codex-review

codex-review is a skill for Claude Code, Codex, Cursor from jaansokk/cursor_tools. It costs 50 tokens per session (724 once invoked), scanned A, original, MIT.

A command-line review process for checking code changes for bugs, regressions, security risks, and missing tests.

In plain words
What is it for?
Use it to review a diff, commit range, branch, or pull request and receive findings with file references, fix suggestions, and test-gap warnings.
Why use it?
It adds a focused second review of local changes, staged changes, commits, branches, or pull requests before they are accepted.

Skill for Claude CodeCodexCursor

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

Made for: Claude Code, Codex, Cursor.

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/jaansokk/cursor_tools/codex-review.svg)](https://agentmods.dev/skills/jaansokk/cursor_tools/codex-review)
Your own site
<a href="https://agentmods.dev/skills/jaansokk/cursor_tools/codex-review"><img src="https://agentmods.dev/badge/skills/jaansokk/cursor_tools/codex-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 724 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 $0.00050 $0.00724
Opus 5 $0.00025 $0.00362
Sonnet 5 $0.00010 $0.00145
Haiku 4.5 $0.00005 $0.00072

Measured 3d ago against content hash f491ffad6358, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

.cursor/skills/codex-review/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Review

When to use this skill

Use this whenever the user asks to:

  • Review local changes, staged changes, or a commit range
  • Review a branch or pull request with Codex CLI
  • Run a second-opinion review focused on correctness and risk

Default model

  • Default to gpt-5.3-codex.
  • Baseline command:
codex -m gpt-5.3-codex
  • Current docs recommend gpt-5.3-codex as the default coding model.
  • A separate gpt-5.3-codex-high slug is not documented in the public model list.
  • If the user explicitly wants to try a high-reasoning alias anyway, attempt it once and fall back to gpt-5.3-codex if unavailable.

Review workflow

  1. Scope the review target first:
    • working tree (git diff)
    • staged only (git diff --staged)
    • commit range (git diff <base>...<head>)
  2. Gather context:
    • git status --short
    • git log --oneline -n 20
    • relevant diff output
  3. Ask Codex for a risk-focused review (not a style nit pass).
  4. Return findings ordered by severity, with concrete file/symbol references and suggested fixes.
  5. Always call out test gaps and regression risk if coverage is unclear.

Command templates

A) Review current local changes (interactive)

codex -m gpt-5.3-codex "Review the current repository changes.
Focus on correctness bugs, behavioral regressions, security issues, and missing tests.
Ignore low-value style nits.
Return findings ordered by severity with file paths and concise fix suggestions."

B) Review staged diff (non-interactive)

codex -m gpt-5.3-codex -q "$(cat <<'EOF'
Review the staged git diff in this repository.
Prioritize:
1) correctness and logic flaws,
2) behavioral regressions,
3) security concerns,
4) missing/weak tests.

Output format:
- Severity: Critical/High/Medium/Low
- File: path
- Issue: short title
- Why it matters
- Suggested fix
EOF
)"

C) Optional model override with fallback

MODEL="gpt-5.3-codex-high"
codex -m "$MODEL" -q "Review current changes for bugs, regressions, security, and missing tests." \
  || codex -m gpt-5.3-codex -q "Review current changes for bugs, regressions, security, and missing tests."

Read the full file on GitHub · 95 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. 3d ago First seen · 95 lines · 50 tokens per session scan A f491ffad6358

Subscribe to this mod's changes

codex-review is a skill published in the GitHub repository jaansokk/cursor_tools (1 stars, last pushed 5mo ago), licensed MIT. It adds 50 tokens to every session and 724 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

continuous-discovery

Guide teams through building sustainable customer interview habits and discovery practices. Use when setting up weekly customer interviews, preparing interview guides, coaching story-based interviewing technique, synthesizing user research findings, planning assumption tests, or helping teams that say they don't have…

luisabwk/kraken · 60 tokens

prd-writer

Guide users through writing Product Requirements Documents (PRDs) and decomposing them into executable technical tasks. Use when creating a PRD, product spec, product one-pager, feature brief, PRP, or when breaking requirements into tasks with estimates, sprint planning, or technical decomposition.

luisabwk/kraken · 61 tokens

product-led-growth-playbook

Evaluate growth strategy, growth team structure, and go-to-market motions using Elena Verna's PLG frameworks. Use when the user asks about product-led growth, PLG, growth team hiring, self-serve vs sales-led motions, product-led sales, PQA/PQL models, growth loops, when to hire a head of growth, earned vs rented…

luisabwk/kraken · 97 tokens

ab-testing-framework

Design, run, and analyze A/B tests (controlled experiments) using Ronny Kohavi's methodology and Gibson Biddle's DHM trade-off analysis. Use when the user needs to plan an experiment, choose metrics (OEC), evaluate statistical significance, assess sample size requirements, avoid common experimentation pitfalls, or…

luisabwk/kraken · 75 tokens

dhm-strategy-framework

Evaluate and strengthen product strategy using Gibson Biddle's DHM framework (Delight, Hard-to-copy, Margin-enhancing). Use when the user asks about product strategy, competitive advantage, feature prioritization trade-offs, or wants to stress-test whether a product idea is strategically sound.

luisabwk/kraken · 62 tokens

ai-evals-builder

Build AI evals using the Husain-Shankar framework (error analysis, open/axial coding, LLM-as-judge). Use when a user needs to create, improve, or debug evals for an AI product — including defining failure modes, building LLM judges, or setting up production monitoring for an LLM application.

luisabwk/kraken · 72 tokens