feat: 增强 command-guide skill 支持深度命令分析和 CLI 辅助查询

新增 Mode 6: 深度命令分析
- 创建 reference 备份目录(80个文档:11 agents + 69 commands)
- 支持简单查询(直接文件查找)和复杂查询(CLI 辅助分析)
- 集成 gemini/qwen 进行跨命令对比、最佳实践、工作流分析
- 添加查询复杂度自动分类和降级策略

更新文档
- SKILL.md: 添加 Mode 6 说明和 Reference Documentation 章节
- implementation-details.md: 添加完整的 Mode 6 实现逻辑
- 版本更新至 v1.3.0

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
catlog22
2025-11-06 16:27:58 +08:00
parent 0ab3d0e1af
commit 1897ba4e82
85 changed files with 30439 additions and 199 deletions

View File

@@ -0,0 +1,204 @@
---
name: breakdown
description: Decompose complex task into subtasks with dependency mapping, creates child task JSONs with parent references and execution order
argument-hint: "task-id"
---
# Task Breakdown Command (/task:breakdown)
## Overview
Breaks down complex tasks into executable subtasks with context inheritance and agent assignment.
## Core Principles
**File Cohesion:** Related files must stay in same task
**10-Task Limit:** Total tasks cannot exceed 10 (triggers re-scoping)
## Core Features
**CRITICAL**: Manual breakdown with safety controls to prevent file conflicts and task limit violations.
### Breakdown Process
1. **Session Check**: Verify active session contains parent task
2. **Task Validation**: Ensure parent is `pending` status
3. **10-Task Limit Check**: Verify breakdown won't exceed total limit
4. **Manual Decomposition**: User defines subtasks with validation
5. **File Conflict Detection**: Warn if same files appear in multiple subtasks
6. **Similar Function Warning**: Alert if subtasks have overlapping functionality
7. **Context Distribution**: Inherit parent requirements and scope
8. **Agent Assignment**: Auto-assign agents based on subtask type
9. **TODO_LIST Update**: Regenerate TODO_LIST.md with new structure
### Breakdown Rules
- Only `pending` tasks can be broken down
- **Manual breakdown only**: Automated breakdown disabled to prevent violations
- Parent becomes `container` status (not executable)
- Subtasks use format: IMPL-N.M (max 2 levels)
- Context flows from parent to subtasks
- All relationships tracked in JSON
- **10-task limit enforced**: Breakdown rejected if total would exceed 10 tasks
- **File cohesion preserved**: Same files cannot be split across subtasks
## Usage
### Basic Breakdown
```bash
/task:breakdown impl-1
```
Interactive process:
```
Task: Build authentication module
Current total tasks: 6/10
MANUAL BREAKDOWN REQUIRED
Define subtasks manually (remaining capacity: 4 tasks):
1. Enter subtask title: User authentication core
Focus files: models/User.js, routes/auth.js, middleware/auth.js
2. Enter subtask title: OAuth integration
Focus files: services/OAuthService.js, routes/oauth.js
FILE CONFLICT DETECTED:
- routes/auth.js appears in multiple subtasks
- Recommendation: Merge related authentication routes
SIMILAR FUNCTIONALITY WARNING:
- "User authentication" and "OAuth integration" both handle auth
- Consider combining into single task
# Use AskUserQuestion for confirmation
AskUserQuestion({
questions: [{
question: "File conflicts and/or similar functionality detected. How do you want to proceed?",
header: "Confirm",
options: [
{ label: "Proceed with breakdown", description: "Accept the risks and create the subtasks as defined." },
{ label: "Restart breakdown", description: "Discard current subtasks and start over." },
{ label: "Cancel breakdown", description: "Abort the operation and leave the parent task as is." }
],
multiSelect: false
}]
})
User selected: "Proceed with breakdown"
Task IMPL-1 broken down:
IMPL-1: Build authentication module (container)
├── IMPL-1.1: User authentication core -> @code-developer
