code-review

A structured checklist for reviewing code, including correctness, security, performance, maintainability, tests, and documentation.

In plain words
What is it for?
Use it to review a change or pull request and return practical feedback on its implementation and test coverage.
Why use it?
It helps find bugs, security risks, missing edge cases, and unclear or fragile code before changes are accepted.

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

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00017 $0.01065
Opus 5 $0.00009 $0.00532
Sonnet 5 $0.00003 $0.00213
Haiku 4.5 $0.00002 $0.00106

Measured yesterday against content hash cd4a003abe9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "{GITEA_URL}/api/v1/repos/{owner}/{repo}/pulls/{pr_number}/reviews" \
.opencode/skills/code-review/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What I do

I perform comprehensive code reviews with focus on:

  • Code quality and maintainability
  • Security vulnerabilities
  • Performance issues
  • Best practices adherence
  • Test coverage
  • Documentation completeness

Review Checklist

1. Correctness

  • Does the code do what the PR claims?
  • Are edge cases handled?
  • Are there potential bugs?
  • Are error conditions properly handled?

2. Security

  • Input validation present?
  • SQL injection prevention?
  • XSS prevention?
  • Authentication/authorization correct?
  • Secrets not exposed in code?
  • Proper error messages (no info leakage)?

3. Performance

  • N+1 query issues?
  • Unnecessary iterations?
  • Large data in memory?
  • Caching opportunities?

4. Code Style

  • Follows project conventions?
  • Naming conventions consistent?
  • Code duplication minimized?
  • Functions single-purpose?

5. Testing

  • Unit tests for new logic?
  • Integration tests for flows?
  • Edge cases covered?
  • Test readability?

6. Documentation

  • Comments for complex logic?
  • API documentation updated?
  • README updated if needed?
  • Breaking changes documented?

Review Comment Format

Use structured comments for clarity:

For Issues

[Issue]: Brief description
[Severity]: High/Medium/Low
[Suggestion]: Suggested fix or approach

Example:

[Issue]: SQL query vulnerable to injection
[Severity]: High
[Suggestion]: Use parameterized query:
  db.query("SELECT * FROM users WHERE id = ?", [userId])

For Suggestions

[Suggestion]: Improvement idea
[Benefit]: What this improves
[Effort]: Low/Medium/High

For Praise

[Nit]: Minor style preference (optional to address)
[Good]: Specific positive observation

Review Workflow

  1. Understand context - Read PR description and linked issues
  2. Check scope - Ensure changes match stated goals
  3. Review iteratively - Top-down: architecture, logic, style
  4. Test locally - Pull and verify functionality
  5. Provide feedback - Clear, actionable, constructive
  6. Follow up - Verify fixes addressed concerns

Read the full file on GitHub · 188 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. yesterday First seen · 188 lines · 17 tokens per session scan A cd4a003abe9a

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository MartinKuhne/devstack (2 stars, last pushed 20d ago), licensed MIT. It adds 17 tokens to every session and 1,065 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens