mirror of
https://github.com/anthropics/claude-code.git
synced 2025-11-28 08:40:27 +08:00
68f90e05ddMigrates the ralph-wiggum plugin from internal marketplace to public marketplace. Implements Geoffrey Huntley's "Ralph Wiggum" technique using Claude Code's Stop hook mechanism for continuous iterative development loops. Key features: - Interactive self-referential AI loops in current session - Stop hook intercepts exit and feeds same prompt back - Iteration tracking and completion promise detection - Max iterations safety limits Changes: - Remove all tmux dependencies and background execution mode - Simplify to interactive-only mode using Stop hooks - Add comprehensive error handling with clear messages - Fix documentation to accurately describe Stop hook mechanism - Add input validation for all command-line arguments - Register plugin in public marketplace Security fixes: - Remove eval usage (command injection vulnerability) - Add numeric validation before arithmetic operations - Remove silent error suppression 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
126 lines
3.2 KiB
Markdown
126 lines
3.2 KiB
Markdown
---
|
|
description: "Explain Ralph Wiggum technique and available commands"
|
|
---
|
|
|
|
# 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:**
|
|
```bash
|
|
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:**
|
|
1. Claude receives the SAME prompt
|
|
2. Works on the task, modifying files
|
|
3. Tries to exit
|
|
4. Stop hook intercepts and feeds the same prompt again
|
|
5. Claude sees its previous work in the files
|
|
6. Iteratively improves until completion
|
|
|
|
The technique is described as "deterministically bad in an undeterministic world" - failures are predictable, enabling systematic improvement through prompt tuning.
|
|
|
|
## Available Commands
|
|
|
|
### /ralph-loop <PROMPT> [OPTIONS]
|
|
|
|
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 completion
|
|
|
|
**How it works:**
|
|
1. Creates `.claude/.ralph-loop.local.md` state file
|
|
2. You work on the task
|
|
3. When you try to exit, stop hook intercepts
|
|
4. Same prompt fed back
|
|
5. You see your previous work
|
|
6. Continues until promise detected or max iterations
|
|
|
|
---
|
|
|
|
### /cancel-ralph
|
|
|
|
Cancel an active Ralph loop (removes the loop state file).
|
|
|
|
**Usage:**
|
|
```
|
|
/cancel-ralph
|
|
```
|
|
|
|
**How it works:**
|
|
- Checks for active loop state file
|
|
- Removes `.claude/.ralph-loop.local.md`
|
|
- Reports cancellation with iteration count
|
|
|
|
---
|
|
|
|
## Key Concepts
|
|
|
|
### Completion Promises
|
|
|
|
To 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.
|
|
|
|
### Self-Reference Mechanism
|
|
|
|
The "loop" doesn't mean Claude talks to itself. It means:
|
|
- Same prompt repeated
|
|
- Claude's work persists in files
|
|
- Each iteration sees previous attempts
|
|
- Builds incrementally toward goal
|
|
|
|
## Example
|
|
|
|
### Interactive Bug Fix
|
|
|
|
```
|
|
/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:
|
|
- Attempt fixes
|
|
- Run tests
|
|
- See failures
|
|
- Iterate on solution
|
|
- In your current session
|
|
|
|
## When to Use Ralph
|
|
|
|
**Good for:**
|
|
- Well-defined tasks with clear success criteria
|
|
- Tasks requiring iteration and refinement
|
|
- Iterative development with self-correction
|
|
- Greenfield projects
|
|
|
|
**Not good for:**
|
|
- Tasks requiring human judgment or design decisions
|
|
- One-shot operations
|
|
- Tasks with unclear success criteria
|
|
- Debugging production issues (use targeted debugging instead)
|
|
|
|
## Learn More
|
|
|
|
- Original technique: https://ghuntley.com/ralph/
|
|
- Ralph Orchestrator: https://github.com/mikeyobrien/ralph-orchestrator
|