pi-ralph-wiggum

Ralph Wiggum - Long-Running Development Loops

Use the ralph_start tool to begin a loop:

ralph_start({
  name: "loop-name",
  taskContent: "# Task\n\n## Goals\n- Goal 1\n\n## Checklist\n- [ ] Item 1\n- [ ] Item 2",
  maxIterations: 50,        // Default: 50
  itemsPerIteration: 3,     // Optional: suggest N items per turn
  reflectEvery: 10          // Optional: reflect every N iterations
})

Loop Behavior

1. Write the task file: Create .ralph/<name>.md with the task content. The tool does NOT create this file—you must write it yourself using the Write tool.
2. Work on the task and update the file each iteration.
3. Record verification evidence (commands run, file paths, outputs) in the task file.
4. Call ralph_done to proceed to the next iteration.
5. Before outputting <promise>COMPLETE</promise>, run a final verification command that an external monitor can rerun from the same worktree.
6. Stop when complete or when max iterations is reached (default 50).

Completion Gate

For build/test/refactor tasks, do not mark complete based only on checked checklist items.

Before emitting <promise>COMPLETE</promise>:

• Preserve any build artifacts, generated files, virtualenvs, or environment setup required by the final verification command.
• Record the exact final command, working directory, relevant environment variables, and output summary in the task file.
• Ensure the command can be rerun by a separate monitor in a fresh shell from the same worktree.
• If a test cannot be rerun externally, mark the item blocked or deferred instead of complete.
• If cleanup removes required verification artifacts, recreate them or update the final command before completion.

Stale Prompt Guard

Before doing any work from a Ralph prompt, reload .ralph/<name>.state.json. If the loop state says "status": "completed", do not edit files, do not run task commands, and do not call ralph_done. Reply briefly that the stale prompt was ignored because the loop is already completed.