catlog22/Claude-Code-Workflow
1
0
Fork 0
mirror of https://github.com/catlog22/Claude-Code-Workflow.git synced 2026-02-05 01:50:27 +08:00
Code Issues Packages Projects Releases Wiki Activity
648 Commits 20 Branches 102 Tags
45a082d9636be344d66f4de09ab4104d92ce2014
Commit Graph

648 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
catlog22
45a082d963 refactor(agents): remove Performance Optimization section from cli-explore-agent 
- Removed Performance Optimization section (49 lines)
- Performance considerations should not appear in agent responsibilities
- Deleted caching strategy, parallel execution, and resource limits sections
- Agent documentation now focuses solely on core capabilities and execution flow
 2025-11-18 13:07:47 +08:00
catlog22
19ebb2dc82 fix(workflow): complete path migration and enhance session:complete 
Comprehensive update to eliminate all old path references and implement transactional archival in session:complete.

## Part 1: Complete Path Migration (43 files)

### Files Updated
- action-plan-verify.md
- session/list.md, session/resume.md
- tdd-verify.md, tdd-plan.md, test-*.md
- All brainstorm/*.md files (13 files)
- All tools/*.md files (10 files)
- All ui-design/*.md files (10 files)
- lite-plan.md, lite-execute.md, plan.md

### Path Changes
- `.workflow/.active-*` → `find .workflow/sessions/ -name "WFS-*" -type d`
- `.workflow/WFS-{session}` → `.workflow/sessions/WFS-{session}`
- `.workflow/.archives/` → `.workflow/archives/`
- Removed all marker file operations (touch/rm .active-*)

### Verification
- ✅ 0 references to .active-* markers remain
- ✅ 0 references to direct .workflow/WFS-* paths
- ✅ 0 references to .workflow/.archives/ (dot prefix)

## Part 2: Transactional Archival Enhancement

### session/complete.md - Complete Rewrite

**New Four-Phase Architecture**:

1. **Phase 1: Pre-Archival Preparation**
   - Find active session in .workflow/sessions/
   - Check for existing .archiving marker (resume detection)
   - Create .archiving marker to prevent concurrent operations

2. **Phase 2: Agent Analysis (In-Place)**
   - Agent processes session WHILE STILL in sessions/ directory
   - Pure analysis - no file moves or manifest updates
   - Returns complete metadata package for atomic commit
   - Failure here → session remains active, safe to retry

3. **Phase 3: Atomic Commit**
   - Only executes if Phase 2 succeeds
   - Move session to archives/
   - Update manifest.json
   - Remove .archiving marker
   - All-or-nothing guarantee

4. **Phase 4: Project Registry Update**
   - Extract feature metadata and update project.json

**Key Improvements**:
- **Agent-first, move-second**: Prevents inconsistent states
- **Transactional guarantees**: All-or-nothing file operations
- **Resume capability**: .archiving marker enables safe retry
- **Error recovery**: Comprehensive failure handling documented

**Old Design Flaw (Fixed)**:
- Old: Move first → Agent processes → If agent fails, session moved but metadata incomplete
- New: Agent processes → If success, atomic commit → Guaranteed consistency

## Benefits

1. **Consistency**: All commands use identical path patterns
2. **Robustness**: Transactional archival prevents data loss
3. **Maintainability**: Single source of truth for directory structure
4. **Recoverability**: Failed operations can be safely retried
5. **Alignment**: Closer to OpenSpec's clean three-layer model

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-18 12:39:23 +08:00
catlog22
d9fcdad949 refactor(workflow): migrate to sessions/ subdirectory structure 
Refactor workflow directory structure to improve clarity and robustness by introducing dedicated sessions/ subdirectory for active sessions.

