code-review

code-review is a skill for Claude Code, Codex from bestdeejay-design/agent-skills. It costs 159 tokens per session (1,782 once invoked), scanned A, original, MIT.

A structured review process for examining changed code and reporting problems with their severity, file, line, and suggested fix.

In plain words
What is it for?
It checks correctness, security, performance, style, tests, unusual cases, and accessibility in a Git diff, pull request, or commit.
Why use it?
It gives developers a consistent way to find issues in a code change before it is merged.

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/bestdeejay-design/agent-skills/code-review
Any agent
npx skills add bestdeejay-design/agent-skills --skill code-review
Clone the repo
git clone --depth 1 https://github.com/bestdeejay-design/agent-skills

Made for: Claude Code, Codex.

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 code-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/code-review.svg)](https://agentmods.dev/skills/bestdeejay-design/agent-skills/code-review)
Your own site
<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 159 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,782 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 5.1 $0.00159 $0.01782
Opus 5 $0.00079 $0.00891
Sonnet 5 $0.00032 $0.00356
Haiku 4.5 $0.00016 $0.00178

Measured 5d ago against content hash a3aac8e6a519, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 5d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/checklists.py, scripts/review.py), 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/code-review/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review

Структурированный ревью PR/diff за один запуск: чек-лист, severity, файл:строка, исправление.

Загружай этот скилл когда нужно проверить код (diff, PR, commit) и получить структурированные замечания с приоритетами. Скилл читает изменения, применяет чек-лист из шести категорий и выдаёт готовый текст для комментария в PR.

🎯 When to use

Use this skill when:

  • Нужно ревью PR/commit/diff перед мержем
  • Просят «проверь код», «найди баги», «замечания по коду»
  • Нужен чек-лист code quality перед релизом
  • Нужно быстро прогнать diff по категориям: correctness, security, performance, style, tests, edge cases, a11y
  • Нужен структурированный комментарий к PR с severity и ссылками на файл:строку

Do NOT use when:

  • Нужно внести правки — скилл только анализирует и комментирует; исправления вносит агент отдельно по явному запросу
  • Нужен полный аудит всего репозитория, а не изменений — скилл работает по diff
  • Нужен security-аудит с PoC-доказательством уязвимости — используй специализированный security-скилл
  • Это первичное ревью архитектуры без кода — скилл анализирует код, не схемы

📦 What this skill does

Inputs

  • --repo PATH — git-репозиторий: берётся git diff HEAD (staged + unstaged)
  • --file PATH — обычный файл: ревьюится целиком, каждая строка считается добавленной
  • --diff PATH — файл, содержащий git diff
  • stdin — git diff (по умолчанию, git diff | review.py)

Outputs

  • Список замечаний: [severity] файл:строка — правило: проблема + предлагаемое исправление
  • Сводка по категориям и severity (critical/warning/nit)
  • Markdown-отчёт по шаблону templates/review-template.md — готов для комментария в PR

🔧 How to use

Шаг 1: получить diff

git diff HEAD > /tmp/pr.diff

Шаг 2: запустить ревью

python3 scripts/review.py --diff /tmp/pr.diff

Или напрямую из репозитория:

python3 scripts/review.py --repo /path/to/repo

Или через stdin:

git diff | python3 scripts/review.py

Read the full file on GitHub · 143 lines

Files

What ships with it

5 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. 5d ago First seen · 143 lines · 159 tokens per session scan A a3aac8e6a519

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed today), licensed MIT. It adds 159 tokens to every session and 1,782 once invoked, about $0.0008 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.