Lightweight fast-path instruction package for AI coding agents: reduces unnecessary context loading and adds state-aware validation.
1 file for Codex and OpenCode: adaptive-token-efficiency AGENTS.md — 113 tokens loaded in every session.
AGENTS.md A 113 tok These files are gunwoo55/adaptive-token-efficiency's own configuration — they tell 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.