pr-babysit
Use when a PR should be babysat to green — poll its review bots (any bot reviewer — Cursor BugBot, OpenAI Codex, the MemHub reviewer, others) and CI, fix the real findings, push, and when clean propose a team rule for any finding that taught something the next PR should not repeat (e.g. "babysit this PR", "watch PR 14 and fix the bot findings", or, on Claude Code only, auto-armed by the memhub hook right after gh pr create — Codex and Cursor do not run that hook, so there it is started by hand). Designed as the body of a self-paced /loop — one poll→fix→push pass per invocation; the final pass proposes rules (usually none) and ends the loop.
Pinned to revision 38fcebbb5125, so it is the text this page describes rather than whatever the author pushed since.
Pre-approved tools experimental
Experimental field. Support varies between clients, so this list is what the author declared, not what your client will enforce.
- Bash(git remote get-url origin)
- Bash(gh pr view *)
- Bash(gh api repos/*/comments --paginate)
- Bash(gh api repos/*/reviews --paginate)
- Bash(gh api repos/*/replies -f body=*)
- Bash(git pull)
- Bash(git add *)
- Bash(git commit *)
- Bash(git push)
- Bash(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rulebook_verify.py" *)
- Bash(python3 "${CLAUDE_PLUGIN_ROOT}/scripts/rulebook_conflicts.py" *)
- Write(//tmp/*.json)
- Edit(//tmp/*.json)
- Edit(./**)
- mcp__plugin_memhub_memhub__list_rules
- mcp__plugin_memhub-staging_memhub__list_rules
- mcp__plugin_memhub_memhub__list_rulebooks
- mcp__plugin_memhub-staging_memhub__list_rulebooks
- mcp__plugin_memhub_memhub__create_rule
- mcp__plugin_memhub-staging_memhub__create_rule
- Read
- Glob
- Grep
Files
Every link opens the file at its source, pinned to the revision this page describes.