codex-peer-review

github:jcputney/agent-peer-review · first committed 2026-01-15 · source · badge

This skill should be invoked BEFORE presenting implementation plans, architecture recommendations, code review findings, or answers to broad technical questions. Use proactively when about to "recommend", "suggest", "propose", "design", "plan", or answer "how should", "what's the best way", "which approach". MANDATORY for multi-file changes, refactoring proposals, and security-sensitive recommenda

Skill Health: not yet scored

Listed, not yet scored. This skill has no public model test yet. It is in the scoring queue; submitted skills go first, then the most-installed.

Version history

8 commits to this file on GitHub (newest first).

2026-08-06 · commit 93a36ea · fix: stop the reviewer agent scanning the whole disk for its own skill (2.1.1)
2026-06-03 · commit 601c922 · fix: support Codex profile-v2 config scheme (2.1.0)
2026-04-06 · commit e3facfd · feat: 2.0.0 — symmetric blind-debate redesign
2026-02-06 · commit 68b793f · Fix plugin for current Claude Code spec (v1.0.10)
2026-01-26 · commit 37c63fe · Refine allowed tools and update peer review docs
2026-01-17 · commit be6f223 · Enhance peer review hooks for broader coverage
2026-01-17 · commit 47c93ae · Add allowed-tools lists to peer review plugin docs
2026-01-15 · commit aa1eb68 · Restructure as generic marketplace with plugins subdirectory

Archived snapshots