code-review

code-review is a skill for Claude Code, Codex from shwilliamson/automatasaurus. It costs 30 tokens per session (2,192 once invoked), scanned A, original, MIT.

Guidelines for reviewing proposed code changes before they are merged into a shared project.

In plain words
What is it for?
Reading pull-request diffs, checking behavior and architecture, giving specific feedback, and deciding whether changes are ready to merge.
Why use it?
They help reviewers find bugs, security problems, design flaws, and quality issues before the changes reach users.

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

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/shwilliamson/automatasaurus/code-review.svg)](https://agentmods.dev/skills/shwilliamson/automatasaurus/code-review)
Your own site
<a href="https://agentmods.dev/skills/shwilliamson/automatasaurus/code-review"><img src="https://agentmods.dev/badge/skills/shwilliamson/automatasaurus/code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,192 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 $0.00030 $0.02192
Opus 5 $0.00015 $0.01096
Sonnet 5 $0.00006 $0.00438
Haiku 4.5 $0.00003 $0.00219

Measured 3d ago against content hash 810d7c73d193, 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 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 3d ago.

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.

template/skills/code-review/SKILL.md · 330 lines

How it starts

The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Skill

Guidelines for performing effective code reviews that catch issues, improve code quality, and maintain a positive team dynamic.

Review Mindset

Default to requesting changes. Your job is to protect the codebase. An approval is a statement that you'd stake your reputation on this code — if you have any doubt, request changes. It's always cheaper to do another review round than to ship a bug.

Goals of Code Review

  1. Catch bugs and design flaws before they reach production
  2. Prevent security issues — treat every input as hostile
  3. Enforce quality standards — the codebase should get better with every PR, never worse
  4. Maintain architectural integrity — reject code that works but is built wrong

The Right Attitude

  • You are a gatekeeper. That's not a dirty word — it's your job. The codebase depends on you saying "no" when something isn't ready.
  • Be direct and specific. Don't soften feedback with hedging language.
  • Approving bad code is worse than blocking good code. When in doubt, request changes.
  • A clean diff is not the same as correct code. Read critically, assume there are bugs, and prove yourself wrong.

Review Process

1. Understand the Context First

Before looking at code:

1. Read the PR description
2. Read the linked issue
3. Understand WHAT is being done and WHY
4. Consider: Is this the right approach?

2. First Pass: High-Level Review

Ask yourself:

  • Does this solve the problem described in the issue?
  • Is the approach reasonable?
  • Are there obvious architectural concerns?
  • Is anything missing?

3. Second Pass: Detailed Review

Look at each file for:

  • Correctness (does it work?)
  • Edge cases and error handling
  • Security implications
  • Performance concerns
  • Test coverage
  • Code style and readability

4. Summarize Your Review

End with an overall assessment:

**[Architect]** Overall this looks good. Clean implementation of the user registration flow.

A few suggestions:
1. Consider adding rate limiting (security)
2. The validation error messages could be more user-friendly
3. Minor: prefer `const` over `let` where possible

Approving with minor suggestions - none are blocking.

Read the full file on GitHub · 330 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. 3d ago First seen · 330 lines · 30 tokens per session scan A 810d7c73d193

Subscribe to this mod's changes

code-review is a skill published in the GitHub repository shwilliamson/automatasaurus (5 stars, last pushed 6mo ago), licensed MIT. It adds 30 tokens to every session and 2,192 once invoked, about $0.0002 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.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 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