Local-first MCP review graph extracted from Rordi: bounded agent review, attributable evidence, and explicit shipping decisions.
2 files for Codex, OpenCode and Claude Code: loopbreaker AGENTS.md, loopbreaker CLAUDE.md — 778 tokens loaded in every session.
AGENTS.md A 610 tok CLAUDE.md A 168 tok These files are rordi-ai/loopbreaker's own configuration — they tell Codex, OpenCode and Claude Code 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.