Claude-Code-Workflow
JSON-driven multi-agent cadence-team development framework with intelligent CLI orchestration (Gemini/Qwen/Codex), context-first architecture, and automated workflow execution
β¨ Key Features
π― Skill-based WorkflowsFrom π Multi-CLI OrchestrationGemini, Qwen, Codex, Claude - auto-select or manual β‘ Team Architecture v2Role-based agents with inner loop execution π§ Queue SchedulerBackground queue execution service |
π¦ Session Lifecyclestart/resume/complete/sync workflow sessions π₯οΈ Terminal DashboardMulti-terminal grid with execution monitor π¨ Orchestrator EditorTemplate-based workflow visual editing π¬ A2UIAgent-to-User interactive interface |
π New? See Workflow Guide for complete workflow documentation.
π Quick Start
Install CCW
npm install -g claude-code-workflow
ccw install -m Global
Codex Configuration (Required for .codex/skills/)
If you use Codex CLI with the .codex/skills/ workflow skills, add these required features to your ~/.codex/config.toml:
[features]
default_mode_request_user_input = true # Enable request_user_input tool for interactive confirmations
multi_agent = true # Enable multi-agent coordination (spawn_agent, wait, etc.)
multi_agent_v2 = true # Enable v4 agent API (fork_context, task_name, send_message, assign_task, list_agents)
enable_fanout = true # Enable spawn_agents_on_csv for parallel wave execution
These features are required for workflow skills to function properly. Without them, interactive confirmation gates (
request_user_input), subagent orchestration, and CSV-driven parallel execution will not work.
Workflow Skills vs Commands
CCW uses two types of invocations:
| Type | Format | Examples |
|---|---|---|
| Skills | Trigger phrase (no slash) | workflow-lite-plan, brainstorm, workflow-plan |
| Commands | Slash command | /ccw, /workflow/session:start, /issue/new |
Choose Your Workflow Skill
| Skill Trigger | Use Case |
|---|---|
workflow-lite-plan | Lightweight planning, single-module features (hands off to lite-execute) |
workflow-multi-cli-plan | Multi-CLI collaborative analysis |
workflow-plan | Full planning with session persistence |
workflow-tdd-plan | Test-driven development |
workflow-test-fix | Test generation and fix cycles |
brainstorm | Multi-role brainstorming analysis |
Workflow Examples
# Skill triggers (no slash - just describe what you want)
workflow-lite-plan "Add JWT authentication"
workflow-plan "Implement payment gateway integration"
workflow-execute
# Brainstorming
brainstorm "Design real-time collaboration system"
# Slash commands for session management
/workflow/session:start
/workflow/session:resume
/workflow/session:complete
π οΈ CLI Tool Installation
| CLI | Description | Official Docs |
|---|---|---|
| Gemini | Google AI analysis | google-gemini/gemini-cli |
| Codex | OpenAI autonomous coding | openai/codex |
| OpenCode | Open-source multi-model | opencode-ai/opencode |
| Qwen | Alibaba Qwen-Code | QwenLM/Qwen |
π Semantic CLI Invocation
Users can semantically specify CLI tools in prompts - the system automatically invokes the corresponding CLI.
Basic Invocation
| User Prompt | System Action |
|---|---|
| "Use Gemini to analyze the auth module" | Auto-invoke gemini CLI for analysis |
| "Let Codex review this code" | Auto-invoke codex CLI for review |
| "Ask Qwen about performance optimization" | Auto-invoke qwen CLI for consultation |
Multi-CLI Orchestration
| Pattern | User Prompt Example |
|---|---|
| Collaborative | "Use Gemini and Codex to collaboratively analyze security vulnerabilities" |
| Parallel | "Have Gemini, Codex, and Qwen analyze the architecture in parallel" |
| Iterative | "Use Gemini to diagnose, then Codex to fix, iterate until resolved" |
| Pipeline | "Gemini designs the solution, Codex implements, Claude reviews" |
π ACE Tool Configuration
ACE (Augment Context Engine) provides powerful semantic code search.
| Method | Link |
|---|---|
| Official | Augment MCP Documentation |
| Proxy | ace-tool (GitHub) |
π CodexLens Local Search
β οΈ In Development: CodexLens is under iterative optimization. Some features may be unstable.
