docs: forbid assistant references in commit and PR text - #8
Conversation
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 72ae2dce32
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| Never include Claude, Codex, or other AI assistant references in commit subjects | ||
| or bodies, PR titles or descriptions, or PR comments. This includes assistant |
There was a problem hiding this comment.
Allow functional assistant mentions
When an adopting assistant is authorized to request an optional review, this blanket ban prevents it from posting the required @claude or focused @codex request. The documented Claude workflow only starts when a new PR conversation comment contains @claude (docs/code-review.md:33-35, templates/workflows/claude.yml:20-22), so following this new rule makes that supported route unusable. Restrict the prohibition to attribution/credit claims or explicitly exempt operational bot invocations and technical discussion of integrations.
Useful? React with 👍 / 👎.
Make the shared commit and writing rules explicitly forbid assistant names, session links, signatures, attribution, and claims of doing the work in commit messages, PR titles and descriptions, and PR comments. Check the saved PR content after publication and remove references appended by tooling.
Validation:
just checkpassed all 32 tests, and both modified skills passed frontmatter and structure validation. Adopting repositories receive the updated rules after merge and their next task refresh.