Skill RSI is a recursive self-improvement loop for Agent Skills, grounded in evals. Standalone or Codex plugin.
2 files for Claude Code, Codex and OpenCode: mermaid-diagrams, Skill-RSI AGENTS.md — 780 tokens loaded in every session.
AGENTS.md A 780 tok .agents/skills/mermaid-diagrams/SKILL.md A 143 tok These files are justinwetch/Skill-RSI's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.