Explain Ralph Wiggum technique and available commands
Executes iterative AI development loops by repeatedly applying the same prompt to continuously refine code.
/plugin marketplace add Arthur742Ramos/ralph-wiggum-windows/plugin install arthur742ramos-ralph-wiggum-windows@Arthur742Ramos/ralph-wiggum-windowsPlease 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 ($true) {
Get-Content PROMPT.md | claude-code --continue
}
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:
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
This is a Windows-compatible fork that uses PowerShell instead of bash/jq:
stop-hook.ps1 (PowerShell)setup-ralph-loop.ps1 (PowerShell)ConvertFrom-JsonTo 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:
Good for:
Not good for: