Claude Review Loop
Claude Code plugin implementing an automated code-review loop that runs diffs through Codex.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Claude Review Loop, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A plugin that adds an automated code-review loop to Claude Code by routing diffs through Codex for a second-model review. It is built from commands and hooks — the hook triggers review on events and the command runs it on demand. It gates changes behind an independent review pass.
Key features and capabilities
- Automated code-review loop
- Second-model review via Codex
- Command + hook driven
Use cases
- Gating commits behind an automated review pass
- Getting an independent Codex review of Claude's diffs