| Search Mode | Description |
|---|---|
| FTS | Full-text search, based on SQLite FTS5 |
| Semantic | Semantic search, using local embedding models |
| Hybrid | Hybrid search, combining FTS + Semantic + Reranking |
π» CCW CLI Commands
π Recommended Commands
| Command | Description | When to Use |
|---|---|---|
| /ccw | Auto workflow orchestrator - analyzes intent, selects workflow, executes | β General tasks, auto workflow selection |
| /ccw-coordinator | Smart orchestrator - recommends command chains, allows manual adjustment | π§ Complex multi-step workflows |
Quick Examples:
# /ccw - Auto workflow selection
/ccw "Add user authentication"
/ccw "Fix memory leak in WebSocket"
/ccw "Implement with TDD"
# /ccw-coordinator - Manual chain orchestration
/ccw-coordinator "Implement OAuth2 system"
Session Management Commands
/workflow:session:start # Start new workflow session
/workflow:session:resume # Resume paused session
/workflow:session:list # List all sessions
/workflow:session:sync # Sync session work
/workflow:session:complete # Complete session
Issue Workflow Commands
/issue/new # Create new issue
/issue/plan # Plan issue resolution
/issue/queue # Form execution queue
/issue/execute # Execute issue queue
Other CLI Commands
ccw install # Install workflow files
ccw view # Open dashboard
ccw cli -p "..." # Execute CLI tools (Gemini/Qwen/Codex)
ccw upgrade -a # Upgrade all installations
ποΈ Architecture
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Workflow Skills β
β π workflow-lite-plan / workflow-multi-cli-plan (lightweight) β
β π workflow-plan / workflow-tdd-plan (session-based) β
β π§ͺ workflow-test-fix / workflow-test-fix β
β π§ brainstorm (multi-role analysis) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Team Architecture v2 β
β π€ team-worker agents with role-spec based execution β
β π Inner loop framework for sequential task processing β
β π’ Message bus protocol with team coordination β
β π§ Wisdom accumulation (learnings/decisions/conventions) β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Queue Scheduler Service β
β βοΈ Background execution service with API endpoints β
β π Queue management and unified CLI execution settings β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β Terminal Dashboard & Orchestrator β
β π₯οΈ Multi-terminal grid with execution monitor β
β π¨ Template-based workflow editor with slash commands β
β π‘ Real-time agent communication via A2UI β
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
π¦ Project Structure
Claude-Code-Workflow/
βββ .claude/
β βββ agents/ # 22 specialized agents (team-worker, cli-discuss, etc.)
β βββ commands/ # Slash commands (5 categories)
β β βββ ccw.md # Main orchestrator
β β βββ ccw-coordinator.md
β β βββ cli/ # CLI commands (cli-init, codex-review)
β β βββ issue/ # Issue management (plan, execute, queue)
β β βββ memory/ # Memory commands (prepare, style-skill-memory)
β β βββ workflow/ # Workflow commands (session, ui-design, etc.)
β βββ skills/ # 37 modular skills
β βββ workflow-lite-plan/
β βββ workflow-plan/
β βββ workflow-tdd-plan/
β βββ workflow-test-fix/
β βββ brainstorm/
β βββ team-*/ # Team coordination skills
β βββ ...
βββ ccw/
β βββ src/ # TypeScript source code
β β βββ commands/ # CLI command implementations
β β βββ core/ # Core services (a2ui, auth, hooks, routes)
β β βββ mcp-server/ # MCP server implementation
β β βββ tools/ # Tool implementations
β βββ frontend/ # React frontend (Terminal Dashboard, Orchestrator)
βββ codex-lens/ # Local semantic code search engine
βββ docs/ # Documentation
πΌ Team Cadence Control (Beat Model)
The v2 team architecture introduces an event-driven beat model for efficient orchestration:
Beat Cycle (single beat)
======================================================================
Event Coordinator Workers
----------------------------------------------------------------------
callback/resume --> +- handleCallback -+
| mark completed |
| check pipeline |
+- handleSpawnNext -+
| find ready tasks |
| spawn workers ---+--> [team-worker A] Phase 1-5
| (parallel OK) --+--> [team-worker B] Phase 1-5
+- STOP (idle) -----+ |
|
callback <-----------------------------------------+
(next beat) SendMessage + TaskUpdate(completed)
======================================================================
Key Benefits:
- π― Event-driven: Coordinator only wakes when needed (callback/resume)
- β‘ Fast-advance: Simple successors spawn directly without coordinator roundtrip
- π Dynamic pipelines: Generated per-task from dependency graph
- π Parallel execution: Independent tasks run concurrently
π₯οΈ Frontend Highlights
Terminal Dashboard
Multi-terminal grid layout with real-time execution monitoring.
Features:
- π₯οΈ Multi-terminal grid with resizable panes
- π Execution monitor with agent list
- π File sidebar for project navigation
- π― Session grouping by project tags
- π Fullscreen/immersive mode
Orchestrator Editor
Visual workflow template editor with drag-drop.
Features:
- π¨ React Flow-based visual editing
- π¦ Template library with pre-built workflows
- π§ Property panel for node configuration
- β‘ Slash command integration
π Acknowledgments
Impeccable β Design audit methodology, OKLCH color system, anti-AI-slop detection patterns, editorial typography standards, motion/animation token architecture, and vanilla JS interaction patterns. The UI team skills (
team-ui-polish,team-interactive-craft,team-motion-design,team-visual-a11y,team-uidesign,team-ux-improve) draw heavily from Impeccable's design knowledge.gstack β Systematic debugging methodology, security audit frameworks, and release pipeline patterns. The skills
investigate(Iron Law debugging),security-audit(OWASP Top 10 + STRIDE), andship(gated release pipeline) are inspired by gstack's workflow designs.
π€ Contributing
π License
MIT License - see LICENSE
π Links
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found