Agent skill
ralph-runner
Run long-running autonomous AI agents using PRD-based task scoping.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/ralph-runner
SKILL.md
Ralph Wiggum Agent Runner
Run autonomous coding agents that ship code while you sleep.
When to Use
- Multi-story feature implementation
- Overnight autonomous coding
- Batch processing of related tasks
- When you want AI to work independently
Quick Commands
# Run with current PRD
./scripts/ralph/ralph.sh
# Run with custom PRD
./scripts/ralph/ralph.sh scripts/ralph/my-feature.json
# Watch progress
tail -f scripts/ralph/progress.txt
How It Works
- Agent reads PRD, picks highest priority incomplete story
- Implements ONLY that one story
- Runs build/lint to ensure CI stays green
- Commits work, updates PRD, appends to progress.txt
- Repeats until all stories pass or max iterations
PRD Structure
{
"stories": [
{
"id": "STORY-001",
"title": "User can do X",
"priority": 1,
"passes": false,
"acceptance_criteria": ["..."],
"files_to_modify": ["..."]
}
]
}
Stop Condition
Agent emits <promise>COMPLETE</promise> when all stories pass.
Files
| File | Purpose |
|---|---|
scripts/ralph/ralph.sh |
Runner script |
scripts/ralph/prd.json |
Current PRD |
scripts/ralph/progress.txt |
Progress log |
Reference Files
| Topic | File |
|---|---|
| Full documentation | scripts/ralph/README.md |
| PRD template | scripts/ralph/prd.template.json |
Related Skills
empathy-ledger-codebase- Codebase patternsdeployment-workflow- CI/CD integration
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?