# Setup Ralph

Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in...

- Repository: https://github.com/glittercowboy/taches-cc-resources (1986 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-04-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add glittercowboy/taches-cc-resources --skill setup-ralph -g -a claude-code -y`
Codex: `npx skills add glittercowboy/taches-cc-resources --skill setup-ralph -g -a codex -y`
Cursor: `npx skills add glittercowboy/taches-cc-resources --skill setup-ralph -g -a cursor -y`
Gemini CLI: `npx skills add glittercowboy/taches-cc-resources --skill setup-ralph -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add glittercowboy/taches-cc-resources`

## Description

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

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

<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.

### Three Phases, Two Prompts, One Loop

1. **Planning Phase**: Gap analysis (specs vs code) outputs prioritized TODO list, no implementation, no commits
2. **Building Phase**: Picks tasks from plan, implements, runs tests (backpressure), commits
3. **Observation Phase**: You sit on the loop, not in it, engineer the setup and environment that allows Ralph to succeed

### Key Principles

**Your Role**: Ralph does all the work, including deciding which planned work to implement next and how to implement it. Your job is to engineer the environment.

**Backpressure**: Create backpressure via tests, typechecks, lints, builds that reject invalid/unacceptable work.

**Observation**: Watch, especially early on. Prompts evolve through observed failure patterns.

**Context Efficiency**: With ~176K usable tokens from 200K window, allocating 40-60% to "smart zone" means tight tasks with one task per loop achieves maximum context utilization.

**File I/O as State**: The plan file persists between isolated loop executions, serving as deterministic shared state, no sophisticated orchestration needed.

The rest: https://github.com/glittercowboy/taches-cc-resources/blob/HEAD/skills/setup-ralph/SKILL.md