codex-code-review

A cross-model review routine that sends code changes to the Codex command-line tool for inspection.

In plain words
What is it for?
Use it to review uncommitted files, a branch compared with a base branch, recent commits, or a specified list of files. It is intended to run after tests and before committing and pushing.
Why use it?
It helps find critical problems in uncommitted changes before they are committed or pushed. The review can repeat until no critical issues remain.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tykisgod/quick-question/codex-code-review
Any agent
npx skills add tykisgod/quick-question --skill codex-code-review
Clone the repo
git clone --depth 1 https://github.com/tykisgod/quick-question

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,228 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.02228
Opus 5 $0.00019 $0.01114
Sonnet 5 $0.00008 $0.00446
Haiku 4.5 $0.00004 $0.00223

Measured 2d ago against content hash a9d0dc8a35e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-code-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 2d 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/codex-code-review/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Invoke scripts via ${CLAUDE_PLUGIN_ROOT}/bin/<name>. That env var is set by Claude Code for every plugin context and gives the absolute path to the marketplace clone — no PATH or cwd assumptions. Bare-command invocation (e.g. code-review.sh) is NOT reliable: the plugin never puts its scripts on PATH, so bare calls exit 127.

Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).

Arguments: $ARGUMENTS

  • No arguments: review uncommitted changes (default)
  • --base <branch>: full branch diff against a base
  • --commits: review only the most recent commit
  • --files "a.cs b.cs": explicit file list

Review Scope Selection (no arguments)

Default: uncommitted changes. Run git diff --name-only HEAD -- '*.cs' to get the list of changed files. This is the most common case — code has been written but not yet committed.

Override order:

  1. User specified a scope (e.g. "review Phase 8") → follow user intent
  2. No uncommitted changes but branch has commitsgit diff --name-only develop...HEAD -- '*.cs'
  3. User says "review the whole branch"--base develop

Pass the file list to the review script as --files.

Execution Flow

1-5. Automated Review Loop

Loop automatically, no need to ask the user each round. Loop terminates when any condition is met:

  • No [Critical] issues in Codex review results
  • 5 rounds completed
  • No new critical issues in two consecutive rounds

Each round:

a. Send to Codex for Review

Before sending the diff to Codex, if qq-policy-check.sh is available, run it on the same changed .cs files first. Treat those deterministic findings as already-established local policy results. Codex should focus on bugs, behavior, architecture, and anything not trivially captured by deterministic checks.

Use the Bash tool with run_in_background: true to run in the background:

${CLAUDE_PLUGIN_ROOT}/bin/code-review.sh $ARGUMENTS

The script calls codex exec with a manually-constructed diff and the Unity best-practice checklist inlined in the prompt. It always passes -c model_reasoning_effort=high to avoid the shallow "No findings" result that Codex's default (reasoning=none) produces. Results are written to stdout and Docs/qq/<branch-name>/codex-code-review_<timestamp>.md.

Read the full file on GitHub · 126 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. 2d ago First seen · 126 lines · 39 tokens per session scan A a9d0dc8a35e6

Subscribe to this mod's changes

codex-code-review is a skill published in the GitHub repository tykisgod/quick-question (11 stars, last pushed 7d ago), licensed MIT. It adds 39 tokens to every session and 2,228 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 2026-08-30.

Related

Other skills, from other repositories

geometry-and-math

Use this skill when using Phaser 4 math and geometry utilities. Covers vectors, rectangles, circles, triangles, polygons, random number generation, angles, distance, interpolation, and snapping. Triggers on: Vector2, Rectangle, Circle, math, distance, angle, random, lerp.

phaserjs/phaser · 64 tokens

text-and-bitmaptext

Use this skill when displaying text in Phaser 4. Covers Text game objects, BitmapText, web fonts, text styling, word wrap, alignment, padding, and dynamic text content. Triggers on: Text, BitmapText, this.add.text, font, word wrap, text style.

phaserjs/phaser · 64 tokens

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

assets-create-folder

Create a new folder under a parent folder inside 'Assets/'. The parent path must start with 'Assets/' and every intermediate folder in it must already exist. Refreshes the AssetDatabase at the end and returns the GUID(s) of the created folder(s).

IvanMurzak/Unity-MCP · 55 tokens

assets-prefab-save

Save the currently opened prefab edit stage back to its prefab asset without exiting the stage. Pair with 'assets-prefab-open' to enter the edit mode first.

IvanMurzak/Unity-MCP · 37 tokens

mobile-games

Mobile game development principles. Touch input, battery, performance, app stores.

vudovn/ag-kit · 18 tokens