review-cheat-sheet

review-cheat-sheet is a skill for Claude Code, Codex from mickeyyaya/refactoring-skills. It costs 42 tokens per session (4,184 once invoked), scanned A, original, MIT.

A one-page guide for reviewing code changes, with checks for different review areas and links to more detailed guidance. A pull request is a proposed change to a codebase for others to review before merging.

In plain words
What is it for?
Use it to begin code reviews, choose relevant checks, apply severity levels, and find deeper review instructions.
Why use it?
It gives reviewers a consistent starting point and helps them decide when a problem is serious enough to block a change.

Skill for Claude CodeCodex

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

Good fit Use it to begin code reviews, choose relevant checks, apply severity levels, and find deeper review instructions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mickeyyaya/refactoring-skills/review-cheat-sheet
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 mickeyyaya/refactoring-skills --skill review-cheat-sheet
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/refactoring-skills

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-cheat-sheet

README.md
[![agentmods](https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-cheat-sheet/github.svg)](https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-cheat-sheet)
Your own site
<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-cheat-sheet"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-cheat-sheet/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-cheat-sheet

Your own site · 80×15
<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-cheat-sheet"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-cheat-sheet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,184 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 $0.00042 $0.04184
Opus 5 $0.00021 $0.02092
Sonnet 5 $0.00008 $0.00837
Haiku 4.5 $0.00004 $0.00418

Measured 9d ago against content hash 90ab0b58f884, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

review-cheat-sheet 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 9d 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.

skills/review-cheat-sheet/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Cheat Sheet — Master Reference

Overview

This is the navigator for the entire review skill library. Load this skill first, scan for the relevant phase, follow the check, then jump to the linked skill for deeper guidance. A full review using this sheet takes 20–45 minutes for a typical PR; the First Pass alone takes under 5 minutes.

For efficiency guidance on ordering and time-boxing your review, see review-efficiency-patterns. For universal signals that apply across all languages, see cross-language-review-heuristics.


Severity Quick Reference

Severity Label Action
Must-fix before merge CRITICAL Block the PR — do not approve
High confidence the change is wrong HIGH Request changes, do not approve
Likely to cause a defect or maintenance burden MEDIUM Request changes or leave note
Style, preference, or minor improvement LOW Suggest, do not block
Optional, reviewer preference NIT Prefix comment with "nit:"

For confidence scoring, false positive reduction, and calibrating severity judgments, see review-accuracy-calibration. For writing actionable comments at each severity level, see review-feedback-quality.


Stop the PR (CRITICAL — Must-Fix Before Merge)

Check these first. If any are true, leave a blocking comment immediately and skip the rest of the review until resolved.

  • Security vulnerability present — hardcoded secret, SQL injection, XSS, auth bypass, path traversal. See security-patterns-code-review.
  • Data loss risk — destructive migration without rollback, DELETE without WHERE, unhandled overwrite of user data. See database-review-patterns.
  • Breaking API change without migration — removed field, renamed endpoint, changed contract with no versioning or deprecation path. See review-api-contract.
  • Missing error handling on external calls — network call, DB query, or third-party SDK call with no error branch. See error-handling-patterns.
  • Test suite failing — CI is red; do not approve a PR on a red build.

Read the full file on GitHub · 391 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. 9d ago First seen · 391 lines · 42 tokens per session scan A 90ab0b58f884

Subscribe to this mod's changes

review-cheat-sheet is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 4,184 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 2026-09-03.