ralph-wiggum
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-jkitchin-skillz --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Ralph Wiggum Mode "Me fail English? That's unpossible!" - Ralph Wiggum Ralph Wiggum Mode is an autonomous AI coding loop that enables Claude Code to work continuously on tasks without human intervention. Named after the persistently optimistic Simpsons character, this technique lets Claude work "overnight shifts" while you sleep. ## Key Principle **Progress persists in files and git, not in the LLM's context window.** When context fills up, the loop restarts Claude with fresh context. The new instance picks up from the filesystem state (your code, git history, and task tracking files). ## When to Use This Skill Use Ralph Wiggum mode for: - Overnight feature development - Bug bashes (fixing multiple issues) - Test coverage improvement - Refactoring large codebases - Documentation generation - Any multi-step task you'd like completed while away ## Security Model **CRITICAL: Ralph requires a sandboxed environment.** Ralph uses `--dangerously-skip-permissions` which can: - Delete files without confirmation - Read credentials (~/.ssh, ~/.aws) - Make network requests - Run arbitrary commands **Ralph will REFUSE to start unless it detects:** - Container environment (Docker/Kubernetes) -
- Key Principle
- When to Use This Skill
- Security Model
- Quick Start
- 1. Initialize Ralph in Your Project
- 2. Define Your Work
- 3. Run Ralph (In Sandbox)
- 4. Review Results
- How It Works
- Files Reference
- RALPHPROMPT.md
- IMPLEMENTATIONPLAN.md
- ralph.sh
- ralph-sandbox.sh
Run the init script to scaffold Ralph files Create specs directory for requirements mkdir -p specs Write your requirements cat > specs/my-feature.md << 'EOF' Update the implementation plan cat > IMPLEMENTATION_PLAN.md << 'EOF' With iteration limit Check progress from another terminal tail -f ralph.log
What does the ralph-wiggum skill do?
Autonomous AI coding loop for unattended development - lets Claude work continuously on tasks while you sleep, with mandatory sandbox enforcement for safety
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-jkitchin-skillz --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.