ralph-loop
Interactive self-referential AI loops (the Ralph Wiggum technique) for iterative development until completion.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for ralph-loop, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
Anthropic's official ralph-loop plugin. It implements the Ralph Wiggum technique — Claude repeatedly works on the same task, seeing its previous work each iteration, until the task is complete. Surface is a command that re-invokes the model in a loop over accumulating context.
Key features and capabilities
- Self-referential iteration loop
- Model sees its prior work each pass
- Runs until task completion
Use cases
- Grind a stubborn task to completion iteratively
- Long-running refactors that need repeated passes