Official agent skill

Code Review

by getsentry in getsentry/warden

Finds real correctness bugs in code changes. An agent skill from getsentry/warden.

OfficialCustom licenceAuto-check passedDevelopment

Install Code Review

skills CLI
$ npx skills add getsentry/warden --skill code-review -a claude-code

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

GitHub CLI
$ gh skill install getsentry/warden 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/getsentry/warden.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/warden/src/builtin-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
414
Token cost
~1.9k tokens
SKILL.md length
953 words
Files
6 (incl. references)
Skills in repo
8
Repo updated
First seen
Licence
Custom licence

At a glance

Finds real correctness bugs in code changes. An agent skill from getsentry/warden.

  • Works in 7 steps: Read the changed hunk and enough… → Identify the contract: caller… → Construct adversarial cases: null or… → …
  • Adversarial code review
  • SKILL.md covers References, Bugs Only Rule, Investigation Process and What To Report, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Code Review is an agent skill from getsentry/warden, published by the product's own GitHub organization. Finds real correctness bugs in code changes. Use for adversarial code review, bug hunts, regression review, PR correctness review, logic errors, data loss, race conditions, state bugs, interface contract breaks, error handling bugs, edge cases, broken builds, or broken workflows. Excludes style, readability, architecture, AppSec, and best-practice-only feedback unless the issue causes a demonstrable bug.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `SOURCES.md`, `SPEC.md` and `references/github-workflows.md`).

It sits in Development, covering Code review, Failing and flaky tests and Pull requests. It works with Python. The repository describes itself as: Your code is under new management. Agents that review your code.

When your agent uses it

  • Adversarial code review
  • Regression review
  • PR correctness review
  • Race conditions

Example prompts

  • “Use the code-review skill to find real correctness bugs in code changes. An agent skill from getsentry/warden”
  • “/code-review”

Requirements

  • Python 3
  • Pre-approved tools (allowed-tools): Read, Grep, Glob

Workflow steps

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

  1. Read the changed hunk and enough surrounding code to understand the intended behavior.
  2. Identify the contract: caller expectations, public types, schemas, validation, docs, tests, persistence shape, API response shape…
  3. Construct adversarial cases: null or undefined, empty collections, zero, false, empty string, duplicates, missing keys, boundary counts…
  4. Trace data and state across imports, wrappers, validators, serializers, database writes, caches, queues, and dependent call sites.
  5. Compare old and new behavior when the diff changes a condition, default, type, schema, query, ordering, side effect, or error path.
  6. Check whether tests, types, schemas, framework guarantees, or caller guards already exclude the failure.
  7. Report only defects that survive this verification.

What it can do on your machine

Read from SKILL.md and the folder at commit 1ee135e. 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:

    • Read
    • Grep
    • Glob

    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.

Context cost

Code Review loads about 1.9k tokens when it runs, and up to ~5.6k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 953 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~105
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5.6k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 953 words (~1,867 tokens).

“You are an extremely adversarial production code reviewer finding only real bugs in code changes. Try to break the changed behavior from every reachable angle, but report nothing unless the failure is concrete, reproducible from the code, and would cause…”

— opening of SKILL.md by getsentry, Custom licence
name
code-review
allowed-tools
Read, Grep, Glob

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (references) in packages/warden/src/builtin-skills/code-review of getsentry/warden.

  • SKILL.md
  • SOURCES.md
  • SPEC.md
  • references/github-workflows.md
  • references/javascript-typescript.md
  • references/python.md

Open the folder on GitHubat commit 1ee135e

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 skillgetsentry/warden414—~1.9kAutomated safety check: PassCustom licence
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT
Docling Pull Request Reviewdocling-project/docling68k—~1kAutomated safety check: PassMIT
Code Reviewerjewbetcha/opentrace1162 repos~1.1kAutomated safety check: NotesMIT
Code Graph RAG Pull Request Reviewvitali87/code-graph-rag5.2k—~685Automated safety check: PassMIT

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k 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
  • Docling Pull Request Review

    docling-project/docling

    Reviews or re-reviews a Docling pull request in fixed stages, with findings that can be reproduced and an explicit record of every check that was run.

    68k GitHub stars~1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • 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 Graph RAG Pull Request Review

    vitali87/code-graph-rag

    Reviews pull requests to code-graph-rag, watching for wrong or missing graph edges in language parsers, cross-language consistency and tests that really exercise a fix.

    5.2k GitHub stars~685 tokensUpdated today
    DevelopmentAuto-check passed
  • Coding Agent

    mastra-ai/mastra

    Authoring playbook for building agents that write, edit, review, or refactor code.

    29k GitHub stars~2.3k tokensUpdated today
    DevelopmentAuto-check passed

More from getsentry/warden

All 8 skills in this repo
  • Skill Writer

    getsentry/warden

    Official

    Create, synthesize, and iteratively improve agent skills following the Agent Skills specification.

    414 GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed
  • Warden Sweep

    getsentry/warden

    Official

    Full-repository code sweep. An agent skill from getsentry/warden.

    414 GitHub stars~780 tokensUpdated 7 days ago
    Auto-check passed
  • Warden

    getsentry/warden

    Official

    Run Warden to analyze code changes before committing. An agent skill from getsentry/warden.

    414 GitHub stars~610 tokensUpdated 7 days ago
    Auto-check passed
  • Warden Service

    getsentry/warden

    Official

    Queries and summarizes the Warden Service read API. An agent skill from getsentry/warden.

    414 GitHub stars~944 tokensUpdated 7 days ago
    Auto-check passed
  • Agent Prompt

    getsentry/warden

    Official

    Reference guide for writing effective agent prompts and skills.

    414 GitHub stars~430 tokensUpdated 7 days ago
    Auto-check passed
  • Security Review

    getsentry/warden

    Official

    Finds exploitable application security vulnerabilities in code changes.

    414 GitHub stars~1.8k tokensUpdated 7 days ago
    Auto-check passed

Works with

Categories

Questions about Code Review

What does Code Review do?

Finds real correctness bugs in code changes. An agent skill from getsentry/warden. Code Review is an agent skill from getsentry/warden, published by the product's own GitHub organization. Finds real correctness bugs in code changes.

When should I use Code Review?

Code Review fits situations like: adversarial code review; regression review; PR correctness review; race conditions.

How do I install Code Review in Claude Code?

Run `npx skills add getsentry/warden --skill code-review -a claude-code`. Or copy the skill folder (packages/warden/src/builtin-skills/code-review in getsentry/warden) 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 getsentry/warden --skill code-review -a codex`. Or copy the skill folder (packages/warden/src/builtin-skills/code-review in getsentry/warden) 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 getsentry/warden --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: Read, Grep, Glob.

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 has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Code Review use?

About 1.9k tokens (SKILL.md is roughly 7.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.7k tokens, read only when the agent opens those files.

What are the alternatives to Code Review?

Skills that share tags, products or a category with Code Review: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Code Review Skill (awesome-skills/code-review-skill, 2.1k stars), Docling Pull Request Review (docling-project/docling, 68k stars) and Code Reviewer (jewbetcha/opentrace, 116 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

getsentry (a GitHub organization, an official publisher) maintains it in getsentry/warden, which has 414 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 30, 2026.

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