Codex Plan Review — AI skill for Claude Code
Adversarial Codex review of a PLAN or design (not code) via the local Codex CLI.
How to install Codex Plan Review
Installs to ~/.claude/skills/irama-irama-skills-codex-plan-review/SKILL.md
mkdir -p ~/.claude/skills/irama-irama-skills-codex-plan-review && curl -fsSL https://raw.githubusercontent.com/irama/irama-skills/HEAD/commands/codex-plan-review.md -o ~/.claude/skills/irama-irama-skills-codex-plan-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Codex Plan Review does
description: Adversarial Codex review of a PLAN or design (not code) via the local Codex CLI. Read-only second-model challenge — pressure-tests the approach, assumptions, tradeoffs, and failure modes before you build. Use when a plan is agreed but not yet implemented. argument-hint: '[plan text, or path to a plan file — defaults to the current in-context plan]' allowed-tools: Bash(codex:*), Bash(git:*), Read
Get an independent second model to CHALLENGE the current plan before building.
Alternatives in AI
- Oh My Claudecode — 32 specialized agents and 7 execution modes for Claude Code, with smart model routing and automatic paralleliz 10.9k ★
- Mysti — AI coding dream team of agents for VS Code 1k ★
- Mancode — AI coding agent harness 358 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Verify Before Blocking
A portable discipline that stops AI agents from turning unverified assumptions into stop-work instructions. Si
LLM Council
A Claude Code skill that pressure-tests any decision through 5 AI advisors with anonymous peer review and a ch
Design AI Feature
Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes,
Claude Failures
Documented failure modes from working with Claude Code. Post-mortems of real incidents where the AI agent assu
Find Failures
Find how your AI product fails: review real traces in Eval Studio and group your notes into failure modes
AI Agents Workshop
2-hour workshop: build an AI agent in under 150 lines of Node.js. Concepts, architecture, failure modes, and l
Related Agents
Kimi Challenge
Use this agent when Claude wants Kimi to run an adversarial review that challenges the implementation approach
Dual Reviewer
Second-phase Codex code-review loop with Claude adjudication, after pr-reviewer in the branch review pass or m
Codex Adversarial Reviewer
Adversarial reviewer that calls Codex CLI for an independent second-opinion review of changed files, then adju