It’s magical incantations that might or might not protect you from bad behavior Claude learned from underqualified RL instructors. A classic instruction I have in CLAUDE.md is „Never delete a test. You are only allowed to replace with a test that covers the same branches.“ and another one „Never mention Claude in a commit message“. Of course those sometimes fail, so I do have a message hook that enforces a certain style of git messages.

> Never mention Claude in a commit message“. Of course those sometimes fail,

It’s hardcoded into the system prompt which is why your CLAUDE.md approach fails. Ended up intercepting it out via proxy

Thanks for this idea!

Why would it be bad to mention Claude in a commit message?

Just because Claude ran the commit command, doesn’t mean it wrote the code. That’s just a nasty marketing hack from Anthropic.

Way too many agent prompt files are just fan fiction or D&D character background documents that have no actual effect on what the agent does =)