## Directory Structure Changes

### Before (Old Structure)
```
.workflow/
├── .active-WFS-session-1    # Marker files (fragile)
├── WFS-session-1/           # Active sessions mixed with config
├── WFS-session-2/
├── project.json
└── .archives/               # Archived sessions
```

### After (New Structure)
```
.workflow/
├── project.json             # Project metadata
├── sessions/                # [NEW] All active sessions
│   └── WFS-session-1/
└── archives/                # Archived sessions (removed dot prefix)
```

## Key Improvements

1. **Physical Isolation**: Active sessions now in dedicated sessions/ subdirectory
2. **No Marker Files**: Removed fragile .active-* marker file mechanism
3. **Directory-Based State**: Session state determined by directory location
   - In sessions/ = active
   - In archives/ = archived
4. **Simpler Discovery**: `ls .workflow/sessions/` instead of `find .workflow/ -name ".active-*"`
5. **Cleaner Root**: .workflow/ root now only contains project.json, sessions/, archives/

## Path Transformations

| Old Pattern | New Pattern |
|-------------|-------------|
| `find .workflow/ -name ".active-*"` | `find .workflow/sessions/ -name "WFS-*" -type d` |
| `.workflow/WFS-[slug]/` | `.workflow/sessions/WFS-[slug]/` |
| `.workflow/.archives/` | `.workflow/archives/` |
| `touch .workflow/.active-*` | *Removed* |
| `rm .workflow/.active-*` | *Removed* |

## Modified Commands

### session/start.md
- Update session creation path to .workflow/sessions/WFS-*/
- Remove .active-* marker file creation
- Update session discovery to use directory listing
- Updated all 3 modes: Discovery, Auto, Force New

### session/complete.md
- Update session move from sessions/ to archives/
- Remove .active-* marker file deletion
- Update manifest path to archives/manifest.json
- Update agent prompts with new paths

### status.md
- Update session discovery to find .workflow/sessions/
- Update all session file path references
- Update archive query examples

### execute.md
- Update session discovery logic
- Update all task file paths to include sessions/ prefix
- Update context package paths
- Update error handling documentation

## Benefits

- **Robustness**: Eliminates marker file state inconsistency risk
- **Clarity**: Clear separation between active and archived sessions
- **Simplicity**: Session discovery is straightforward directory listing
- **Alignment**: Closer to OpenSpec's three-layer structure (specs/changes/archive)

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-18 11:34:52 +08:00
catlog22
2aacc34c24 refactor(workflow): remove redundant sections, focus on core responsibilities 
Streamline workflow command documentation by removing sections that don't belong to core command responsibilities.

## Changes

### init.md (-46 lines)
- Remove Integration with Existing Commands section
- Remove Performance Considerations section
- Remove Related Commands section
- Focus: Project initialization and analysis only

### session/complete.md (-30 lines)
- Remove Quick Commands reference section
- Remove Archive Query Commands section
- Focus: Session archival and feature registry updates only

### session/start.md (-34 lines)
- Remove Simple Bash Commands reference section
- Keep: Session ID Format (specification/standard)
- Focus: Session creation and discovery only

### status.md (-165 lines)
- Remove Simple Bash Commands section
- Remove Simple Output Format examples
- Remove Project Mode Quick Commands section
- Focus: Status display logic only

### context-gather.md (-29 lines)
- Remove Usage Examples section
- Remove Success Criteria section
- Remove Error Handling table
- Keep: Notes (core design principles)
- Focus: Context gathering orchestration only

## Benefits
- Reduced documentation redundancy (~304 lines removed)
- Clearer command responsibilities and boundaries
- Easier maintenance and updates
- Commands focus on their specific roles in workflow

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-18 11:21:35 +08:00
catlog22
4dafec7054 feat(workflow): add project-level state management with intelligent initialization 
Implement comprehensive project.json system for tracking project state, completed features, and architecture overview.

