Individual skill

setup-ralph

Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

skills/setup-ralph/SKILL.md

Read pinned source

Source commit 1757615b99ab789a72ff2d02e9f6112af2a15c04

What was checked

Matches the observed repository HEAD: Yes
Scanner rules are current: Yes
Repository scan complete: No
Skill scan complete: No
Observed behavior: Network or broad shell
Last checked: Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings): 1,987
Repository last updated: Apr 1, 2026
License: MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

anthropic Repository topic
claude Repository topic
claudecode Repository topic
prompts Repository topic
commands Repository topic
skills Repository topic
subagents Repository topic
engineering Derived category

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files

README.mddoc · 4,487 bytes
SKILL.mdcore · 4,406 bytes
SKILL.mdcore · 4,406 bytes
references/operational-learnings.mddoc · 11,142 bytes
references/project-structure.mddoc · 6,423 bytes
references/prompt-design.mddoc · 10,217 bytes
references/ralph-fundamentals.mddoc · 7,097 bytes
references/validation-strategy.mddoc · 8,910 bytes
templates/Dockerfileruns · 793 bytes
templates/PROMPT_build.mddoc · 3,054 bytes
templates/PROMPT_plan.mddoc · 1,509 bytes
templates/loop-docker.shruns · 6,545 bytes
templates/loop.shruns · 17,113 bytes
workflows/customize-loop.mddoc · 5,238 bytes
workflows/setup-new-loop.mddoc · 8,078 bytes
workflows/troubleshoot-loop.mddoc · 6,059 bytes
workflows/understand-ralph.mddoc · 7,109 bytes

Read excerpt


<essential_principles>
## What is Ralph?

Ralph is Geoffrey Huntley's autonomous AI coding methodology that uses iterative loops with task selection, execution, and validation. In its purest form, it's a Bash loop:

```bash
while :; do cat PROMPT.md | claude ; done
```

The loop feeds a prompt file to Claude, the agent completes one task, updates the implementation plan, commits changes, then exits. The loop restarts immediately with fresh context.

### Core Philosophy

**The Ralph Wiggum Technique is deterministically bad in an undeterministic world.** Ralph solves context accumulation by starting each iteration with fresh context—the core insight behind Geoffrey's approach.