└── IMPL-1.2: OAuth integration -> @code-developer
Files updated: .task/IMPL-1.json + 2 subtask files + TODO_LIST.md
```
## Decomposition Logic
### Agent Assignment
- **Design/Planning** → `@planning-agent`
- **Implementation** → `@code-developer`
- **Testing** → `@code-developer` (type: "test-gen")
- **Test Validation** → `@test-fix-agent` (type: "test-fix")
- **Review** → `@universal-executor` (optional)
### Context Inheritance
- Subtasks inherit parent requirements
- Scope refined for specific subtask
- Implementation details distributed appropriately
## Safety Controls
### File Conflict Detection
**Validates file cohesion across subtasks:**
- Scans `focus_paths` in all subtasks
- Warns if same file appears in multiple subtasks
- Suggests merging subtasks with overlapping files
- Blocks breakdown if critical conflicts detected
### Similar Functionality Detection
**Prevents functional overlap:**
- Analyzes subtask titles for similar keywords
- Warns about potential functional redundancy
- Suggests consolidation of related functionality
- Examples: "user auth" + "login system" → merge recommendation
### 10-Task Limit Enforcement
**Hard limit compliance:**
- Counts current total tasks in session
- Calculates breakdown impact on total
- Rejects breakdown if would exceed 10 tasks
- Suggests re-scoping if limit reached
### Manual Control Requirements
**User-driven breakdown only:**
- No automatic subtask generation
- User must define each subtask title and scope
- Real-time validation during input
- Confirmation required before execution
## Implementation Details
- Complete task JSON schema
- Implementation field structure
- Context inheritance rules
- Agent assignment logic
## Validation
### Pre-breakdown Checks
1. Active session exists
2. Task found in session
3. Task status is `pending`
4. Not already broken down
5. **10-task limit compliance**: Total tasks + new subtasks ≤ 10
6. **Manual mode enabled**: No automatic breakdown allowed
### Post-breakdown Actions
1. Update parent to `container` status
2. Create subtask JSON files
3. Update parent subtasks list
4. Update session stats
5. **Regenerate TODO_LIST.md** with new hierarchy
6. Validate file paths in focus_paths
7. Update session task count
## Examples
### Basic Breakdown
```bash
/task:breakdown impl-1
impl-1: Build authentication (container)
├── impl-1.1: Design schema -> @planning-agent
├── impl-1.2: Implement logic + tests -> @code-developer
└── impl-1.3: Execute & fix tests -> @test-fix-agent
```
## Error Handling
```bash
# Task not found
Task IMPL-5 not found
# Already broken down
Task IMPL-1 already has subtasks
# Wrong status
Cannot breakdown completed task IMPL-2
# 10-task limit exceeded
Breakdown would exceed 10-task limit (current: 8, proposed: 4)
Suggestion: Re-scope project into smaller iterations
# File conflicts detected
File conflict: routes/auth.js appears in IMPL-1.1 and IMPL-1.2
Recommendation: Merge subtasks or redistribute files
# Similar functionality warning
Similar functions detected: "user login" and "authentication"
Consider consolidating related functionality
# Manual breakdown required
Automatic breakdown disabled. Use manual breakdown process.
```
**System ensures**: Manual breakdown control with file cohesion enforcement, similar functionality detection, and 10-task limit compliance

View File

@@ -0,0 +1,152 @@
---
name: create
description: Generate task JSON from natural language description with automatic file pattern detection, scope inference, and dependency analysis
argument-hint: "\"task title\""
---
# Task Create Command (/task:create)
## Overview
Creates new implementation tasks with automatic context awareness and ID generation.
