Agent skill

Code Review

by agulli in agulli/atlas-agents

Perform a structured security and quality audit on source code.

MITAuto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add agulli/atlas-agents --skill code-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install agulli/atlas-agents code-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/agulli/atlas-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ch09_agent_skills/skills/code-review .claude/skills/code-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
code-review
GitHub stars
579
Token cost
~593 tokens
SKILL.md length
280 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Perform a structured security and quality audit on source code.

  • Works in 5 steps: Read the target files. Use file_read or… → Security pass. Check for OWASP Top 10… → Logic pass. Check for → …
  • Asked to review code
  • SKILL.md covers Overview, Process, Rationalizations and Verification
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Review is an agent skill from agulli/atlas-agents. Perform a structured security and quality audit on source code. Use when asked to review code, audit a pull request, check for vulnerabilities, or assess code quality.

Its SKILL.md is about 590 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Requires python 3.10+

It sits in Development, covering Code review, Code quality and Pull requests. The licence is MIT.

When your agent uses it

  • Asked to review code
  • Audit a pull request
  • Check for vulnerabilities
  • Assess code quality

Example prompts

  • “/code-review”

Requirements

  • Python 3
  • Compatibility (from SKILL.md): Requires python 3.10+
  • Pre-approved tools (allowed-tools): Bash(grep:*), Bash(rg:*), Read

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Read the target files. Use file_read or equivalent to load every file under review. Do not review from memory or summaries.
  2. Security pass. Check for OWASP Top 10 vulnerabilities in this order
  3. Logic pass. Check for
  4. Style pass. Flag only violations that affect readability or correctness
  5. Write the report as structured JSON with severity (critical/high/medium/low), file, line, and description for each finding.

What it can do on your machine

Read from SKILL.md and the folder at commit 2b21998. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(grep:*)
    • Bash(rg:*)
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Requires python 3.10+

    From compatibility in the SKILL.md frontmatter.

Context cost

Code Review loads about 593 tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 280 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~593

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from agulli/atlas-agents at commit 2b21998, republished under its MIT licence (© agulli). 280 words, ~593 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder).
name
code-review
description
Perform a structured security and quality audit on source code. Use when asked to review code, audit a pull request, check for vulnerabilities, or assess code quality.
allowed-tools
Bash(grep:*), Bash(rg:*), Read
compatibility
Requires python 3.10+
license
MIT

Overview

You are conducting a code review as a principal engineer with security expertise. This is not a courtesy scan — you are the last gate before production.

Process

  1. Read the target files. Use file_read or equivalent to load every file under review. Do not review from memory or summaries.
  2. Security pass. Check for OWASP Top 10 vulnerabilities in this order:
    • SQL injection (string concatenation in queries)
    • Path traversal (../ in file operations without validation)
    • Command injection (os.system, subprocess with shell=True)
    • Hardcoded secrets (API keys, passwords, tokens in source)
    • Insecure deserialization (pickle.loads, yaml.load without SafeLoader)
  3. Logic pass. Check for:
    • Unhandled exceptions that silently swallow errors
    • Race conditions in concurrent code
    • Off-by-one errors in loops and slicing
    • Mutable default arguments in function signatures
  4. Style pass. Flag only violations that affect readability or correctness:
    • Functions longer than 50 lines
    • Deeply nested conditionals (>3 levels)
    • Unused imports or variables
  5. Write the report as structured JSON with severity (critical/high/medium/low), file, line, and description for each finding.

Rationalizations

ExcuseRebuttal
"The code looks fine at a glance"You must read every line. Glancing is not reviewing.
"This is just a small change"Small changes cause production outages. Review the diff AND the surrounding context.
"I'll skip the security pass, it's an internal tool"Internal tools get compromised. The security pass is mandatory.
"There are too many files to review"Review them all. If there are more than 20 files, summarize findings per-directory.

Verification

Do not mark this review as complete until you have:

  • Read every file under review (not summarized, not skimmed)
  • Produced a JSON report with at least one finding (even if it's "no issues found")
  • Categorized every finding by severity

© agulli, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in ch09_agent_skills/skills/code-review of agulli/atlas-agents.

Open the folder on GitHubat commit 2b21998

Compare with similar skills

Code Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Code Review this skillagulli/atlas-agents579—~593Automated safety check: PassMIT
WooCommerce Code Reviewwoocommerce/woocommerce11k3 repos~1.1kAutomated safety check: PassCustom licence
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT
Code Reviewerjewbetcha/opentrace1162 repos~1.1kAutomated safety check: NotesMIT
Code Review SkillRain-kl/OpenFlare288—~2.3kAutomated safety check: NotesMIT
Code ReviewerYikai-Liao/symusic1891 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • WooCommerce Code Review

    woocommerce/woocommerce

    Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.

