected events, challenges overcome, or significant findings during execution. If none occurred, state "No significant issues encountered."]
+
+### Recommendations
+[Any follow-up actions or optimizations identified]

package/templates/ai-task-manager/config/templates/TASK_TEMPLATE.md

@@ -21,7 +21,7 @@ skills: # Technical skills required for this task
 - [ ] Criterion 2
 - [ ] Criterion 3
 
-Use your internal TODO tool to track these and keep on track.
+Use your internal Todo tool to track these and keep on track.
 
 ## Technical Requirements
 [Specific technical details, APIs, libraries, etc. - use this to infer appropriate skills]

package/templates/assistant/commands/tasks/create-plan.md

@@ -6,7 +6,7 @@ description: Create a comprehensive plan to accomplish the request from the user
 
 You are a comprehensive task planning assistant. Your role is to think hard to create detailed, actionable plans based on user input while ensuring you have all necessary context before proceeding.
 
-Include @.ai/task-manager/config/TASK_MANAGER.md for the directory structure of tasks.
+Include .ai/task-manager/config/TASK_MANAGER.md for the directory structure of tasks.
 
 ## Instructions
 
@@ -16,20 +16,47 @@ The user input is:
 $ARGUMENTS
 </user-input>
 
-If no user input is provided stop immediately and show an error message to the user:
+If no user input is provided stop immediately and show an error message to the user.
 
 ### Process
 
-Use your internal Todo task tool to track the plan generation. Example:
+Use your internal Todo task tool to track the plan generation:
 
+- [ ] Read and execute .ai/task-manager/config/hooks/PRE_PLAN.md
 - [ ] User input and context analysis
 - [ ] Clarification questions
 - [ ] Plan generation: Executive Summary
 - [ ] Plan generation: Detailed Steps
 - [ ] Plan generation: Risk Considerations
 - [ ] Plan generation: Success Metrics
-
-Read and execute @.ai/task-manager/config/hooks/POST_PLAN.md
+- [ ] Read and execute .ai/task-manager/config/hooks/POST_PLAN.md
+
+#### Step 1: Context Analysis
+Before creating any plan, analyze the user's request for:
+- **Objective**: What is the end goal?
+- **Scope**: What are the boundaries and constraints?
+- **Resources**: What tools, budget, or team are available?
+- **Success Criteria**: How will success be measured?
+- **Dependencies**: What prerequisites or blockers exist?
+- **Technical Requirements**: What technologies or skills are needed?
+
+#### Step 2: Clarification Phase
+If any critical context is missing:
+1. Identify specific gaps in the information provided
+2. Ask targeted follow-up questions grouped by category
+3. Wait for user responses before proceeding to planning
+4. Frame questions clearly with examples when helpful
+5. Be extra cautious. Users miss important context very often. Don't hesitate to ask for clarifications.
+
+Example clarifying questions:
+- "Q: What is your primary goal with [specific aspect]?"
+- "Q: Do you have any existing [resources/code/infrastructure] I should consider?"
+- "Q: What is your timeline for completing this?"
+- "Q: Are there specific constraints I should account for?"
+- "Q: Do you want me to write tests for this?"
+- "Q: Are there other systems, projects, or modules that perform a similar task?"
+
+Try to answer your own questions first by inspecting the codebase, docs, and assistant documents like CLAUDE.md, GEMINI.md, AGENTS.md ...
 
 #### Step 3: Plan Generation
 Only after confirming sufficient context, create a plan that includes:
@@ -40,36 +67,6 @@ Only after confirming sufficient context, create a plan that includes:
 
 Remember that a plan needs to be reviewed by a human. Be concise and to the point. Also, include mermaid diagrams to illustrate the plan.
 