## Core Principles
**Task System:** @~/.claude/workflows/task-core.md
## Core Features
### Automatic Behaviors
- **ID Generation**: Auto-generates IMPL-N format (max 2 levels)
- **Context Inheritance**: Inherits from active workflow session
- **JSON Creation**: Creates task JSON in active session
- **Status Setting**: Initial status = "pending"
- **Agent Assignment**: Suggests agent based on task type
- **Session Integration**: Updates workflow session stats
### Context Awareness
- Validates active workflow session exists
- Avoids duplicate task IDs
- Inherits session requirements and scope
- Suggests task relationships
## Usage
### Basic Creation
```bash
/task:create "Build authentication module"
```
Output:
```
Task created: IMPL-1
Title: Build authentication module
Type: feature
Agent: code-developer
Status: pending
```
### Task Types
- `feature` - New functionality (default)
- `bugfix` - Bug fixes
- `refactor` - Code improvements
- `test` - Test implementation
- `docs` - Documentation
## Task Creation Process
1. **Session Validation**: Check active workflow session
2. **ID Generation**: Auto-increment IMPL-N
3. **Context Inheritance**: Load workflow context
4. **Implementation Setup**: Initialize implementation field
5. **Agent Assignment**: Select appropriate agent
6. **File Creation**: Save JSON to .task/ directory
7. **Session Update**: Update workflow stats
**Task Schema**: See @~/.claude/workflows/task-core.md for complete JSON structure
## Implementation Field Setup
### Auto-Population Strategy
- **Detailed info**: Extract from task description and scope
- **Missing info**: Mark `pre_analysis` as multi-step array format for later pre-analysis
- **Basic structure**: Initialize with standard template
### Analysis Triggers
When implementation details incomplete:
```bash
Task requires analysis for implementation details
Suggest running: gemini analysis for file locations and dependencies
```
## File Management
### JSON Task File
- **Location**: `.task/IMPL-[N].json` in active session
- **Content**: Complete task with implementation field
- **Updates**: Session stats only
### Simple Process
1. Validate session and inputs
2. Generate task JSON
3. Update session stats
4. Notify completion
## Context Inheritance
Tasks inherit from:
1. **Active Session** - Requirements and scope from workflow-session.json
2. **Planning Document** - Context from IMPL_PLAN.md
3. **Parent Task** - For subtasks (IMPL-N.M format)
## Agent Assignment
Based on task type and title keywords:
- **Build/Implement** → @code-developer
- **Design/Plan** → @planning-agent
- **Test Generation** → @code-developer (type: "test-gen")
- **Test Execution/Fix** → @test-fix-agent (type: "test-fix")
- **Review/Audit** → @universal-executor (optional, only when explicitly requested)
## Validation Rules
1. **Session Check** - Active workflow session required
2. **Duplicate Check** - Avoid similar task titles
3. **ID Uniqueness** - Auto-increment task IDs
4. **Schema Validation** - Ensure proper JSON structure
## Error Handling
```bash
# No workflow session
No active workflow found
Use: /workflow init "project name"
# Duplicate task
Similar task exists: IMPL-3
Continue anyway? (y/n)
# Max depth exceeded
Cannot create IMPL-1.2.1 (max 2 levels)
Use: IMPL-2 for new main task
```
## Examples
### Feature Task
```bash
/task:create "Implement user authentication"
Created IMPL-1: Implement user authentication
Type: feature
Agent: code-developer
Status: pending
```
### Bug Fix
```bash
/task:create "Fix login validation bug" --type=bugfix
Created IMPL-2: Fix login validation bug
Type: bugfix
Agent: code-developer
Status: pending
```

View File

@@ -0,0 +1,270 @@
---
name: execute
description: Execute task JSON using appropriate agent (@doc-generator/@implementation-agent/@test-agent) with pre-analysis context loading and status tracking
argument-hint: "task-id"
---
## Command Overview: /task:execute
**Purpose**: Executes tasks using intelligent agent selection, context preparation, and progress tracking.
## Execution Modes
- **auto (Default)**
- Fully autonomous execution with automatic agent selection.
- Provides progress updates at each checkpoint.
- Automatically completes the task when done.
- **guided**
- Executes step-by-step, requiring user confirmation at each checkpoint.
- Allows for dynamic adjustments and manual review during the process.
- **review**
- Optional manual review using `@universal-executor`.
- Used only when explicitly requested by user.
## Agent Selection Logic
The system determines the appropriate agent for a task using the following logic.
```pseudo
FUNCTION select_agent(task, agent_override):
// A manual override always takes precedence.
// Corresponds to the --agent=<agent-type> flag.
IF agent_override IS NOT NULL:
RETURN agent_override
// If no override, select based on keywords in the task title.
ELSE:
CASE task.title:
WHEN CONTAINS "Build API", "Implement":
RETURN "@code-developer"
WHEN CONTAINS "Design schema", "Plan":
RETURN "@planning-agent"
WHEN CONTAINS "Write tests", "Generate tests":
RETURN "@code-developer" // type: test-gen
WHEN CONTAINS "Execute tests", "Fix tests", "Validate":
RETURN "@test-fix-agent" // type: test-fix
WHEN CONTAINS "Review code":
RETURN "@universal-executor" // Optional manual review
DEFAULT:
RETURN "@code-developer" // Default agent
END CASE
END FUNCTION
```
## Core Execution Protocol
`Pre-Execution` -> `Execution` -> `Post-Execution`
### Pre-Execution Protocol
`Validate Task & Dependencies` **->** `Prepare Execution Context` **->** `Coordinate with TodoWrite`
- **Validation**: Checks for the task's JSON file in `.task/` and resolves its dependencies.
- **Context Preparation**: Loads task and workflow context, preparing it for the selected agent.
- **Session Context Injection**: Provides workflow directory paths to agents for TODO_LIST.md and summary management.
- **TodoWrite Coordination**: Generates execution Todos and checkpoints, syncing with `TODO_LIST.md`.
### Post-Execution Protocol
`Update Task Status` **->** `Generate Summary` **->** `Save Artifacts` **->** `Sync All Progress` **->** `Validate File Integrity`
- Updates status in the task's JSON file and `TODO_LIST.md`.
- Creates a summary in `.summaries/`.
- Stores outputs and syncs progress across the entire workflow session.
### Task & Subtask Execution Logic
This logic defines how single, multiple, or parent tasks are handled.
```pseudo
FUNCTION execute_task_command(task_id, mode, parallel_flag):
// Handle parent tasks by executing their subtasks.
IF is_parent_task(task_id):
subtasks = get_subtasks(task_id)
EXECUTE_SUBTASK_BATCH(subtasks, mode)
// Handle wildcard execution (e.g., IMPL-001.*)
ELSE IF task_id CONTAINS "*":
subtasks = find_matching_tasks(task_id)
IF parallel_flag IS true:
EXECUTE_IN_PARALLEL(subtasks)
ELSE:
FOR each subtask in subtasks:
EXECUTE_SINGLE_TASK(subtask, mode)
// Default case for a single task ID.
ELSE:
EXECUTE_SINGLE_TASK(task_id, mode)
END FUNCTION
```
### Error Handling & Recovery Logic
```pseudo
FUNCTION pre_execution_check(task):
// Ensure dependencies are met before starting.
IF task.dependencies ARE NOT MET:
LOG_ERROR("Cannot execute " + task.id)
LOG_INFO("Blocked by: " + unmet_dependencies)
HALT_EXECUTION()
FUNCTION on_execution_failure(checkpoint):
// Provide user with recovery options upon failure.
LOG_WARNING("Execution failed at checkpoint " + checkpoint)
PRESENT_OPTIONS([
"Retry from checkpoint",
"Retry from beginning",
"Switch to guided mode",
"Abort execution"
])
AWAIT user_input
// System performs the selected action.
END FUNCTION
```
### Simplified Context Structure (JSON)
This is the simplified data structure loaded to provide context for task execution.
