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.
npx skills add mickeyyaya/refactoring-skills --skill review-cheat-sheetgit clone --depth 1 https://github.com/mickeyyaya/refactoring-skillsWrote 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.
[](https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-cheat-sheet)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
- 9d ago First seen · 391 lines · 42 tokens per session scan A 90ab0b58f884
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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…