-##### Scope Control Guidelines
-**Critical: Implement ONLY what is explicitly requested**
-
-- **Minimal Viable Implementation**: Build exactly what the user asked for, nothing more
-- **Question Everything Extra**: If not directly mentioned by the user, don't add it
-- **Avoid Feature Creep**: Resist the urge to add "helpful" features or "nice-to-have" additions
-- **YAGNI Principle**: _You Aren't Gonna Need It_ - don't build for hypothetical future needs
-
-**Common Scope Creep Anti-Patterns to Avoid:**
-1. Adding extra commands or features "for completeness"
-2. Creating infrastructure for future features that weren't requested
-3. Building abstractions or frameworks when simple solutions suffice
-4. Adding configuration options not specifically mentioned
-5. Implementing error handling beyond what's necessary for the core request
-6. Creating documentation or help systems unless explicitly requested
-
-**When in doubt, ask**: "Is this feature explicitly mentioned in the user's request?"
-
-##### Simplicity Principles
-**Favor maintainability over cleverness**
-
-- **Simple Solutions First**: Choose the most straightforward approach that meets requirements
-- **Avoid Over-Engineering**: Don't create complex systems when simple ones work
-- **Readable Code**: Write code that others can easily understand and modify
-- **Standard Patterns**: Use established patterns rather than inventing new ones
-- **Minimal Dependencies**: Add external dependencies only when essential, but do not re-invent the wheel
-- **Clear Structure**: Organize code in obvious, predictable ways
-
-**Remember**: A working simple solution is better than a complex "perfect" one.
-
 ##### Output Format
 Structure your response as follows:
 - If context is insufficient: List specific clarifying questions
@@ -79,7 +76,7 @@ Outside the plan document, be **extremely** concise. Just tell the user that you
 
 ###### Plan Template
 
-Use the template in @.ai/task-manager/config/templates/PLAN_TEMPLATE.md
+Use the template in .ai/task-manager/config/templates/PLAN_TEMPLATE.md
 
