Skip to content
  1. Home
  2. Agent skills
  3. ralph-loop

ralph-loop

Loop Claude on one prompt until a completion promise appears

What it is

Implements the Ralph Wiggum technique: /ralph-loop feeds the same prompt repeatedly via a Stop hook until a stated completion promise is output, so the model iterates on its own earlier work.

Good for

  • Iterate until tests pass
  • Grind through a well-specified task
  • Run unattended refactors

Install or run

/plugin install ralph-loop@claude-plugins-official

Command as given in the project README. Read the repository before you run anything on your machine.

Worth knowingCan burn many tokens; set an iteration limit and a clear completion promise.

Sources

The summary is ours, written from the README. Spotted an error? See how we work.

More for automation & ops

See the topic →
  • Computer Use

    NousResearch/hermes-agent

    Drive the desktop background-first and escalate on signal

    SkillGitHub stars: 263k
  • Dynamic Workflow

    NousResearch/hermes-agent

    Plan-in-code fan-outs, adversarial verification and multi-wave runs

    SkillGitHub stars: 263k
  • Watchers

    NousResearch/hermes-agent

    Poll RSS, JSON APIs and GitHub with watermark dedup

    SkillGitHub stars: 263k
  • gstack

    garrytan/gstack

    Garry Tan's Claude Code setup: role-based skills for review, QA and release

    SkillGitHub stars: 141k