Agent skill

Code Review

A skill your agent uses when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge.

MITAuto-check passedDevelopment

Install Code Review

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a claude-code

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

GitHub CLI

$ gh skill install WrongStack/WrongStack 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/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/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/

Paste into Claude Code

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .claude/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack code-review --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/core/skills/code-review .agents/skills/code-review && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .agents/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack code-review --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/core/skills/code-review .cursor/skills/code-review && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .cursor/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/WrongStack/WrongStack.git --path packages/core/skills/code-review

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack code-review --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/core/skills/code-review .gemini/skills/code-review && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .gemini/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install WrongStack/WrongStack code-review

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/core/skills/code-review .github/skills/code-review && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .github/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add WrongStack/WrongStack --skill code-review -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install WrongStack/WrongStack code-review --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/WrongStack/WrongStack.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/core/skills/code-review .opencode/skills/code-review && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "code-review" agent skill from https://github.com/WrongStack/WrongStack/tree/main/packages/core/skills/code-review into .opencode/skills/code-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-review", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: code-review
GitHub stars: 370
Token cost: ~1.3k tokens
SKILL.md length: 592 words
Files: 2
Skills in repo: 38
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

A skill your agent uses when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge.

Works in 9 steps: Pin the change set exactly — git diff… → Learn the intent first: PR description,… → Read changed code in context — the whole… → …
Asked to review code changes — a pull request
SKILL.md covers Overview, Rules, What to check, in priority order and Workflow, plus 4 more sections
Calls git

What it does

Code Review is an agent skill from WrongStack/WrongStack. Use this skill when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge. Triggers: user says "review", "code review", "review this PR", "review my changes", "look over the diff", "is this ready to merge", "PR feedback", "anything wrong with this change".

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `SKILL.save.md`).

It sits in Development, covering Code review and Pull requests. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

Asked to review code changes — a pull request
The current diff — for correctness
Maintainability before they merge

Example prompts

“review”
“code review”
“review this PR”
“/code-review”

Workflow steps

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

Pin the change set exactly — git diff ...HEAD for a branch, the PR
Learn the intent first: PR description, linked issue, commit messages. Judge
Read changed code in context — the whole function, its callers, and its
Check the blast radius. For every changed signature, return shape, thrown
Every finding cites file:line, names the input or scenario that breaks and
Rank by severity — blocking, should fix, nit — and keep nits few so they
Skip what the formatter and linter already enforce.
Say what you verified and what you did not.
Stay read-only unless the user asks for fixes.

What it can do on your machine

Read from SKILL.md and the folder at commit 0fb4c17. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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 1.3k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 592 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~94
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 WrongStack/WrongStack at commit 0fb4c17, republished under its MIT licence (© WrongStack). 592 words, ~1,322 tokens.

Download SKILL.mdSave it as .claude/skills/code-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: code-review
description: Use this skill when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge. Triggers: user says "review", "code review", "review this PR", "review my changes", "look over the diff", "is this ready to merge", "PR feedback", "anything wrong with this change".
version: 1.0.0
required-capabilities: filesystem.read
optional-capabilities: version-control.manage, code.inspect, verification.run

Code Review

Overview

A review finds what the author can't see from inside the change: inputs they didn't consider, callers the change breaks, security holes, and design that will be expensive to live with. It is read-only unless the user asks for fixes.

This is the on-demand review of any change set. chimera is the automatic review of files changed during a WrongStack session.

Rules

Pin the change set exactly — git diff <base>...HEAD for a branch, the PR diff, or staged plus unstaged changes locally — and state the base you reviewed against.
Learn the intent first: PR description, linked issue, commit messages. Judge the change against what it is meant to do.
Read changed code in context — the whole function, its callers, and its tests — not only the diff hunks.
Check the blast radius. For every changed signature, return shape, thrown error, default value, or config key, find the callers (the codebase-impact-analysis or codebase-incoming-calls tool when the index exists, grep otherwise) and confirm they still work.
Every finding cites file:line, names the input or scenario that breaks and the consequence, and proposes a concrete fix. Without a scenario it is a question, and should be asked as one.
Rank by severity — blocking, should fix, nit — and keep nits few so they never bury a blocker.
Skip what the formatter and linter already enforce.
Say what you verified and what you did not.
Stay read-only unless the user asks for fixes.

What to check, in priority order

Correctness — conditions and boundaries, null, empty and very large inputs, error paths, awaited async work and ordering, concurrency, resource cleanup, behaviour on retry.
Contracts — public API, schema, and config changes; migrations and their rollback; callers updated; backwards compatibility.
Security — validation at trust boundaries, object-level authorization, injection (SQL, shell, HTML, paths), secrets, SSRF, sensitive data in logs.
Tests — something fails without this change; edge and error cases covered; assertions on behaviour.
Operability — errors carry context, logs or metrics where diagnosis will need them, timeouts on I/O, a way to turn risky behaviour off.
Maintainability — an existing helper duplicated (search before accepting a new one), naming, dead code, comments that explain why.
Performance on hot paths — N+1 queries, unbounded loads, blocking I/O on request paths.

Show full SKILL.md (207 more words)Show less

Workflow

Scope the change set and the base.
Intent from the description, issue, and commits.
Map the diff: list files, group them by concern, and skim everything once before commenting.
Deep read in the priority order above, with blast-radius checks.
Run what is cheap and allowed — type check, lint, and the covering tests (the codebase-targeted-test tool finds them).
Write the review.

Output

text

## Review — feature/retry-charges against main

**Verdict:** Request changes
Adds automatic retries to card charges; the retry path can double-charge.

### Blocking
1. src/billing/charge.ts:88 — each retry sends a new charge without an idempotency
   key, so a timeout after the provider accepted the first attempt charges twice.
   → Send `idempotencyKey: order.id` on every attempt.

### Should fix
2. src/api/orders.ts:41 — `limit` is not capped; `?limit=100000` loads the whole table.
   → Clamp it to 100.

### Nits
3. src/billing/charge.ts:12 — rename `tmp` to `pendingCharge`.

### Verified
Type check and the billing tests pass. End-to-end suite not run.

When nothing blocks, say so plainly. A short approval is a complete review.

Anti-patterns

Reviewing only the hunks without the surrounding code and callers.
Style-only reviews that miss the bug.
Vague comments — "this looks off", "consider refactoring".
Speculation stated as fact.
Redesigning the change to personal preference.
Approving without reading the tests.

Before returning

Change set and base stated; intent understood
Changed code read in context; callers of changed contracts checked
Every finding has file:line, a breaking scenario, and a fix
Severity ranked; nits few and labelled
What was and wasn't verified is stated
No files modified unless fixes were requested

Skills in scope

security-scanner — for a deeper pass on security-sensitive changes
bug-hunter — for scanning beyond the diff when a defect pattern repeats
testing — for judging whether the tests prove the change
chimera — for the automatic post-session review format

Files

SKILL.md and 1 other file in packages/core/skills/code-review of WrongStack/WrongStack.

SKILL.md
SKILL.save.md

Open the folder on GitHubat commit 0fb4c17

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
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Code Review this skillWrongStack/WrongStack	370	—	~1.3k	Automated safety check: Pass	MIT	today
PR Babysitteropeninterpreter/openinterpreter	69k	3 repos	~4.2k	Automated safety check: Pass	Apache-2.0	2 days ago
WooCommerce Code Reviewwoocommerce/woocommerce	11k	3 repos	~1.1k	Automated safety check: Pass	Custom licence	today
Open Code Review CLIalibaba/open-code-review	45k	—	~3.1k	Automated safety check: Pass	Apache-2.0	today
GitHub Review Iterationprisma/orm	48k	—	~2.2k	Automated safety check: Pass	Apache-2.0	today
Understand Diff AnalysisEgonex-AI/Understand-Anything	86k	—	~1.4k	Automated safety check: Pass	MIT	today

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
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
Open Code Review CLI
alibaba/open-code-review
Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.
45k GitHub stars~3.1k tokensUpdated today
DevelopmentAuto-check passed
GitHub Review Iteration
prisma/orm
Official
Runs a loop on a GitHub pull request: fetch review state, triage comments into actions, implement them and resolve threads, repeating until nothing actionable is left.
48k GitHub stars~2.2k tokensUpdated today
DevelopmentAuto-check passed
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
86k GitHub stars~1.4k tokensUpdated today
DevelopmentAuto-check passed
Code Review
flutter/flutter
Performs a comprehensive, multi-step code review of pull requests or local code changes, using iterative refinement (generation, critique, synthesis) to ensure high-quality, actionable feedback.
179k GitHub stars~1.4k tokensUpdated today
DevelopmentAuto-check passed

Questions about Code Review

What does Code Review do?

A skill your agent uses when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge. Code Review is an agent skill from WrongStack/WrongStack. Use this skill when asked to review code changes — a pull request, a branch, a commit range, or the current diff — for correctness, security, and maintainability before they merge.

When should I use Code Review?

Code Review fits situations like: asked to review code changes — a pull request; the current diff — for correctness; maintainability before they merge.

How do I install Code Review in Claude Code?

Run `npx skills add WrongStack/WrongStack --skill code-review -a claude-code`. Or copy the skill folder (packages/core/skills/code-review in WrongStack/WrongStack) 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 WrongStack/WrongStack --skill code-review -a codex`. Or copy the skill folder (packages/core/skills/code-review in WrongStack/WrongStack) 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 WrongStack/WrongStack --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?

Going by SKILL.md and its folder, Code Review needs the command-line tools its instructions call (git).

Does Code Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. 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 (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Code Review use?

About 1.3k tokens (SKILL.md is roughly 5.3k 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: PR Babysitter (openinterpreter/openinterpreter, 69k stars), WooCommerce Code Review (woocommerce/woocommerce, 11k stars), Open Code Review CLI (alibaba/open-code-review, 45k stars) and GitHub Review Iteration (prisma/orm, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Code Review?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 370 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 8, 2026.

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

Install Code Review

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Code Review

Overview

Rules

What to check, in priority order

Workflow

Output

Anti-patterns

Before returning

Skills in scope

Files

Compare with similar skills

Similar skills

More from WrongStack/WrongStack

Related

Questions about Code Review