Loop engineering for AI coding agents — shaping the whole run, not one prompt: a Markdown-first overlay of task records, role boundaries, verification evidence, and review gates that holds across multi-hour work
1 file for Codex and OpenCode: agenticloop AGENTS.md — 1,980 tokens loaded in every session.
AGENTS.md C 1,980 tok These files are bartoszarendt/agenticloop'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.