Plugin Claude Code
AI code-review PR loop for Claude Code and Codex. Reads real review-thread state, sweeps the pattern instances the reviewer missed, verifies against your own tests, and stops at a hard cycle cap.
Instructions file
Instructions for OrenAshkenazy/gh-review-loop, covering claude.md, skill.md placement rule, test runner, if installed via homebrew on apple silicon and or run pytest from a virtual environment.
Plugin Claude Code
Clears AI reviewer feedback on your PR: reads real review-thread state, sweeps the sibling instances the reviewer missed, gates every push on your repo's own tests, then requests re-review — hard-capped so it can never spam the PR. Works with Codex out of the box, or any reviewer bot you configure.
Hook
Runs before the agent uses a tool for Edit, Write, MultiEdit, NotebookEdit and Bash tool calls, executing loop_profile_gate.py and loop_summary_gate.py (2 commands). From OrenAshkenazy/gh-review-loop.
Hook
Runs when the agent finishes a response, executing loop_summary_hook.py. From OrenAshkenazy/gh-review-loop.
Skill Claude CodeCodex
Use after a GitHub PR is opened or to handle AI reviewer feedback (Codex, CodeRabbit, Copilot, or any reviewer bot) - run the review loop, fix reviewer comments, sweep sibling instances, verify, push, request re-review.