From ralph-wiggum
Explains Ralph Wiggum technique for iterative AI development loops via repeated prompts and self-reference, and lists commands /ralph-loop and /cancel-ralph.
How this command is triggered — by the user, by Claude, or both
Slash command
/ralph-wiggum:helpThe summary Claude sees in its command listing — used to decide when to auto-load this command
# Ralph Wiggum Plugin Help Please explain the following to the user: ## What is the Ralph Wiggum Technique? The Ralph Wiggum technique is an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley. **Core concept:** The same prompt is fed to Claude repeatedly. The "self-referential" aspect comes from Claude seeing its own previous work in the files and git history, not from feeding output back as input. **Each iteration:** 1. Claude receives the SAME prompt 2. Works on the task, modifying files 3. Tries to exit 4. Stop hook intercepts and feeds t...
Please explain the following to the user:
The Ralph Wiggum technique is an iterative development methodology based on continuous AI loops, pioneered by Geoffrey Huntley.
Core concept:
while :; do
cat PROMPT.md | claude-code --continue
done
The same prompt is fed to Claude repeatedly. The "self-referential" aspect comes from Claude seeing its own previous work in the files and git history, not from feeding output back as input.
Each iteration:
The technique is described as "deterministically bad in an undeterministic world" - failures are predictable, enabling systematic improvement through prompt tuning.
Start a Ralph loop in your current session.
Usage:
/ralph-loop "Refactor the cache layer" --max-iterations 20
/ralph-loop "Add tests" --completion-promise "TESTS COMPLETE"
Options:
--max-iterations <n> - Max iterations before auto-stop--completion-promise <text> - Promise phrase to signal completionHow it works:
.claude/.ralph-loop.local.md state fileCancel an active Ralph loop (removes the loop state file).
Usage:
/cancel-ralph
How it works:
.claude/.ralph-loop.local.mdTo signal completion, Claude must output a <promise> tag:
<promise>TASK COMPLETE</promise>
The stop hook looks for this specific tag. Without it (or --max-iterations), Ralph runs infinitely.
The "loop" doesn't mean Claude talks to itself. It means:
/ralph-loop "Fix the token refresh logic in auth.ts. Output <promise>FIXED</promise> when all tests pass." --completion-promise "FIXED" --max-iterations 10
You'll see Ralph:
Good for:
Not good for:
npx claudepluginhub k1lllagt/claude-code --plugin ralph-wiggum/helpExplains the Ralph Wiggum technique for iterative AI development loops using repeated prompts and lists available commands including /wiggum-loop and /cancel-wiggum.
/helpExplains Ralph Loop plugin for iterative AI development via repeated Claude prompts with file self-reference, and lists commands /ralph-loop to start loops and /cancel-ralph to cancel.
/helpExplains the Ralph Wiggum technique for iterative AI development via continuous Claude loops and lists all available Ralph Wiggum plugin commands with usage examples.
/ralph-loopStarts an iterative development loop that repeatedly feeds the same prompt to Claude, enabling incremental improvements across turns. Supports --max-iterations and --completion-promise flags.
/helpDisplays categorized overview of Task Master AI commands including setup, tasks, status, analysis. Accepts arguments for specific command help.