codex-review

codex-review is a skill for Claude Code from MereWhiplash/engram-cogitator. It costs 42 tokens per session (949 once invoked), scanned A, original, MIT.

An independent review of a design document or implementation plan by OpenAI Codex before work begins.

In plain words
What is it for?
Use it to review design or plan files when Codex is enabled in the project configuration and installed on the command line.
Why use it?
It can reveal missed edge cases, feasibility problems, and simpler approaches before the plan is carried out.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; mentions Codex.

Part of the cogitation plugin — 20 skills, 1 command, 1 hook shipped together

Good fit Use it to review design or plan files when Codex is enabled in the project configuration and installed on the command line.

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

Made for: Claude Code.

Or install cogitation, the plugin that ships this one along with the rest of its 20 skills, 1 command, 1 hook.

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/merewhiplash/engram-cogitator/codex-review/github.svg)](https://agentmods.dev/skills/merewhiplash/engram-cogitator/codex-review)
Your own site
<a href="https://agentmods.dev/skills/merewhiplash/engram-cogitator/codex-review"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/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/merewhiplash/engram-cogitator/codex-review"><img src="https://agentmods.dev/badge/skills/merewhiplash/engram-cogitator/codex-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 949 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 $0.00042 $0.00949
Opus 5 $0.00021 $0.00475
Sonnet 5 $0.00008 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured 10d ago against content hash fc0aa91d8e16, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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.

cogitation/skills/codex-review/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review (Tier 2 — design/plan docs)

Get an independent second opinion from OpenAI Codex on a design or plan document before committing to execution.

Announce: "I'm using the codex-review skill to get a second opinion from Codex."

Scope

  • This skill = document review (design docs, implementation plans). The official codex-plugin-cc reviews diffs, not arbitrary docs — this fills that gap.
  • For code / adversarial review of a diff, prefer the official plugin instead: /codex:adversarial-review --background.

Step 0: Gate

Only run if .cogitation/config.json has codex.enabled: true AND codex is on PATH:

command -v codex >/dev/null || { echo "codex not installed; skipping"; exit 0; }

If disabled or missing, say so and fall back to Tier 0/1 review. Don't install anything.

Step 1: Identify the Artifact

If unspecified, pick the most recent:

ls -t docs/designs/*.md docs/plans/*.md 2>/dev/null | head -1

If both a design and a plan are plausible, ask with AskUserQuestion which to review.

Step 2: Build the Review Prompt

Design docs — focus: feasibility vs. the actual codebase, missed edge cases, simpler alternatives, data-model/migration risk, security & permissions.

Implementation plans — focus: task ordering/dependencies, completeness vs. design, test coverage of described behavior, file paths exist, scope.

Output structure to request: CONCERNS (block execution) · SUGGESTIONS (non-blocking) · STRENGTHS (brief).

Step 3: Run Codex — NON-BLOCKING

Run Codex in the background and let the harness notify you on completion. Do NOT block the session in the foreground.

Write stdout and stderr to separate files (don't merge — stderr is progress/log noise):

mkdir -p .cogitation/codex
OUT=.cogitation/codex/review-$(git rev-parse --short HEAD).md
ERR=.cogitation/codex/review.log
cat <artifact-path> | codex -a never exec \
  --model gpt-5.4 \
  --sandbox read-only \
  --ephemeral \
  --color never \
  -C "$(git rev-parse --show-toplevel)" \
  "<review-prompt>" \
  > "$OUT" 2> "$ERR"

Read the full file on GitHub · 86 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. 10d ago First seen · 86 lines · 42 tokens per session scan A fc0aa91d8e16

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository MereWhiplash/engram-cogitator (4 stars, last pushed 2mo ago), licensed MIT. It adds 42 tokens to every session and 949 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.