review

review is a skill for Claude Code, Codex from alphacornutum/layercake. It costs 94 tokens per session (500 once invoked), scanned A, original, MIT.

A structured review process for code changes, pull requests, or staged files. It checks correctness, security, failures, design, tests, and clarity, then reports issues with file locations and severity.

In plain words
What is it for?
It is for reviewing diffs and pull requests, finding defects or security problems, and suggesting specific fixes.
Why use it?
It helps find bugs and risks before code is merged, instead of relying on a quick or incomplete review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for reviewing diffs and pull requests, finding defects or security problems, and suggesting specific fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alphacornutum/layercake/review
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.

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

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 review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphacornutum/layercake/review/github.svg)](https://agentmods.dev/skills/alphacornutum/layercake/review)
Your own site
<a href="https://agentmods.dev/skills/alphacornutum/layercake/review"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alphacornutum/layercake/review"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00094 $0.00500
Opus 5.5 $0.00038 $0.00200
Sonnet 5.5 $0.00019 $0.00100
Haiku 4.5 $0.00009 $0.00050

Measured 20d ago against content hash 2cf2f5f10b29, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 20d 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.

.ai/src/skills/review/SKILL.md · 48 lines

What it actually says

Code Review

Systematically review changes for correctness, security, and maintainability.

Steps

  1. Read the full diff. Understand the scope before commenting.
  2. Check PR description or commit messages for context — what problem is being solved?
  3. Review in priority order:
    • Correctness — Logic errors, off-by-one bugs, missing edge cases, race conditions.
    • Security — Injection risks, hardcoded secrets, missing validation, exposed PII.
    • Error handling — Unhandled failures, swallowed exceptions, missing error paths.
    • Architecture — Does this follow existing patterns? Are boundaries respected?
    • Testing — Are new behaviors tested? Are error paths covered?
    • Naming & clarity — Would a new team member understand this?
  4. For each issue:
    • Point to the exact file and line.
    • Explain why it's a problem, not just what to change.
    • Suggest a fix when possible.
    • Mark as blocking (must fix) or suggestion (nice to have).
  5. When the code is solid, say so plainly. Manufactured criticism erodes review trust.

Output Format

## Summary
[1-2 sentence overview]

## Issues
- **[blocking]** file.ts:42 — [problem and suggested fix]
- **[suggestion]** file.ts:15 — [observation and reasoning]

## Verdict
[Approve / Request changes / Needs discussion]

Gotchas

  • Skip style nitpicks that a formatter or linter would catch — those are noise.
  • Review what's there, not what you would have written. The author's approach stands unless it has a concrete flaw.
  • Resolve every blocking issue before approving — politeness is not a reason to ship a known bug.
  • Check the full PR, not just the latest commit — bugs often hide in earlier commits.
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. 20d ago First seen · 48 lines · 94 tokens per session scan A 2cf2f5f10b29

Subscribe to this mod's changes

review is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 500 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.

Related

Other skills, from other repositories

after-effects-scripting

Drive a running After Effects instance directly from the shell to build, edit and render motion graphics — no MCP, plugin or panel required. Use whenever the user wants Claude to work inside After Effects: building animations, title sequences, logo stings, UI/product motion, data visualisations, or fixing an existing…

Maciejdziuba/youtube-skills · 148 tokens

autoreview

Structured code review through the shared OpenClaw agent-skills installation.

openclaw/clawhub · 17 tokens

omh-code-review

This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).

rlaope/oh-my-hermes · 48 tokens

revdiff-plan

Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…

umputun/revdiff · 84 tokens

asplos-writing-style

Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…

brycewang-stanford/Awesome-Journal-Skills · 65 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens