Why coding agents ignore your instructions
Your instruction file says stop and the agent does it anyway. The mechanics behind that, and a diagnosis you can run before you rewrite the rule again.
Filtering by topic #agents-md · clear
Your instruction file says stop and the agent does it anyway. The mechanics behind that, and a diagnosis you can run before you rewrite the rule again.
Your AGENTS.md is wrong three weeks later and the agent trusts it. Use dox to regenerate the file from the repo, then review the diff like code.
One root AGENTS.md in a monorepo goes stale and burns context on directories the agent never opens. Here is the nested layout that fixes it.
AGENTS.md tells a coding agent how to work in your repo. DESIGN.md tells it why the code is shaped that way, so it stops undoing your decisions.
AGENTS.md is the README your coding agent reads. What belongs in one, what never does, how CLAUDE.md fits, and a starter template to copy.