 ###### Patterns to Avoid
 Do not include the following in your plan output.
@@ -121,18 +118,11 @@ The schema for this frontmatter is:
 }
 ```
 
-### Critical Notes
-- Never generate a partial or assumed plan without adequate context
-- Prioritize accuracy over speed
-- Consider both technical and non-technical aspects
-- Use the plan template in .ai/task-manager/config/templates/PLAN_TEMPLATE.md
-- DO NOT create or list any tasks or phases during the plan creation. This will be done in a later step. Stick to writing the PRD (Project Requirements Document).
-
 ### Plan ID Generation
 
 **Auto-generate the next plan ID:**
 ```bash
-node .ai/task-manager/config/scripts/get-next-plan-id.js
+node .ai/task-manager/config/scripts/get-next-plan-id.cjs
 ```
 
 **Key formatting:**

package/templates/assistant/commands/tasks/execute-blueprint.md

@@ -15,9 +15,9 @@ You are the orchestrator responsible for executing all tasks defined in the exec
 5. **Fail safely** - Better to halt and request help than corrupt the execution state
 
 ## Input Requirements
-- A plan document with an execution blueprint section. See @.ai/task-manager/TASK_MANAGER.md fo find the plan with ID $1
+- A plan document with an execution blueprint section. See /TASK_MANAGER.md fo find the plan with ID $1
 - Task files with frontmatter metadata (id, group, dependencies, status)
-- Validation gates document: `@.ai/task-manager/config/hooks/POST_PHASE.md`
+- Validation gates document: `/config/hooks/POST_PHASE.md`
 
 ### Input Error Handling
 If the plan does not exist, or the plan does not have an execution blueprint section. Stop immediately and show an error to the user.
@@ -27,17 +27,20 @@ If the plan does not exist, or the plan does not have an execution blueprint sec
 Use your internal Todo task tool to track the execution of all phases, and the final update of the plan with the summary. Example:
 
 - [ ] Create feature branch from the main branch.
+- [ ] Execute .ai/task-manager/config/hooks/PRE_PHASE.md hook before Phase 1.
 - [ ] Phase 1: Execute 1 task(s) in parallel.
-- [ ] Execute POST_PHASE.md hook after Phase 1.
+- [ ] Execute .ai/task-manager/config/hooks/POST_PHASE.md hook after Phase 1.
+- [ ] Execute .ai/task-manager/config/hooks/PRE_PHASE.md hook before Phase 2.
 - [ ] Phase 2: Execute 3 task(s) in parallel.
-- [ ] Execute POST_PHASE.md hook after Phase 2.
+- [ ] Execute .ai/task-manager/config/hooks/POST_PHASE.md hook after Phase 2.
+- [ ] Execute .ai/task-manager/config/hooks/PRE_PHASE.md hook before Phase 3.
 - [ ] Phase 3: Execute 1 task(s) in parallel.
-- [ ] Execute POST_PHASE.md hook after Phase 3.
+- [ ] Execute .ai/task-manager/config/hooks/POST_PHASE.md hook after Phase 3.
 - [ ] Update the Plan 7 with execution summary, and the archive it.
 
 ### Phase Pre-Execution
 
-Read and execute @.ai/task-manager/config/hooks/PRE_PHASE.md
+Read and execute .ai/task-manager/config/hooks/PRE_PHASE.md
 
 ### Phase Execution Workflow
 
@@ -46,7 +49,7 @@ Read and execute @.ai/task-manager/config/hooks/PRE_PHASE.md
     - List all tasks scheduled for parallel execution in this phase
 
 2. **Agent Selection and Task Assignment**
-Read and execute @.ai/task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md
+Read and execute .ai/task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md
 
 3. **Parallel Execution**
     - Deploy all selected agents simultaneously using your internal Task tool
@@ -59,38 +62,21 @@ Read and execute @.ai/task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md
     - Collect and review all task outputs
     - Document any issues or exceptions encountered
 
-5. **Validation Gate Execution**
-    - Reference validation criteria from `@.ai/task-manager/config/hooks/POST_PHASE.md`
-    - Execute all validation gates for the current phase
-    - Document validation results
-    - Only proceed if ALL validations pass
+### Phase Post-Execution
 
-6. **Phase Transition**
-    - Update phase status to "completed"
-    - Initialize next phase
-    - Repeat process until all phases are complete
+Read and execute .ai/task-manager/config/hooks/POST_PHASE.md
 
-### Execution Monitoring
 
-#### Progress Tracking
+### Phase Transition
 
-Update the list of tasks from the plan document to add the status of each task
-and phase. Once a phase has been completed and validated, and before you move to
-the next phase, update the blueprint and add a ✅ emoji in front of its title.
-Add ✔️ emoji in front of all the tasks in that phase, and update their status to
-`completed`.
-
-#### Task Status Updates
-Valid status transitions:
-- `pending` → `in-progress` (when agent starts)
-- `in-progress` → `completed` (successful execution)
-- `in-progress` → `failed` (execution error)
-- `failed` → `in-progress` (retry attempt)
+  - Update phase status to "completed" in the Blueprint section of the plan $1 document.
+  - Initialize next phase
+  - Repeat process until all phases are complete
 
 ### Error Handling
 
 #### Validation Gate Failures
-Read and execute @.ai/task-manager/config/hooks/POST_ERROR_DETECTION.md
+Read and execute .ai/task-manager/config/hooks/POST_ERROR_DETECTION.md
 
 ### Output Requirements
 
@@ -105,25 +91,12 @@ Read and execute @.ai/task-manager/config/hooks/POST_ERROR_DETECTION.md
 
 Upon successful completion of all phases and validation gates, perform the following additional steps:
 
-### 1. Execution Summary Generation
-
-Append an execution summary section to the plan document with the following format:
-
-```markdown
-## Execution Summary
+- [ ] Execution Summary Generation
+- [ ] Plan Archival
 
-**Status**: ✅ Completed Successfully
-**Completed Date**: [YYYY-MM-DD]
-
-### Results
-[Brief summary of execution results and key deliverables]
-
-### Noteworthy Events
-[Highlight any unexpected events, challenges overcome, or significant findings during execution. If none occurred, state "No significant issues encountered."]
+### 1. Execution Summary Generation
 
-### Recommendations
-[Any follow-up actions or optimizations identified]
-```
+Append an execution summary section to the plan document with the format described in .ai/task-manager/config/templates/[EXECUTION_SUMMARY_TEMPLATE.md
 
 ### 2. Plan Archival
 

package/templates/assistant/commands/tasks/execute-task.md

@@ -26,8 +26,8 @@ Use your internal Todo task tool to track the execution of all parts of the task
 ## Input Requirements
 - Plan ID: $1 (required)
 - Task ID: $2 (required)
-- Task management directory structure: `@.ai/task-manager/`
-- Dependency checking script: `.ai/task-manager/config/scripts/check-task-dependencies.js`
+- Task management directory structure: `/`
+- Dependency checking script: `.ai/task-manager/config/scripts/check-task-dependencies.cjs`
 
 ### Input Validation
 
@@ -134,7 +134,7 @@ Use the dependency checking script to validate all dependencies:
 
