Weyoun/chess
1
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Releases Wiki Activity
chess/.claude/commands/automation/auto-agent.md
Christoph Wagner 5ad0700b41 refactor: Consolidate repository structure - flatten from workspace pattern 
Restructured project from nested workspace pattern to flat single-repo layout.
This eliminates redundant nesting and consolidates all project files under version control.

## Migration Summary

**Before:**
```
alex/ (workspace, not versioned)
├── chess-game/ (git repo)
│   ├── js/, css/, tests/
│   └── index.html
└── docs/ (planning, not versioned)
```

**After:**
```
alex/ (git repo, everything versioned)
├── js/, css/, tests/
├── index.html
├── docs/ (project documentation)
├── planning/ (historical planning docs)
├── .gitea/ (CI/CD)
└── CLAUDE.md (configuration)
```

## Changes Made

### Structure Consolidation
- Moved all chess-game/ contents to root level
- Removed redundant chess-game/ subdirectory
- Flattened directory structure (eliminated one nesting level)

### Documentation Organization
- Moved chess-game/docs/ → docs/ (project documentation)
- Moved alex/docs/ → planning/ (historical planning documents)
- Added CLAUDE.md (workspace configuration)
- Added IMPLEMENTATION_PROMPT.md (original project prompt)

### Version Control Improvements
- All project files now under version control
- Planning documents preserved in planning/ folder
- Merged .gitignore files (workspace + project)
- Added .claude/ agent configurations

### File Updates
- Updated .gitignore to include both workspace and project excludes
- Moved README.md to root level
- All import paths remain functional (relative paths unchanged)

## Benefits

✅ **Simpler Structure** - One level of nesting removed
✅ **Complete Versioning** - All documentation now in git
✅ **Standard Layout** - Matches open-source project conventions
✅ **Easier Navigation** - Direct access to all project files
✅ **CI/CD Compatible** - All workflows still functional

## Technical Validation

- ✅ Node.js environment verified
- ✅ Dependencies installed successfully
- ✅ Dev server starts and responds
- ✅ All core files present and accessible
- ✅ Git repository functional

## Files Preserved

**Implementation Files:**
- js/ (3,517 lines of code)
- css/ (4 stylesheets)
- tests/ (87 test cases)
- index.html
- package.json

**CI/CD Pipeline:**
- .gitea/workflows/ci.yml
- .gitea/workflows/release.yml

**Documentation:**
- docs/ (12+ documentation files)
- planning/ (historical planning materials)
- README.md

**Configuration:**
- jest.config.js, babel.config.cjs, playwright.config.js
- .gitignore (merged)
- CLAUDE.md

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

Co-Authored-By: Claude <noreply@anthropic.com>
2025-11-23 10:05:26 +01:00

2.5 KiB
Raw Permalink Blame History

auto agent

Automatically spawn and manage agents based on task requirements.

Usage

npx claude-flow auto agent [options]

Options

  • --task, -t <description> - Task description for agent analysis
  • --max-agents, -m <number> - Maximum agents to spawn (default: auto)
  • --min-agents <number> - Minimum agents required (default: 1)
  • --strategy, -s <type> - Selection strategy: optimal, minimal, balanced
  • --no-spawn - Analyze only, don't spawn agents

Examples

Basic auto-spawning

npx claude-flow auto agent --task "Build a REST API with authentication"

Constrained spawning

npx claude-flow auto agent -t "Debug performance issue" --max-agents 3

Analysis only

npx claude-flow auto agent -t "Refactor codebase" --no-spawn

Minimal strategy

npx claude-flow auto agent -t "Fix bug in login" -s minimal

How It Works

  1. Task Analysis

    • Parses task description
    • Identifies required skills
    • Estimates complexity
    • Determines parallelization opportunities

  2. Agent Selection

    • Matches skills to agent types
    • Considers task dependencies
    • Optimizes for efficiency
    • Respects constraints

  3. Topology Selection

    • Chooses optimal swarm structure
    • Configures communication patterns
    • Sets up coordination rules
    • Enables monitoring

  4. Automatic Spawning

    • Creates selected agents
    • Assigns specific roles
    • Distributes subtasks
    • Initiates coordination

Agent Types Selected

  • Architect: System design, architecture decisions
  • Coder: Implementation, code generation
  • Tester: Test creation, quality assurance
  • Analyst: Performance, optimization
  • Researcher: Documentation, best practices
  • Coordinator: Task management, progress tracking

Strategies

Optimal

  • Maximum efficiency
  • May spawn more agents
  • Best for complex tasks
  • Highest resource usage

Minimal

  • Minimum viable agents
  • Conservative approach
  • Good for simple tasks
  • Lowest resource usage

Balanced

  • Middle ground
  • Adaptive to complexity
  • Default strategy
  • Good performance/resource ratio

Integration with Claude Code

// In Claude Code after auto-spawning
mcp__claude-flow__auto_agent {
  task: "Build authentication system",
  strategy: "balanced",
  maxAgents: 6
}

See Also

  • agent spawn - Manual agent creation
  • swarm init - Initialize swarm manually
  • smart spawn - Intelligent agent spawning
  • workflow select - Choose predefined workflows