```json
{
"task": {
"id": "IMPL-1",
"title": "Build authentication module",
"type": "feature",
"status": "active",
"agent": "code-developer",
"context": {
"requirements": ["JWT authentication", "OAuth2 support"],
"scope": ["src/auth/*", "tests/auth/*"],
"acceptance": ["Module handles JWT tokens", "OAuth2 flow implemented"],
"inherited_from": "WFS-user-auth"
},
"relations": {
"parent": null,
"subtasks": ["IMPL-1.1", "IMPL-1.2"],
"dependencies": ["IMPL-0"]
},
"implementation": {
"files": [
{
"path": "src/auth/login.ts",
"location": {
"function": "authenticateUser",
"lines": "25-65",
"description": "Main authentication logic"
},
"original_code": "// Code snippet extracted via gemini analysis",
"modifications": {
"current_state": "Basic password authentication only",
"proposed_changes": [
"Add JWT token generation",
"Implement OAuth2 callback handling",
"Add multi-factor authentication support"
],
"logic_flow": [
"validateCredentials() ───► checkUserExists()",
"◊─── if password ───► generateJWT() ───► return token",
"◊─── if OAuth ───► validateOAuthCode() ───► exchangeForToken()",
"◊─── if MFA ───► sendMFACode() ───► awaitVerification()"
],
"reason": "Support modern authentication standards and security requirements",
"expected_outcome": "Comprehensive authentication system supporting multiple methods"
}
}
],
"context_notes": {
"dependencies": ["jsonwebtoken", "passport", "speakeasy"],
"affected_modules": ["user-session", "auth-middleware", "api-routes"],
"risks": [
"Breaking changes to existing login endpoints",
"Token storage and rotation complexity",
"OAuth provider configuration dependencies"
],
"performance_considerations": "JWT validation adds ~10ms per request, OAuth callbacks may timeout",
"error_handling": "Ensure sensitive authentication errors don't leak user enumeration data"
},
"pre_analysis": [
{
"action": "analyze patterns",
"template": "~/.claude/workflows/cli-templates/prompts/analysis/02-analyze-code-patterns.txt",
"method": "gemini"
}
]
}
},
"workflow": {
"session": "WFS-user-auth",
"phase": "IMPLEMENT",
"session_context": {
"workflow_directory": ".workflow/WFS-user-auth/",
"todo_list_location": ".workflow/WFS-user-auth/TODO_LIST.md",
"summaries_directory": ".workflow/WFS-user-auth/.summaries/",
"task_json_location": ".workflow/WFS-user-auth/.task/"
}
},
"execution": {
"agent": "code-developer",
"mode": "auto",
"attempts": 0
}
}
```
### Agent-Specific Context
Different agents receive context tailored to their function, including implementation details:
**`@code-developer`**:
- Complete implementation.files array with file paths and locations
- original_code snippets and proposed_changes for precise modifications
- logic_flow diagrams for understanding data flow
- Dependencies and affected modules for integration planning
- Performance and error handling considerations
**`@planning-agent`**:
- High-level requirements, constraints, success criteria
- Implementation risks and mitigation strategies
- Architecture implications from implementation.context_notes
**`@test-fix-agent`**:
- Test files to execute from task.context.focus_paths
- Source files to fix from implementation.files[].path
- Expected behaviors from implementation.modifications.logic_flow
- Error conditions to validate from implementation.context_notes.error_handling
- Performance requirements from implementation.context_notes.performance_considerations
**`@universal-executor`**:
- Used for optional manual reviews when explicitly requested
- Code quality standards and implementation patterns
- Security considerations from implementation.context_notes.risks
- Dependency validation from implementation.context_notes.dependencies
- Architecture compliance checks
### Simplified File Output
- **Task JSON File (`.task/<task-id>.json`)**: Updated with status and last attempt time only.
