In my experience, a vague or outdated Agent.md causes more damage than not having one, because people assume it is accurate and stop asking questions. A simple, honest doc that is kept current is far more useful than a detailed one nobody maintains.

One approach (Claude Code) is to evolve it over time. Start small and run /insights often and use that to refine the CLAUDE.md as needed.

https://github.com/trailofbits/claude-code-config?tab=readme...

Yes, zero instructions are better than wrong instructions because outdated or incorrect context actively forces the AI to write broken code.

Start with nothing, and only add a single sentence to your Agent.md after the AI repeatedly makes the same specific mistake.

My approach is to keep them minimal. Make them a table of contents and spark notes, spread them across the repo, keep them up to date as the repo changes.

Something is better than nothing. It's pretty hard to have bad ones, also takes effort to craft good ones. The bad ones are the ones with incorrect information.