## New Features

### 1. /workflow:init Command (NEW)
- Independent project initialization command using cli-explore-agent
- Deep Scan mode analyzes: technology stack, architecture, key components, metrics
- Generates project.json with comprehensive overview field
- Supports --regenerate flag to update analysis while preserving features
- One-time initialization with intelligent project cognition

### 2. Enhanced session:start
- Added Step 0: Check project.json existence before session creation
- Auto-calls /workflow:init if project.json missing
- Separated project-level vs session-level initialization responsibilities

### 3. Enhanced session:complete
- Added Phase 3: Update Project Feature Registry
- Extracts feature metadata from IMPL_PLAN.md
- Records completed sessions as features in project.json
- Includes: title, description, tags, timeline, traceability (archive_path, commit_hash)
- Auto-generates feature IDs and tags from implementation plans

### 4. Enhanced status Command
- Added --project flag for project overview mode
- Displays: technology stack, architecture patterns, key components, metrics
- Shows completed features with full traceability
- Provides query commands for feature exploration

### 5. Enhanced context-gather
- Integrated project.json reading in context-search-agent workflow
- Phase 1: Load project.json overview as foundational context
- Phase 3: Populate context-package.json from project.json
- Prioritizes project.json context for architecture and tech stack
- Avoids redundant project analysis on every planning session

## Data Flow
project.json (init) → context-gather → context-package.json → task-generation
session-complete → project.json (features registry)

## Benefits
- Single source of truth for project state
- Efficient context reuse across sessions
- Complete feature traceability and history
- Consistent architectural baseline for all workflows

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-18 11:10:07 +08:00
catlog22
b4e09213e4 fix(installer): prevent deletion of current manifest in Bash version 
Issue:
- In Bash version, new_install_manifest creates file immediately
- save_install_manifest calls remove_old_manifests_for_path
- This deletes ALL manifests for the path, including the new one
- Result: "WARNING: Failed to save installation manifest"

Solution:
- Add current_manifest_file parameter to remove_old_manifests_for_path
- Skip deletion if file matches current manifest
- Pass manifest_file to exclude it from deletion

Note: PowerShell version does not have this issue because it creates
the manifest file AFTER deleting old ones (hashtable → file conversion)
 2025-11-17 22:51:14 +08:00
catlog22
3f7db2fdbc refactor(installer): implement manifest deduplication for same installation paths 
- Add Remove-OldManifestsForPath function to automatically clean old manifests
- Modify Save-InstallManifest to remove old manifests before saving new one
- Update Get-AllInstallManifests to return only latest manifest per installation path
- Apply same strategy to both Install-Claude.ps1 (PowerShell) and Install-Claude.sh (Bash)

Benefits:
- Each installation location registers only once
- Only latest version manifest is retained
- Uninstall UI shows only latest version per location
- Prevents manifest file accumulation
 2025-11-17 22:48:54 +08:00
catlog22
7bcf7f24a3 refactor(workflow): reorganize lite-plan and lite-execute docs for improved clarity 
Restructure lite-plan.md (844→668 lines, -176) and lite-execute.md (597→569 lines, -28) following agent document patterns. Move Data Structures sections to end as reference, simplify repeated content, improve hierarchical organization. All original content preserved.

Key changes:
- Data Structures moved to end (from beginning)
- Simplified Execution Process to avoid duplication
- Improved section hierarchy and flow
- Consistent structure across both documents
v5.8.3 		2025-11-17 22:10:44 +08:00
catlog22
0a6c90c345 refactor(lite-plan): remove timeout and color attributes for streamlined configuration 2025-11-17 22:05:29 +08:00
catlog22
4a0eef03a2 refactor(agents): reorganize cli-planning agent docs for improved clarity and consistency 
Restructure cli-lite-planning-agent.md and cli-planning-agent.md following action-planning-agent.md's clear hierarchical pattern. Merge duplicate content, consolidate sections, and improve readability while preserving all original information.
 2025-11-17 21:51:01 +08:00
catlog22
9cb9b2213b fix(lite-plan): correct executionContext.planObject.tasks type documentation 
Issue found by Gemini analysis:
- executionContext.planObject.tasks was incorrectly documented as string[]
- Actual runtime structure is array of structured task objects (7 fields)
- This caused documentation mismatch between lite-plan and lite-execute

Fix:
- Update executionContext definition to show full task object structure
- Add comment clarifying it's an array of structured objects (7 fields each)
- Aligns with actual implementation and lite-execute consumption logic

Impact: Documentation only (no code changes, runtime behavior was already correct)
 2025-11-17 20:58:51 +08:00
catlog22
0e21c0dba7 feat(lite-plan): upgrade task structure to detailed objects with implementation guidance 
Major changes:
- Add cli-lite-planning-agent.md for generating structured task objects
- Upgrade planObject.tasks from string[] to structured objects with 7 fields:
  - title, file, action, description (what to do)
  - implementation (3-7 steps on how to do it)
  - reference (pattern, files, examples to follow)
  - acceptance (verification criteria)
- Update lite-execute.md to format structured tasks for Agent/Codex execution
- Clean up agent files: remove "how to call me" sections (cli-planning-agent, cli-explore-agent)
- Update lite-plan.md to use cli-lite-planning-agent for Medium/High complexity tasks

Benefits:
- Execution agents receive complete "how to do" guidance instead of vague descriptions
- Each task includes specific file paths, implementation steps, and verification criteria
- Clear separation of concerns: agents only describe what they do, not how they are called
- Architecture validated by Gemini: 100% consistency, no responsibility leakage

Breaking changes: None (backward compatible via task.title || task fallback in lite-execute)
 2025-11-17 20:52:49 +08:00
catlog22
8e4e751655 fix(lite-plan): update user confirmation step to collect four inputs instead of three 2025-11-17 18:38:44 +08:00
catlog22
6ebb1801d1 feat(lite-plan): add detailed data structures and enhanced task JSON export for improved planning context 2025-11-17 17:06:13 +08:00
catlog22
0380cbb7b8 feat(lite-execute, lite-plan): store original user input for enhanced task execution context 2025-11-17 16:34:23 +08:00
catlog22
85ef755c12 feat(lite-execute): add new command for executing tasks with in-memory plans and flexible input modes 2025-11-17 16:16:15 +08:00
catlog22
a5effb9784 refactor(intelligent-tools): clarify write permission and session resume instructions 2025-11-16 23:16:16 +08:00
catlog22
1d766ed4ad fix(lite-plan): clarify executionId definition and tracking flow 
Changes:
1. Initialize previousExecutionResults array in Step 5.1
2. Add id field to executionCalls objects (format: [Method-Index])
3. Add execution loop structure in Step 5.2 showing sequential processing
4. Clarify executionId comes from executionCalls[currentIndex].id
5. Add comments explaining ID storage for result collection

Benefits:
- Clear definition of where executionId comes from
- Explicit initialization of tracking variables
- Better understanding of execution flow and result collection
- Proper context continuity across multiple execution calls
 2025-11-16 23:14:21 +08:00
catlog22
fe0d30256c feat(lite-plan): enhance execution context continuity for multi-call scenarios 
Improvements:
1. Add plan summary in confirmation question for quick review
2. Add previousExecutionResults tracking for multi-execution flows
3. Include execution result collection mechanism after each call
4. Update both Agent and Codex execution prompts with context continuity

Benefits:
- Subsequent executions can see what previous calls completed
- Avoid duplicate work across multiple execution calls
- Better dependency management and task flow
- Clear context propagation: executionId, status, tasks, outputs, notes
v5.8.2 		2025-11-16 23:10:18 +08:00
catlog22
1c416b538d refactor(lite-plan): separate plan display from user confirmation in Phase 4 
Change Phase 4 confirmation flow from single-step to two-step process:
- Step 4.1: Display complete plan as readable text output
- Step 4.2: Collect three-dimensional input via AskUserQuestion

