codex-review

v0.5.5

Cross-provider adversarial plan/design-doc review via OpenAI Codex (GPT-5.6 Terra): verdict-loop protocol, atomic chain guard, cross-repo decision-gate log.

Claude Code1 Skill

By Jason MatthewLicense: MIT5 GitHub starsUpdated 2 weeks ago

Directory evidence

Runtimes: Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 5, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install codex-review for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install codex-review@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/jasonm4130/claude-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/codex-review/.

Plugin files

plugins/codex-review/

├── .claude-plugin/plugin.json
└── skills/codex-plan-review/SKILL.md

Included Skills1

codex-plan-reviewskills/codex-plan-review/SKILL.md

Cross-provider adversarial review of a finalized plan, spec, design doc, ADR, or code diff using OpenAI Codex (GPT-5.6 Terra). AUTO-TRIGGER at plan gates — invoke immediately after any of: (1) a plan written by `nightshift:plan` is finalized, (2) an ADR draft is completed. AUTO-TRIGGER for code: after implementing a Codex-reviewed plan, run diff mode on the branch range before opening the PR — a reviewed plan is NOT a reviewed diff. Also invoke on request — "codex review this plan", "codex review this diff", "get a second opinion on this design", "terra review". Do NOT re-run on an artifact already reviewed without an explicit user ask; each chain burns paid quota.

Plugin manifests1

plugins/codex-review/.claude-plugin/plugin.json

{
  "name": "codex-review",
  "description": "Cross-provider adversarial plan/design-doc review via OpenAI Codex (GPT-5.6 Terra): verdict-loop protocol, atomic chain guard, cross-repo decision-gate log.",
  "version": "0.5.5",
  "author": {
    "name": "Jason Matthew",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/jasonm4130/claude-skills",
  "repository": "https://github.com/jasonm4130/claude-skills",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "codex",
    "cross-provider",
    "plan-review",
    "design-review",
    "adversarial-review"
  ]
}