- **Session File (`workflow-session.json`)**: Updated task stats (completed count).
- **Summary File**: Generated in `.summaries/` upon completion (optional).
### Simplified Summary Template
Optional summary file generated at `.summaries/IMPL-[task-id]-summary.md`.
```markdown
# Task Summary: IMPL-1 Build Authentication Module
## What Was Done
- Created src/auth/login.ts with JWT validation
- Added tests in tests/auth.test.ts
## Execution Results
- **Agent**: code-developer
- **Status**: completed
## Files Modified
- `src/auth/login.ts` (created)
- `tests/auth.test.ts` (created)
```

View File

@@ -0,0 +1,432 @@
---
name: replan
description: Update task JSON with new requirements or batch-update multiple tasks from verification report, tracks changes in task-changes.json
argument-hint: "task-id [\"text\"|file.md] | --batch [verification-report.md]"
allowed-tools: Read(*), Write(*), Edit(*), TodoWrite(*), Glob(*), Bash(*)
---
# Task Replan Command (/task:replan)
## Overview
Replans individual tasks or batch processes multiple tasks with change tracking and backup management.
**Modes**:
- **Single Task Mode**: Replan one task with specific changes
- **Batch Mode**: Process multiple tasks from action-plan verification report
## Core Principles
**Task System:** @~/.claude/workflows/task-core.md
## Key Features
- **Single/Batch Operations**: Single task or multiple tasks from verification report
- **Multiple Input Sources**: Text, files, or verification report
- **Backup Management**: Automatic backup of previous versions
- **Change Documentation**: Track all modifications
- **Progress Tracking**: TodoWrite integration for batch operations
**CRITICAL**: Validates active session before replanning
## Operation Modes
### Single Task Mode
#### Direct Text (Default)
```bash
/task:replan IMPL-1 "Add OAuth2 authentication support"
```
#### File-based Input
```bash
/task:replan IMPL-1 updated-specs.md
```
Supports: .md, .txt, .json, .yaml
#### Interactive Mode
```bash
/task:replan IMPL-1 --interactive
```
Guided step-by-step modification process with validation
### Batch Mode
#### From Verification Report
```bash
/task:replan --batch ACTION_PLAN_VERIFICATION.md
```
**Workflow**:
1. Parse verification report to extract replan recommendations
2. Create TodoWrite task list for all modifications
3. Process each task sequentially with confirmation
4. Track progress and generate summary report
**Auto-detection**: If input file contains "Action Plan Verification Report" header, automatically enters batch mode
## Replanning Process
### Single Task Process
1. **Load & Validate**: Read task JSON and validate session
2. **Parse Input**: Process changes from input source
3. **Create Backup**: Save previous version to backup folder
4. **Update Task**: Modify JSON structure and relationships
5. **Save Changes**: Write updated task and increment version
6. **Update Session**: Reflect changes in workflow stats
### Batch Process
1. **Parse Verification Report**: Extract all replan recommendations
2. **Initialize TodoWrite**: Create task list for tracking
3. **For Each Task**:
- Mark todo as in_progress
- Load and validate task JSON
- Create backup
- Apply recommended changes
- Save updated task
- Mark todo as completed
4. **Generate Summary**: Report all changes and backup locations
## Backup Management
### Backup Tracking
Tasks maintain backup history:
```json
{
"id": "IMPL-1",
"version": "1.2",
"replan_history": [
{
"version": "1.2",
"reason": "Add OAuth2 support",
"input_source": "direct_text",
"backup_location": ".task/backup/IMPL-1-v1.1.json",
"timestamp": "2025-10-17T10:30:00Z"
}
]
}
```
**Complete schema**: See @~/.claude/workflows/task-core.md
### File Structure
```
.task/
├── IMPL-1.json # Current version
├── backup/
│ ├── IMPL-1-v1.0.json # Original version
