codex-review

codex-review is a skill for Claude Code from eugeniosegala/claude-connoisseur. It costs 21 tokens per session (1,016 once invoked), scanned A, original, MIT.

A code-review helper that sends your plans, code, or both to OpenAI Codex CLI for a separate review.

In plain words
What is it for?
Use it to review architecture decisions, implementation plans, file changes, diffs, or security concerns.
Why use it?
It gives you another assessment before you commit to an approach or change, which can reveal problems you missed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Part of the claude-connoisseur plugin — 13 skills, 2 hooks shipped together

Good fit Use it to review architecture decisions, implementation plans, file changes, diffs, or security concerns.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/eugeniosegala/claude-connoisseur/codex-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 eugeniosegala/claude-connoisseur --skill codex-review
Clone the repo
git clone --depth 1 https://github.com/eugeniosegala/claude-connoisseur

Made for: Claude Code.

Or install claude-connoisseur, the plugin that ships this one along with the rest of its 13 skills, 2 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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/codex-review/github.svg)](https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/codex-review)
Your own site
<a href="https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/codex-review"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/codex-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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/eugeniosegala/claude-connoisseur/codex-review"><img src="https://agentmods.dev/badge/skills/eugeniosegala/claude-connoisseur/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,016 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 $0.00021 $0.01016
Opus 5 $0.00010 $0.00508
Sonnet 5 $0.00004 $0.00203
Haiku 4.5 $0.00002 $0.00102

Measured 11d ago against content hash abba5b2373a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

codex-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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (run-codex.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/codex-review/SKILL.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review

When invoked, send the relevant context — plans, approaches, code, or any combination — to codex CLI for an independent review.

Files and instructions: $ARGUMENTS

What to review

This skill covers both code and plans/approaches:

  • Plans/Approaches: Architecture decisions, implementation strategies, proposed approaches before starting work
  • Code: Code you've written, modified, or are considering changing — diffs, file contents, implementation details, proposed changes
  • Both together: A plan alongside the code that implements it

Adapt what you send based on what the user asks Codex to review.

How to interpret arguments

The arguments are free-form and flexible. They may contain:

  • Natural language describing what to review: "review my current plan", "review the last commit"
  • File references alongside instructions: @auth.ts review this file for security issues
  • Scope instructions: "review the approach and the implementation together"

Parse the arguments to determine what context to gather and send to Codex.

Examples

  • /codex-review review my current plan — review the plan from the current conversation
  • /codex-review review the code I just wrote — review recent code changes
  • /codex-review review the approach and the implementation together — review both plan and code
  • /codex-review @auth.ts review this file for security issues — review a specific file with focus
  • /codex-review review the last commit — review the most recent commit diff

How to proceed

  1. Gather context: Collect the relevant material to send for review based on what the user asked. Match the scope of what you send to the scope of the ask — if the user points at a single function, send that function and its immediate dependencies, not the entire file history or conversation. A quick opinion needs adequate context; a full architecture review needs more.
    • For a targeted question (specific file, function, or snippet): Send only the relevant code and enough surrounding context for Codex to understand it (e.g. types, imports, direct callers). Skip git history, conversation recaps, and unrelated files
    • For plan/approach review: Include the plan text or approach description, plus the key files it affects (entry points, schemas, interfaces) — not the entire codebase it touches
    • For code review of recent changes: Include the diff (git diff) and a brief description of intent — not every file in the repo
    • For broad reviews ("review the architecture", "review everything I've done"): Include more context, but summarise where possible rather than dumping raw content

Read the full file on GitHub · 91 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago First seen · 91 lines · 21 tokens per session scan A abba5b2373a5

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository eugeniosegala/claude-connoisseur (9 stars, last pushed 4mo ago), licensed MIT. It adds 21 tokens to every session and 1,016 once invoked, about $0.0001 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.