codex-review

codex-review is a skill for Claude Code, Codex from shaharsha/claude-skills. It costs 113 tokens per session (8,045 once invoked), scanned B, original, MIT.

A process for getting an independent second opinion on unfinished software work before implementation or merging. It returns review claims that must then be checked against the actual source code.

In plain words
What is it for?
Use it to review plans, designs, feature work, bug fixes, refactors, or changes involving money, authentication, migrations, concurrency, permissions, or deletion.
Why use it?
It can reveal missed defects in plans, features, refactors, or sensitive changes, while requiring the primary reviewer to verify each finding.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Part of the engineering-decisions plugin — 2 skills shipped together , and of shaharsha-skills

Good fit Use it to review plans, designs, feature work, bug fixes, refactors, or changes involving money, authentication, migrations, concurrency, permissions, or deletion.

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

Made for: Claude Code, Codex.

Or install engineering-decisions, the plugin that ships this one along with the rest of its 2 skills.

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/shaharsha/claude-skills/codex-review/github.svg)](https://agentmods.dev/skills/shaharsha/claude-skills/codex-review)
Your own site
<a href="https://agentmods.dev/skills/shaharsha/claude-skills/codex-review"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/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/shaharsha/claude-skills/codex-review"><img src="https://agentmods.dev/badge/skills/shaharsha/claude-skills/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00113 $0.08045
Opus 5 $0.00056 $0.04022
Sonnet 5 $0.00023 $0.01609
Haiku 4.5 $0.00011 $0.00805

Measured 12d ago against content hash e93cc58406cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

codex-review scanned grade B with 2 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/codex_review.sh, scripts/render_review.py, scripts/verify_artifact.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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`sandbox_mode = "danger-full-access"` in `~/.codex/config.toml` is common and

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Raw network — `curl`, `urllib`, `ping` | ❌ DNS resolution fails |
skills/codex-review/SKILL.md · 578 lines

How it starts

The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex review

Hand the work to a different model, in a clean context, with no write access, and get back a list of claims. Then check each claim against the source and decide which ones are real.

The second half is not optional. Codex produces claims, not verdicts — some are defects you missed, some are confident nonsense, and telling them apart by reading the actual code is the entire value of the exercise. A review relayed without adjudication is worse than no review, because it launders a guess into an authority.

When this is worth it

Worth it: a plan about to be implemented, a change about to be merged, anything touching money, auth, migrations, concurrency, permissions, or deletion, and anything where you notice you're reasoning about your own work in a way that feels a bit too comfortable.

Not worth it: work in flight and about to change again, a one-line fix, a change the test suite already covers, or exploration. A review costs a few minutes of wall clock and its output needs adjudicating — spend it where being wrong is expensive.

Pick the mode

Situation Mode What Codex compares against
Plan or design doc, not yet implemented plan the repository it will land in
Change written, ready to commit or merge code the intent and constraints you give it
Change written from a plan code-vs-plan the plan, requirement by requirement

It is not only for code. The three modes name code because that is the common case, but nothing in the mechanism cares: any artifact you can render as text can be reviewed this way. Measured 2026-08-18 on a spreadsheet and a 40-document evidence set, where it found a hardcoded summary row that had silently drifted away from the live formulas feeding it.

Two things make that work, and both generalise:

  • Hand it the outputs as well as the source. The reviewer cannot execute anything, so a formula, a template or a query is opaque to it. Give it both representations — the formulas and the evaluated values, the template and the rendered result — and it can compare them. That comparison is what catches drift; neither representation alone would have.
  • Pre-extract anything binary. Read-only blocks the reviewer from running pdftotext or an OCR pass itself, so do it first and stage the text beside the originals. Say in the prompt which files are extracted text and how reliable the extraction is, or it will treat OCR noise as evidence.

Read the full file on GitHub · 578 lines

Files

What ships with it

7 files 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. 12d ago First seen · 578 lines · 113 tokens per session scan B e93cc58406cd

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository shaharsha/claude-skills (5 stars, last pushed 14d ago), licensed MIT. It adds 113 tokens to every session and 8,045 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.