Agent skill
mission-ralph
Launch ralph.sh in background. Best for large features (10+ tasks). Automatic execution until completion.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/mission-ralph
SKILL.md
/mission-ralph - Automatic Background Execution
Launch the Ralph loop in background. Runs automatically until all tasks complete or a critical blocker halts execution.
The Process
- Validate feature - Check feature exists and has tasks
- Activate feature - Run
bd update FEATURE_ID --status in_progress - Ask launch mode - "Start Ralph in mprocs (visible) or background (invisible)?"
- Launch Ralph:
- If background: Run the script directly
- If visible: Print the command for user to run in a new terminal window
- Inform user - Tell them how to monitor progress
- Exit - HOUSTON's job is done, Ralph takes over
Launch Command
bash skills/mission-ralph/scripts/ralph.sh FEATURE_ID &
Or with visible mode (mprocs TUI):
bash skills/mission-ralph/scripts/ralph.sh FEATURE_ID --visible
What Ralph Does
Ralph spawns fresh Pods for each task in a loop:
- Get next ready task via
bd ready - Spawn Pod (Scout -> Worker -> Inspector -> Analyst -> Airlock)
- Handle result (complete, retry, or create blocking bug)
- Continue until no tasks remain or critical halt
Each Pod includes a Scout phase that gathers codebase context before Worker executes.
User Communication
If background mode:
HOUSTON: Ralph loop launched for feature FEATURE_ID.
Ralph runs automatically in background.
Check progress: /capcom
You'll be notified on:
- Feature completion
- Critical blocker (requires intervention)
Safe to close this session.
If visible mode:
HOUSTON: Run this command in a new terminal window:
bash skills/mission-ralph/scripts/ralph.sh FEATURE_ID --visible
This opens mprocs with live task progress.
Check status anytime: /capcom
Monitoring
/capcom- Check feature status and task progressbd list --parent FEATURE_ID- See all tasksbd ready- See what's next in queuebd dep tree FEATURE_ID- See task hierarchy and status
Exit Codes
| Code | Meaning |
|---|---|
| 0 | Feature complete |
| 1 | Critical blocker - check /capcom |
| 2 | Configuration error |
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?