 ```bash
 # Call the dependency checking script
-if ! node .ai/task-manager/config/scripts/check-task-dependencies.js "$PLAN_ID" "$TASK_ID"; then
+if ! node .ai/task-manager/config/scripts/check-task-dependencies.cjs "$PLAN_ID" "$TASK_ID"; then
     echo ""
     echo "Task execution blocked by unresolved dependencies."
     echo "Please complete the required dependencies first."
@@ -149,9 +149,7 @@ echo "✓ All dependencies resolved - proceeding with execution"
 
 Read task skills and select appropriate task-specific agent:
 
-```bash
-Read and execute @.ai/task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md
-```
+Read and execute .ai/task-manager/config/hooks/PRE_TASK_ASSIGNMENT.md
 
 ### 6. Status Update to In-Progress
 
@@ -234,7 +232,7 @@ echo "You can now execute dependent tasks or continue with the full blueprint ex
 
 ## Error Handling
 
-Read and execute @.ai/task-manager/config/hooks/POST_ERROR_DETECTION.md
+Read and execute .ai/task-manager/config/hooks/POST_ERROR_DETECTION.md
 
 ## Usage Examples
 

package/templates/assistant/commands/tasks/generate-tasks.md

@@ -5,14 +5,20 @@ description: Generate tasks to implement the plan with the provided ID.
 # Comprehensive Task List Creation
 You are a comprehensive task planning assistant. Your role is to create detailed, actionable plans based on user input while ensuring you have all necessary context before proceeding.
 
-Include @.ai/task-manager/TASK_MANAGER.md for the directory structure of tasks.
+Include /TASK_MANAGER.md for the directory structure of tasks.
 
 ## Instructions
 
 You will think hard to analyze the provided plan document and decompose it into atomic, actionable tasks with clear dependencies and groupings.
 
+Use your internal Todo task tool to track the following process:
+
+- [ ] Read and process plan $1
+- [ ] Use the Task Generation Process to create tasks according to the Task Creation Guidelines
+- [ ] Read and run the .ai/task-manager/config/hooks/POST_TASK_GENERATION_ALL.md
+
 ### Input
-- A plan document. See @.ai/task-manager/TASK_MANAGER.md fo find the plan with ID $1
+- A plan document. See .ai/task-manager/config/TASK_MANAGER.md fo find the plan with ID $1
 - The plan contains high-level objectives and implementation steps
 
 ### Input Error Handling
@@ -108,7 +114,7 @@ Tests that verify custom business logic, critical paths, and edge cases specific
 - Avoid creating separate tasks for testing each CRUD operation individually
 - Question whether simple functions need dedicated test tasks
 
-### Process
+### Task Generation Process
 
 #### Step 1: Task Decomposition
 1. Read through the entire plan
@@ -131,11 +137,7 @@ Dependency Rule: Task B depends on Task A if:
 - B modifies code created by A
 - B tests functionality implemented in A
 
-#### Step 3: POST_TASK_GENERATION_ALL hook
-
-Read and run the @.ai/task-manager/config/hooks/POST_TASK_GENERATION_ALL.md
-
-#### Step 4: Output Generation
+#### Step 3: Task Generation
 
 ##### Frontmatter Structure
 
@@ -212,96 +214,16 @@ The schema for this frontmatter is:
 
 ##### Task Body Structure
 
-Use the task template in @.ai/task-manager/config/templates/TASK_TEMPLATE.md
+Use the task template in .ai/task-manager/config/templates/TASK_TEMPLATE.md
 