│ ├── IMPL-1-v1.1.json # Previous backup
│ └── IMPL-1-v1.2.json # Latest backup
└── [new subtasks as needed]
```
**Backup Naming**: `{task-id}-v{version}.json`
## Implementation Updates
### Change Detection
Tracks modifications to:
- Files in implementation.files array
- Dependencies and affected modules
- Risk assessments and performance notes
- Logic flows and code locations
### Analysis Triggers
May require gemini re-analysis when:
- New files need code extraction
- Function locations change
- Dependencies require re-evaluation
## Document Updates
### Planning Document
May update IMPL_PLAN.md sections when task structure changes significantly
### TODO List Sync
If TODO_LIST.md exists, synchronizes:
- New subtasks (with [ ] checkbox)
- Modified tasks (marked as updated)
- Removed subtasks (deleted from list)
## Change Documentation
### Change Summary
Generates brief change log with:
- Version increment (1.1 → 1.2)
- Input source and reason
- Key modifications made
- Files updated/created
- Backup location
## Session Updates
Updates workflow-session.json with:
- Modified task tracking
- Task count changes (if subtasks added/removed)
- Last modification timestamps
## Rollback Support
```bash
/task:replan IMPL-1 --rollback v1.1
Rollback to version 1.1:
- Restore task from backup/.../IMPL-1-v1.1.json
- Remove new subtasks if any
- Update session stats
# Use AskUserQuestion for confirmation
AskUserQuestion({
questions: [{
question: "Are you sure you want to roll back this task to a previous version?",
header: "Confirm",
options: [
{ label: "Yes, rollback", description: "Restore the task from the selected backup." },
{ label: "No, cancel", description: "Keep the current version of the task." }
],
multiSelect: false
}]
})
User selected: "Yes, rollback"
Task rolled back to version 1.1
```
## Batch Processing with TodoWrite
### Progress Tracking
When processing multiple tasks, automatically creates TodoWrite task list:
```markdown
**Batch Replan Progress**:
- [x] IMPL-002: Add FR-12 draft saving acceptance criteria
- [x] IMPL-003: Add FR-14 history tracking acceptance criteria
- [ ] IMPL-004: Add FR-09 response surface explicit coverage
- [ ] IMPL-008: Add NFR performance validation steps
```
### Batch Report
After completion, generates summary:
```markdown
## Batch Replan Summary
**Total Tasks**: 4
**Successful**: 3
**Failed**: 1
**Skipped**: 0
### Changes Made
- IMPL-002 v1.0 → v1.1: Added FR-12 acceptance criteria
- IMPL-003 v1.0 → v1.1: Added FR-14 acceptance criteria
- IMPL-004 v1.0 → v1.1: Added FR-09 explicit coverage
### Backups Created
- .task/backup/IMPL-002-v1.0.json
- .task/backup/IMPL-003-v1.0.json
- .task/backup/IMPL-004-v1.0.json
### Errors
- IMPL-008: File not found (task may have been renamed)
```
## Examples
### Single Task - Text Input
```bash
/task:replan IMPL-1 "Add OAuth2 authentication support"
Processing changes...
Proposed updates:
+ Add OAuth2 integration
+ Update authentication flow
# Use AskUserQuestion for confirmation
AskUserQuestion({
questions: [{
question: "Do you want to apply these changes to the task?",
header: "Apply",
options: [
{ label: "Yes, apply", description: "Create new version with these changes." },
{ label: "No, cancel", description: "Discard changes and keep current version." }
],
multiSelect: false
}]
})
User selected: "Yes, apply"
Version 1.2 created
Context updated
Backup saved to .task/backup/IMPL-1-v1.1.json
```
### Single Task - File Input
```bash
/task:replan IMPL-2 requirements.md
Loading requirements.md...
Applying specification changes...
Task updated with new requirements
Version 1.1 created
Backup saved to .task/backup/IMPL-2-v1.0.json
```
### Batch Mode - From Verification Report
```bash
/task:replan --batch .workflow/WFS-{session}/.process/ACTION_PLAN_VERIFICATION.md
Parsing verification report...
