ralph-loop skillA
ralph-loop is agent-read markdown (skill) from belumume/claude-skills: Activate autonomous Ralph Wiggum loop mode for iterative task completion. Use when you have a well-defined task with clear completion criteria that benefits from persistent, autonomous execution..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Ralph Wiggum Loop Mode Named after the Simpsons character who "never stops despite being confused," this technique runs Claude Code in a loop where the prompt stays the same but the codebase accumulates changes. Each iteration reads previous work and continues until completion. ## When to Use Ralph Mode **Ideal for:** - Well-defined implementation tasks with clear completion criteria - Refactoring or migration work (e.g., React v16 to v19) - Test-driven development cycles (run until tests pass) - Batch processing or repetitive tasks - Overnight autonomous work sessions **Not ideal for:** - Tasks requiring design decisions or human judgment - Exploratory work without clear end states - Tasks where requirements may change mid-execution - First-time implementations where you need to learn the code ## Activation Protocol ### Step 1: Validate Task Suitability Before activating, confirm: - [ ] Task has clear, measurable completion criteria - [ ] Success can be verified programmatically (tests, build, specific file state) - [ ] The work is in a git-tracked directory - [ ] You understand what success looks like ### Step 2: Create State File …
Read the whole file at its exact version.
How to install
mdr add belumume/claude-skills/ralph-loop@v1.0.0mdr add belumume/claude-skills/ralph-loop@sha256:7a19d229656ee2d0Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_mouib2aflrt5k5dn)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-05-23 | 4eda55c | 7,816 B | A | view · diff |
| v1.0.0 | 2026-01-17 | 4e92ee6 | 7,794 B | A | view · diff |
| git:20260117.6ab8021 | 2026-01-17 | 6ab8021 | 7,699 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (7816 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
belumume/claude-skills · 47 stars · license none · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_mouib2aflrt5k5dn GET https://markdownregistry.com/api/v1/resolve?ref=belumume/claude-skills/ralph-loop GET https://markdownregistry.com/api/v1/blob/7a19d229656ee2d01626569280c71c83b329cef42a38ee767bcd43882f975e29
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from belumume/claude-skills
Every file in belumume/claude-skills