    11k GitHub starsUsed in 3 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Code Review Skill

    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…

    2.1k GitHub stars~2.8k tokensUpdated 29 days ago
    DevelopmentAuto-check: notes
  • Code Reviewer

    jewbetcha/opentrace

    Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go.

    116 GitHub starsUsed in 2 repos~1.1k tokens
    DevelopmentAuto-check: notes
  • Code Review Skill

    Rain-kl/OpenFlare

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C/.NET, Kotlin, Swift, NestJS, C/C++, and more.

    288 GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check: notes
  • Code Reviewer

    Yikai-Liao/symusic

    Analyzes code diffs and files to identify bugs, security vulnerabilities (SQL injection, XSS, insecure deserialization), code smells, N+1 queries, naming issues, and architectural concerns, then…

    189 GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed
  • Code Review Specialist

    lhfer/claude-howto-zh-cn

    Structured code review across security, performance, code quality and maintainability, with a checklist, a finding template and two Python scripts for complexity metrics.

    2.3k GitHub stars~267 tokensUpdated 2 mo ago
    DevelopmentAuto-check passed

More from agulli/atlas-agents

All 12 skills in this repo
  • API Design

    agulli/atlas-agents

    Design or review REST and GraphQL API interfaces. An agent skill from agulli/atlas-agents.

    579 GitHub stars~539 tokensUpdated 2 mo ago
    Auto-check passed
  • Data Pipeline

    agulli/atlas-agents

    Design, build, or debug data processing pipelines. An agent skill from agulli/atlas-agents.

    579 GitHub stars~714 tokensUpdated 2 mo ago
    Auto-check passed
  • Database Migration

    agulli/atlas-agents

    Safely run database schema migrations. An agent skill from agulli/atlas-agents.

    579 GitHub stars~702 tokensUpdated 2 mo ago
    Auto-check passed
  • Deploy Checklist

    agulli/atlas-agents

    Execute a structured deployment to staging or production. An agent skill from agulli/atlas-agents.

    579 GitHub stars~756 tokensUpdated 2 mo ago
    Auto-check passed
  • Documentation Writer

    agulli/atlas-agents

    Write or update technical documentation for code, APIs, or systems.

    579 GitHub stars~639 tokensUpdated 2 mo ago
    Auto-check passed
  • Git Commit

    agulli/atlas-agents

    Create well-structured git commits with conventional commit messages.

    579 GitHub stars~463 tokensUpdated 2 mo ago
    Auto-check: notes

Categories

Questions about Code Review

What does Code Review do?

Perform a structured security and quality audit on source code. Code Review is an agent skill from agulli/atlas-agents. Perform a structured security and quality audit on source code.

When should I use Code Review?

Code Review fits situations like: asked to review code; audit a pull request; check for vulnerabilities; assess code quality.

How do I install Code Review in Claude Code?

Run `npx skills add agulli/atlas-agents --skill code-review -a claude-code`. Or copy the skill folder (ch09_agent_skills/skills/code-review in agulli/atlas-agents) into .claude/skills/code-review in your project. Claude Code loads it when a task matches its description.

How do I install Code Review in Codex?

Run `npx skills add agulli/atlas-agents --skill code-review -a codex`. Or copy the skill folder (ch09_agent_skills/skills/code-review in agulli/atlas-agents) into .agents/skills/code-review in your project. Codex loads it when a task matches its description.

Can I use Code Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agulli/atlas-agents --skill code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/code-review, .gemini/skills/code-review, .github/skills/code-review and .opencode/skills/code-review in your project.

What does Code Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Code Review is instructions for the agent only. Our summary lists: Python 3. Its frontmatter pre-approves these tools: Bash(grep:*), Bash(rg:*), Read. Compatibility (from SKILL.md): Requires python 3.10+.

Does Code Review access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Code Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Code Review use?

Code Review is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 593 tokens (SKILL.md is roughly 2.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Code Review?

Skills that share tags, products or a category with Code Review: WooCommerce Code Review (woocommerce/woocommerce, 11k stars), Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Code Reviewer (jewbetcha/opentrace, 116 stars) and Code Review Skill (Rain-kl/OpenFlare, 288 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

agulli (a GitHub user) maintains it in agulli/atlas-agents, which has 579 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on July 17, 2026.

Source: agulli/atlas-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.