Found 4 tasks requiring replanning:
- IMPL-002: Add FR-12 draft saving acceptance criteria
- IMPL-003: Add FR-14 history tracking acceptance criteria
- IMPL-004: Add FR-09 response surface explicit coverage
- IMPL-008: Add NFR performance validation steps
Creating task tracking list...
Processing IMPL-002...
Backup created: .task/backup/IMPL-002-v1.0.json
Updated to v1.1
Processing IMPL-003...
Backup created: .task/backup/IMPL-003-v1.0.json
Updated to v1.1
Processing IMPL-004...
Backup created: .task/backup/IMPL-004-v1.0.json
Updated to v1.1
Processing IMPL-008...
Backup created: .task/backup/IMPL-008-v1.0.json
Updated to v1.1
Batch replan completed: 4/4 successful
Summary report saved
```
### Batch Mode - Auto-detection
```bash
# If file contains "Action Plan Verification Report", auto-enters batch mode
/task:replan ACTION_PLAN_VERIFICATION.md
Detected verification report format
Entering batch mode...
[same as above]
```
## Error Handling
### Single Task Errors
```bash
# Task not found
Task IMPL-5 not found
Check task ID with /workflow:status
# Task completed
Task IMPL-1 is completed (cannot replan)
Create new task for additional work
# File not found
File requirements.md not found
Check file path
# No input provided
Please specify changes needed
Provide text, file, or verification report
```
### Batch Mode Errors
```bash
# Invalid verification report
File does not contain valid verification report format
Check report structure or use single task mode
# Partial failures
Batch completed with errors: 3/4 successful
Review error details in summary report
# No replan recommendations found
Verification report contains no replan recommendations
Check report content or use /workflow:action-plan-verify first
```
## Batch Mode Integration
### Input Format Expectations
Batch mode parses verification reports looking for:
1. **Required Actions Section**: Commands like `/task:replan IMPL-X "changes"`
2. **Findings Table**: Task IDs with recommendations
3. **Next Actions Section**: Specific replan commands
**Example Patterns**:
```markdown
#### 1. HIGH Priority - Address FR Coverage Gaps
/task:replan IMPL-004 "
Add explicit acceptance criteria:
- FR-09: Response surface 3D visualization
"
#### 2. MEDIUM Priority - Enhance NFR Coverage
/task:replan IMPL-008 "
Add performance testing:
- NFR-01: Load test API endpoints
"
```
### Extraction Logic
1. Scan for `/task:replan` commands in report
2. Extract task ID and change description
3. Group by priority (HIGH, MEDIUM, LOW)
4. Process in priority order with TodoWrite tracking
### Confirmation Behavior
- **Default**: Confirm each task before applying
- **With `--auto-confirm`**: Apply all changes without prompting
```bash
/task:replan --batch report.md --auto-confirm
```
## Implementation Details
### Backup Management
```typescript
// Backup file naming convention
const backupPath = `.task/backup/${taskId}-v${previousVersion}.json`;
// Backup metadata in task JSON
{
"replan_history": [
{
"version": "1.2",
"timestamp": "2025-10-17T10:30:00Z",
"reason": "Add FR-09 explicit coverage",
"input_source": "batch_verification_report",
"backup_location": ".task/backup/IMPL-004-v1.1.json"
}
]
}
```
### TodoWrite Integration
```typescript
// Initialize tracking for batch mode
TodoWrite({
todos: taskList.map(task => ({
content: `${task.id}: ${task.changeDescription}`,
status: "pending",
activeForm: `Replanning ${task.id}`
}))
});
// Update progress during processing
TodoWrite({
todos: updateTaskStatus(taskId, "in_progress")
});
// Mark completed
TodoWrite({
todos: updateTaskStatus(taskId, "completed")
});
```