| name | pr-comment-attribution |
| description | Prefix every PR comment the agent posts with the literal "[Claude Code ๐ค]" marker so reviewers can tell the agent's replies apart from the account owner's own. Use whenever posting a PR review-thread reply, an inline review comment, or a top-level issue comment on a PR โ via gh pr comment, gh api .../comments, or the GitHub MCP comment tools. |
PR Comment Attribution
The agent posts PR comments under the human account owner's GitHub identity. Without a marker, reviewers cannot tell an agent-authored reply from one the account owner wrote themselves. Every comment the agent posts therefore begins with the literal prefix:
[Claude Code ๐ค]
Exactly that โ square brackets, the words Claude Code, a space, the robot emoji. Same capitalization and spacing every time.
Where it applies
Every PR comment the agent posts, with no exceptions:
- Per-thread inline replies on review comments
- Top-level issue comments on a PR
- Review-summary bodies
โฆacross whichever tool posts it:
gh pr comment (top-level issue comment)gh pr review --comment / --approve / --request-changes (review-summary body)gh api repos/<owner>/<repo>/issues/<n>/comments and .../pulls/<n>/comments/<id>/replies- the GitHub MCP tools (
add_reply_to_pull_request_comment, add_issue_comment, pull_request_review_write, etc.)
Example
[Claude Code ๐ค] Good catch โ fixed in abc1234. The endpoint now validates
the token before reading the body, so the unauthenticated path can't reach
the parser.
Self-check
Before sending any PR comment: does the body start with [Claude Code ๐ค]? If not, prepend it. The prefix leads the comment โ it is the first thing in the body, not buried mid-paragraph.