Benefits:
- Clearer plan presentation (not embedded in question)
- Simpler question interface focused on user decisions
- Better user experience with logical separation
 2025-11-16 22:56:48 +08:00
catlog22
81362c14de refactor(lite-plan): enhance execution call tracking and user interaction clarity 2025-11-16 21:52:09 +08:00
catlog22
fa6257ecae refactor(lite-plan): streamline planning execution guidelines and enhance user confirmation process 2025-11-16 21:35:47 +08:00
catlog22
ccb4490ed4 refactor(cli-tools): remove redundant model parameters for improved command clarity 2025-11-16 21:11:16 +08:00
catlog22
58206f1996 refactor(lite-plan): update execution method options for clarity and complexity-based selection 2025-11-16 21:03:16 +08:00
catlog22
564bcb72ea refactor(lite-plan): simplify command format for Codex and Qwen by removing redundant parameters 2025-11-16 20:58:25 +08:00
catlog22
965a80b54e docs: Release v5.8.1 - Lite-Plan Workflow & CLI Tools Enhancement 
Major Features:
- Add /workflow:lite-plan - Lightweight interactive planning workflow
  - Three-dimensional multi-select confirmation
  - Smart code exploration with auto-detection
  - Parallel task execution support
  - Flexible execution (Agent/CLI) with optional code review
- Optimize CLI tools - Remove -m parameter requirement
  - Auto-model-selection for Gemini, Qwen, Codex
  - Updated models: gpt-5.1, gpt-5.1-codex, gpt-5.1-codex-mini

Documentation Updates:
- Update README.md with Lite-Plan usage examples
- Update README_CN.md (Chinese translation)
- Add /workflow:lite-plan to COMMAND_SPEC.md
- Add /workflow:lite-plan to COMMAND_REFERENCE.md
- Update CHANGELOG.md with v5.8.1 release notes
- Update intelligent-tools-strategy.md with model selection guidelines

