[BUG] Claude code is ignoring repository rules against AI contributions

Preflight Checklist

• [x] I have searched existing issues and this hasn't been reported yet
• [x] This is a single bug report (please file separate reports for different bugs)
• [x] I am using the latest version of Claude Code

What's Wrong?

Claude (code) is ignoring AI contribution rules for twpayne/chezmoi which has a blanket ban on AI contribution rules in its code of conduct and about 9 other locations in the repo and documentation.

https://github.com/twpayne/chezmoi/issues/5220 is the ~4th instance in about 3 months because Claude does not pay attention to contribution rules for a repo.

The finding is good but the person who filed it will be banned from the project moving forward precisely because Claude did not even look to see if what was requested was permitted.

I am a trusted contributor to chezmoi, but not the owner. However, I have similarly strict rules against reverse centaurs, which this bug report _most certainly was_.

I've checked this against a work Claude instance in the past and it never checked any of the contribution rules for the repo even though the wording is plainly clear.

What Should Happen?

Claude should either (a) refuse to do _anything_ or (b) loudly warn the user when asked to contribute to (in any way) twpayne/chezmoi and similar repositories by reading codes of conduct, pull request templates, contributing rules, or AI policy documents before doing a single damned thing that will get the user banned.

Error Messages/Logs

Steps to Reproduce

1. Ask Claude to do anything in twpayne/chezmoi.
2. It does not prevent you from doing this.

Claude Model

None

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

2.1.289

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_