pytest-clerk-mock

Coordinate one authorized task across a bounded collection of local repositories while preserving unrelated work. Use when a task spans repositories to apply a scoped change, run the same review or validation, or collect and merge information into one result.

Propagate explicitly requested skills, rules, and their changes across the user's other local repositories, creating missing applicable copies while preserving repository-specific guidance. Use when the user invokes /propagate-skill or $propagate-skill alongside a skill or rule creation or update request.

Run code-review repeatedly on its complete selected review target, investigate and fix every legitimate functional finding, validate and push the fixes, and stop only after two consecutive rounds with no functional findings (or a third when the second also makes simplifications). Any functional finding resets that stabilization sequence. Use when asked to review-and-fix, keep reviewing until clean, or run a code review loop.

Review the complete pull-request diff for the current branch with high-signal review lenses and severity-rated findings. When that diff is empty, review commits this Codex session created or pushed instead. Establish or update the branch and draft PR when needed, report findings in chat by default, never post GitHub review comments directly, and never fix findings. Use when asked to review a PR, review current changes, or run /code-review.