See CHANGELOG.md for full details.
v5.8.1 		2025-11-16 20:50:10 +08:00
catlog22
8f55bf2ece refactor(intelligent-tools-strategy): remove optional model parameter for improved command clarity and auto-selection guidance 2025-11-16 20:41:39 +08:00
catlog22
a721c50ba3 refactor(lite-plan): enhance three-dimensional confirmation to support multi-select interactions for task approval, execution method, and code review tool 2025-11-15 19:59:38 +08:00
catlog22
4a5c8490b1 refactor(cli-explore-agent): update color scheme from blue to yellow for improved visibility 2025-11-15 18:17:08 +08:00
catlog22
2f0ca988f4 refactor(lite-plan): enhance confirmation process with three-dimensional user interaction and optional code review 2025-11-15 18:13:10 +08:00
catlog22
a45f5e9dc2 refactor(lite-plan): enhance task dependency management and introduce parallel execution guidelines 2025-11-15 17:57:11 +08:00
catlog22
b8dc3018d4 refactor(lite-plan): enhance argument hints and clarify exploration flags in documentation 2025-11-15 17:39:28 +08:00
catlog22
9d4c9ef212 refactor(execute): clarify resume mode description and enhance error handling details 2025-11-15 17:03:35 +08:00
catlog22
d7ffd6ee32 refactor(execute): streamline execution phases and enhance lazy loading strategy 2025-11-15 16:50:51 +08:00
catlog22
02ee426af0 Refactor UI Design Commands: Replace /workflow:ui-design:update with /workflow:ui-design:design-sync 
- Deleted the `list` command for design runs.
- Removed the `update` command and its associated documentation.
- Introduced `design-sync` command to synchronize finalized design system references to brainstorming artifacts.
- Updated command references in `COMMAND_REFERENCE.md`, `GETTING_STARTED.md`, and `GETTING_STARTED_CN.md` to reflect the new command structure.
- Ensured all related documentation and output styles are consistent with the new command naming and functionality.
 2025-11-15 16:30:40 +08:00
catlog22
e76e5bbf5c refactor(enhance-prompt): update description and streamline enhancement pipeline by removing codebase analysis references 2025-11-15 16:19:36 +08:00
catlog22
763c51cb28 refactor(workflow): remove redundant key characteristics and usage examples from lite-plan documentation 2025-11-15 16:13:08 +08:00
catlog22
c7542d95c8 refactor(memory): streamline SKILL.md usage instructions and remove redundant references 2025-11-15 11:22:01 +08:00
catlog22
02bf6e296c feat(memory): enhance SKILL.md template by adding comprehensive jq usage guide and improving package overview 2025-11-15 11:12:23 +08:00
catlog22
f839a3afb8 refactor(memory): remove outdated template file references from style-skill-memory documentation 2025-11-15 11:05:38 +08:00
catlog22
79714edc9a fix(memory): update path to skill-md-template.md for accurate template processing 2025-11-15 10:16:44 +08:00
catlog22
f9c33bd0ba Add SKILL.md template for Style Memory Package with comprehensive jq usage guide and design principles 2025-11-15 10:09:45 +08:00
catlog22
e4a29c0b2e feat(memory): enhance style-skill-memory process by adding design system analysis and dynamic principle generation 2025-11-14 23:53:12 +08:00
catlog22
ca18043b14 feat(memory): optimize style-skill-memory process by simplifying data extraction and enhancing documentation clarity 2025-11-14 23:29:54 +08:00
catlog22
871a02c1f8 feat(memory): enhance style-skill-memory documentation with design principles and jq usage guide 2025-11-14 23:14:53 +08:00
catlog22
3747a7b083 feat(memory): optimize SKILL.md generation with concise structure and embedded jq commands 2025-11-14 15:43:23 +08:00
catlog22
c05dbb2791 docs(skill): update command guide for v5.8.0 release 
Major updates:
- Add UI Design Style Memory workflow documentation
  - /memory:style-skill-memory command
  - /workflow:ui-design:codify-style orchestrator
  - /workflow:ui-design:reference-page-generator
- Add /workflow:lite-plan intelligent planning command (testing)
- Add /memory:code-map-memory code flow mapping (testing)

Agent enhancements:
- Add cli-explore-agent for code exploration
- Enhance cli-planning-agent task generation
- Major ui-design-agent refactoring

Statistics:
- Commands: 69 → 75 (+6)
- Agents: 11 → 13 (+2)
- Reference docs: 80 → 88 files

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

Co-Authored-By: Claude <noreply@anthropic.com>
v5.8.0 		2025-11-12 21:33:23 +08:00
catlog22
167034aaa7 feat(workflow): add --style-skill parameter for enhanced UI design capabilities 2025-11-12 21:27:00 +08:00
catlog22
a8e8412477 feat(agents): add cli-explore-agent and enhance workflow documentation 
Add new cli-explore-agent for code structure analysis and dependency mapping:
- Dual-source strategy (Bash + Gemini CLI) for comprehensive code exploration
- Three analysis modes: quick-scan, deep-scan, dependency-map
- Language-agnostic support (TypeScript, Python, Go, Java, Rust)

Enhance lite-plan workflow documentation:
- Clarify agent call prompts with structured return formats
- Add expected return structures for cli-explore-agent and cli-planning-agent
- Simplify AskUserQuestion usage with clearer examples
- Document data flow between workflow phases

Add code-map-memory command:
- Generate Mermaid code flow diagrams from feature keywords
- Create SKILL packages for code understanding
- Auto-continue workflow with phase skipping

Improve UI design system:
- Add theme colors guide to ui-design-agent
- Enhance code import workflow documentation

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

Co-Authored-By: Claude <noreply@anthropic.com>
 2025-11-12 21:13:42 +08:00
catlog22
158df6acfa feat(workflow): add lite-plan command for intelligent task planning and execution 2025-11-12 20:11:11 +08:00