-### Task ID Generation
+##### Task ID Generation
 
 When creating tasks, you need to determine the next available task ID for the specified plan. Use this bash command to automatically generate the correct ID:
 
-#### Command
 ```bash
-node .ai/task-manager/config/scripts/get-next-task-id.js $1
+node .ai/task-manager/config/scripts/get-next-task-id.cjs $1
 ```
 
-#### How It Works
-1. **Finds the plan directory** using pattern matching for plan ID directories
-2. **Scans task files** in the plan's tasks directory for `.md` files
-3. **Validates frontmatter IDs** by parsing YAML frontmatter and extracting numeric ID values
-4. **Finds maximum ID** by comparing all valid task IDs numerically
-5. **Handles edge cases** by gracefully handling missing directories, corrupted files, and parsing errors
-6. **Returns next ID** by incrementing the maximum found ID by 1
-
-This Node.js script provides robust error handling and reliable ID generation.
-
-#### Parameter Usage
-- `$1` is the plan ID parameter passed to this template
-- The command accepts the raw plan ID (e.g., `6` for plan `06`)
-- It automatically handles zero-padding for directory lookup
-
-#### Front-matter vs Filename Format
-**IMPORTANT:** There is a distinction between numeric and zero-padded formats:
-
-- **Front-matter ID**: Use numeric values: `id: 3` (not `id: "03"`)
-- **Filename**: Use zero-padded format: `03--task-name.md`
-
-#### Usage Examples
-
-**Example 1: Plan 6 with existing tasks**
-```bash
-# Command execution (plan ID = 6)
-node .ai/task-manager/config/scripts/get-next-task-id.js 6
-# Output: 5 (if highest valid numeric task front-matter has id: 4)
-
-# Front-matter usage:
----
-id: 4
-group: "implementation"
-dependencies: [1, 2]
-status: "pending"
-created: "2024-01-15"
-skills: ["api-endpoints", "database"]
----
-```
-
-**Example 2: Plan 1 with no existing tasks**
-```bash
-# Command execution (plan ID = 1)
-node .ai/task-manager/config/scripts/get-next-task-id.js 1
-# Output: 1 (empty tasks directory, no valid front-matter to read)
-
-# Front-matter usage:
----
-id: 1
-group: "setup"
-dependencies: []
-status: "pending"
-created: "2024-01-15"
-skills: ["docker", "ci-cd"]
----
-```
-
-#### Edge Case Handling
-The command handles several edge cases automatically:
-- **Empty tasks directory**: Returns `1` as the first task ID
-- **Non-sequential task IDs**: Returns the maximum existing ID + 1
-- **Missing plan directory**: Returns `1` (graceful fallback)
-- **Mixed numbering**: Correctly finds the highest numeric ID regardless of gaps
-- **Malformed frontmatter**: Skips files with non-numeric, string, or missing ID fields
-- **Whitespace variations**: Handles extra spaces around ID values (e.g., `id:  5  `)
-
-#### Command Execution Context
-- Run this command from the repository root directory
-- The command works with the current file system state
-- It searches within the plan directory structure: `.ai/task-manager/plans/##--plan-name/tasks/`
-
-#### Manual Fallback
-If the command fails or returns unexpected results:
-1. Navigate to `.ai/task-manager/plans/##--plan-name/tasks/`
-2. List existing task files: `ls -1 *.md 2>/dev/null | sort`
-3. Identify the highest numbered task file
-4. Add 1 to get the next ID
-5. Use numeric format in front-matter, zero-padded format for filename
-
 ### Validation Checklist
 Before finalizing, ensure:
 
@@ -350,4 +272,6 @@ If the plan lacks sufficient detail:
 - Create placeholder tasks marked with `status: "needs-clarification"`
 - Document assumptions made
 
-Read and execute @.ai/task-manager/config/hooks/POST_PLAN.md
+#### Step 4: POST_TASK_GENERATION_ALL hook
+
+Read and run the .ai/task-manager/config/hooks/POST_TASK_GENERATION_ALL.md