并行Ralph循环自动化工具

Step 1: Generate PRD
User: "Create a PRD for user authentication"
Claude: [Generates tasks/prd-auth.md]

Step 2: Execute
User: "Start" or "Execute this PRD"
Claude: ralph_start → Task Agent handles everything automatically

# .ralph.yaml
agent:
  backend: cli
  provider: codex
  coAuthor: "GPT-5.3 Codex <noreply@openai.com>"
  
  codex:
    # Path to Codex CLI (default: "codex")
    codexPath: "codex"
    
    # Approval policy for command execution
    # Options: never, on-request, on-failure, untrusted
    approvalPolicy: on-request
    
    # Sandbox mode for filesystem access
    # Options: read-only, workspace-write, danger-full-access
    sandboxMode: workspace-write
    
    # Execution level (L1=Executor, L2=Builder, L3=Autonomous, L4=Specialist)
    level: L2
    
    # Max auto-recovery attempts when stalled
    maxRecoveryAttempts: 2
    
    # Minutes of inactivity before detecting stall
    stallTimeoutMinutes: 5

# .ralph.yaml
agent:
  backend: cli
  provider: claude
  coAuthor: "Claude Opus 4.6 <noreply@anthropic.com>"

  claude:
    claudePath: claude
    additionalFlags: []

agent:
  backend: sdk
  provider: claude # or codex

# Use Claude CLI
agent:
  backend: cli
  provider: claude

# Use Codex CLI (default)
agent:
  backend: cli
  provider: codex

# Use Claude SDK instead
agent:
  backend: sdk
  provider: claude

## [2024-01-15 14:30] US-001: Setup Database Schema
- Used Prisma with PostgreSQL
- Added index on `userId` for faster queries
- Note: Must run `pnpm db:migrate:dev` after schema changes

## [2024-01-15 15:45] US-002: User Registration API
- Reused validation patterns from existing auth module
- BCrypt rounds set to 12 for password hashing
- Integration test requires test database to be running

npm install -g ralph-mcp

git clone https://github.com/G0d2i11a/ralph-mcp.git
cd ralph-mcp
npm install
npm run build

{
  "mcpServers": {
    "ralph": {
      "command": "npx",
      "args": ["ralph-mcp"]
    }
  }
}

{
  "mcpServers": {
    "ralph": {
      "command": "node",
      "args": ["/path/to/ralph-mcp/dist/index.js"]
    }
  }
}

agent:
  backend: cli
  provider: codex
  codex:
    codexPath: codex
    approvalPolicy: never
    sandboxMode: workspace-write
    level: L2

# Optional: switch the runner to Claude CLI instead
# agent:
#   backend: cli
#   provider: claude

# Optional: force the SDK backend instead
# agent:
#   backend: sdk
#   provider: claude

ralph-runner --watch-prds --watch-prds-dir ~/incoming-prds

watchers:
  prdIngestion:
    enabled: true
    watchDir: ~/incoming-prds
    filePattern: ^ez4ielts-.*\.json$
    projectRoot: ~/Project/ez4ielts
    worktree: true

# 1. Create skill directory
mkdir -p .claude/skills/ralph

# 2. Copy the example (adjust path as needed)
cp /path/to/ralph-mcp/SKILL-EXAMPLE.md .claude/skills/ralph/SKILL.md

# 3. Customize quality check commands for your project

## Skills

| Skill | Trigger |
|-------|---------|
| `ralph` | PRD execution (generate PRD → start → auto merge) |

User: Help me finish the Speaking module from TODO.md

Claude: Let me check TODO.md... Found 3 incomplete items:
  - Speaking dialogue practice
  - Speaking scoring optimization
  - Speaking question bank

I'll create 3 PRDs...
[Generates prd-speaking-dialogue.md]
[Generates prd-speaking-scoring.md]
[Generates prd-speaking-qb.md]

User: Start

Claude:
[ralph_start × 3]
[Task Agent × 3 running in parallel]

3 PRDs started. They'll auto-merge when complete.
Use ralph_status to check progress.

--- Some time later ---

User: Progress?

Claude: [ralph_status]
✅ prd-speaking-dialogue - Merged
✅ prd-speaking-scoring - Merged
🔄 prd-speaking-qb - US-003/005 in progress

User: 👍

// 1. Start PRD execution
ralph_start({ prdPath: "tasks/prd-feature.md" })

// 2. Check status anytime
ralph_status()

// 3. Manual merge if needed (usually automatic)
ralph_merge({ branch: "ralph/prd-feature" })

// Start PRD execution.
// Default Runner mode returns null agentPrompt and lets ralph-runner claim it.
ralph_start({ prdPath: "tasks/prd-feature.md" })

// Start multiple PRDs in parallel
ralph_batch_start({ prdPaths: ["tasks/prd-a.md", "tasks/prd-b.md"] })

// View all PRD status
ralph_status()

// Get single PRD details
ralph_get({ branch: "ralph/prd-feature" })

// Update User Story status (called by agent)
ralph_update({ branch: "ralph/prd-feature", storyId: "US-1", passes: true, notes: "..." })

// Stop execution
ralph_stop({ branch: "ralph/prd-feature" })

// Merge to main
ralph_merge({ branch: "ralph/prd-feature" })

// Record Task agent ID (for tracking)
ralph_set_agent_id({ branch: "ralph/prd-feature", agentTaskId: "abc123" })

// Retry a failed execution
ralph_retry({ branch: "ralph/prd-feature" })

// Reset stagnation counters (after manual fix)
ralph_reset_stagnation({ branch: "ralph/prd-feature" })

---
title: User Authentication
priority: high
---

# User Authentication

Implement user login and registration.

## User Stories

### US-1: User Registration

Users can create new accounts.

**Acceptance Criteria:**
- [ ] Email validation
- [ ] Password strength check
- [ ] Confirmation email sent

### US-2: User Login

Users can log into their accounts.

**Acceptance Criteria:**
- [ ] Email/password authentication
- [ ] Remember me option
- [ ] Forgot password flow

{
  "repository": "~/Project/my-app",
  "branchName": "ralph/prd-feature",
  "description": "Implement feature",
  "dependencies": ["ralph/prd-base"],
  "userStories": [
    {
      "id": "US-001",
      "title": "Feature",
      "description": "As a user, I want the feature, so that I can work faster.",
      "acceptanceCriteria": ["Works end to end"],
      "priority": 1
    }
  ]
}

ralph_start({
  prdPath: "tasks/prd-feature.md",
  autoMerge: true,           // Auto-merge when done
  notifyOnComplete: true,    // Windows Toast notification
  onConflict: "auto_theirs"  // Prefer main on conflicts
})

ralph_batch_start({
  prdPaths: [
    "tasks/prd-auth.md",
    "tasks/prd-dashboard.md",
    "tasks/prd-settings.md"
  ],
  contextInjectionPath: "CLAUDE.md",
  autoMerge: true
})

// Retry a failed execution
ralph_retry({ branch: "ralph/prd-feature" })
// Returns: { success, branch, message, previousStatus, agentPrompt, progress }

// Reset counters and resume
ralph_reset_stagnation({ branch: "ralph/prd-feature" })

// Reset counters only (keep failed status)
ralph_reset_stagnation({ branch: "ralph/prd-feature", resumeExecution: false })