codex-cross-review

codex-cross-review is a skill for Claude Code from Vimalk0703/shipworthy. It costs 43 tokens per session (1,621 once invoked), scanned A, original, MIT.

A review workflow that asks OpenAI Codex to check work produced by Claude, including pull requests (proposed code changes).

In plain words
What is it for?
Use it to cross-check code, review pull requests, or handle many pull-request reviews with two-model verification.
Why use it?
It adds a second model's review to catch issues the first review may miss. If Codex is unavailable, the built-in reviewer can still be used.

Skill for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code; mentions Codex.

Part of the shipworthy plugin — 66 skills, 7 commands, 3 hooks shipped together

Good fit Use it to cross-check code, review pull requests, or handle many pull-request reviews with two-model verification.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vimalk0703/shipworthy/codex-cross-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Vimalk0703/shipworthy --skill codex-cross-review
Clone the repo
git clone --depth 1 https://github.com/Vimalk0703/shipworthy

Made for: Claude Code.

Or install shipworthy, the plugin that ships this one along with the rest of its 66 skills, 7 commands, 3 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for codex-cross-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/vimalk0703/shipworthy/codex-cross-review/github.svg)](https://agentmods.dev/skills/vimalk0703/shipworthy/codex-cross-review)
Your own site
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/codex-cross-review"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/codex-cross-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for codex-cross-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/vimalk0703/shipworthy/codex-cross-review"><img src="https://agentmods.dev/badge/skills/vimalk0703/shipworthy/codex-cross-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,621 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00043 $0.01621
Opus 5 $0.00022 $0.00811
Sonnet 5 $0.00009 $0.00324
Haiku 4.5 $0.00004 $0.00162

Measured 9d ago against content hash 0419b105460c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

codex-cross-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/collaboration/codex-cross-review/SKILL.md · 191 lines

How it starts

The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Cross-Review

Optional capability. This skill requires the codex-plugin-cc Claude Code plugin and the OpenAI Codex CLI. All other Shipworthy skills work independently — this adds dual-model review on top. Users without Codex installed lose nothing; they simply use Claude's built-in code-reviewer agent via shipworthy:requesting-code-review instead.

When activating, output:

shipworthy › skill: codex-cross-review — dispatching Codex for cross-model review

Availability Check

Before invoking any /codex:* command, check whether the plugin is available. If /codex:setup is not recognized or reports Codex is not installed:

  1. Inform the user that this skill requires the codex-plugin-cc plugin
  2. Offer setup guidance (see Prerequisites below)
  3. Fall back to Claude's built-in code-reviewer agent — it covers the same checklist without Codex

This skill never blocks work. If Codex is unavailable, the review still happens via Claude's own agent.

Prerequisites

Requires two things — the Codex CLI and the Claude Code plugin:

# 1. Install and authenticate the Codex CLI (one-time)
npm install -g @openai/codex
codex login                          # browser OAuth (ChatGPT account, incl. Free tier)
# OR: codex login --with-api-key     # OpenAI API key
# OR: codex login --device-auth      # headless/SSH environments

# 2. Install the Claude Code plugin (one-time)
/plugin marketplace add openai/codex-plugin-cc
/plugin install codex@openai-codex
/reload-plugins

# 3. Verify
/codex:setup

No environment variables needed — the Codex CLI manages its own credentials.

When to Use

  • After Claude completes a feature — Codex reviews for blind spots
  • Before merging any PR — structured review with severity-rated findings
  • High-volume PR review — batch review workflow across multiple PRs
  • When the user wants a second opinion from a different model
  • Before shipping to production — final cross-validation gate

Cross-Validation Workflow

Read the full file on GitHub · 191 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 191 lines · 43 tokens per session scan A 0419b105460c

Subscribe to this mod's changes

codex-cross-review is a skill published in the GitHub repository Vimalk0703/shipworthy (7 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 1,621 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.