anthropic-ralph-loop
This plugin implements continuous self-referential AI loops using the Ralph Wiggum technique, where Claude repeatedly works on the same prompt within a session until a completion promise is output, leveraging bash Stop hooks to intercept session exits and re-feed prompts. Users can define tasks with clear completion criteria and iteration limits, letting the model iteratively refine code, run tests, and self-correct through file modifications and git history without external orchestration.
Install
Source: https://github.com/EricGrill/agents-skills-plugins/tree/HEAD/plugins/anthropic-ralph-loop
What it's made of
3 commands · 1 hook
- Commands
- 3
- Agents
- 0
- Skills
- 0
- MCP servers
- 0
- Hooks
- 1 · Stop
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
bash- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (EricGrill).