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-automation-patternsgit 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-automation-patterns)<a href="https://agentmods.dev/skills/mickeyyaya/refactoring-skills/review-automation-patterns"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-automation-patterns/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-automation-patterns"><img src="https://agentmods.dev/badge/skills/mickeyyaya/refactoring-skills/review-automation-patterns.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 | $0.00048 | $0.02582 |
| Opus 5 | $0.00024 | $0.01291 |
| Sonnet 5 | $0.00010 | $0.00516 |
| Haiku 4.5 | $0.00005 | $0.00258 |
Grade A, and why
review-automation-patterns 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 12d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Automation Patterns
Overview
Machines enforce rules with no exceptions (formatting, unused variables, known CVEs, type mismatches). Humans evaluate intent, architecture fitness, naming coherence, test quality, and logic correctness. The goal of review automation is to eliminate machine-checkable items from human review.
Pairs with review-efficiency-patterns and review-code-quality-process. Cross-reference security-patterns-code-review for security-specific automated checks.
Tool Selection by Language
| Language | Linter | Type Checker | Security Scanner | Formatter |
|---|---|---|---|---|
| Go | golangci-lint, go vet | go build (compile-time) | gosec | gofmt, goimports |
| Python | ruff (replaces flake8+isort+pyupgrade) | mypy, pyright | bandit, safety | black, ruff format |
| TypeScript | eslint + typescript-eslint | tsc --noEmit | semgrep, npm audit | prettier |
| Rust | clippy | rust-analyzer, rustc | cargo-audit, cargo-deny | rustfmt |
| Java | checkstyle, spotbugs, PMD | javac (compile-time) | snyk, OWASP dependency-check | google-java-format, spotless |
| C++ | clang-tidy, cppcheck | clang (compile-time) | — (use manual review) | clang-format |
Notes:
- For Go, prefer
golangci-lintas the aggregator — runsgo vet,staticcheck,errcheck, and others in a single pass. - For Python,
ruffhas replaced the traditional flake8+isort+pyupgrade stack and is significantly faster. Runmypyseparately. - For TypeScript,
tsc --noEmitandeslintare complementary —tsccatches type errors,eslintcatches code quality issues. - For Rust,
clippyis authoritative and maintained by the Rust project.cargo-denyextendscargo-auditwith license policy enforcement. - Java's
spotbugsoperates on bytecode and catches null pointer risks, resource leaks, and threading bugs that source-level linters miss.
Linter-to-Review Dimension Mapping
| Review Dimension | Tools That Cover It | What Remains for Human Review |
|---|---|---|
| Security | gosec, bandit, semgrep, cargo-audit, snyk, npm audit | Business logic bypasses, authorization flaws, indirect injection, custom crypto misuse |
| Correctness | tsc, mypy, go vet, rustc, javac, clippy | Logic errors, wrong algorithm, off-by-one in business rules, incorrect state transitions |
| Performance | clippy (some alloc patterns), spotbugs (some threading) | Algorithmic complexity, N+1 queries, unnecessary serialization, cache invalidation |
| Style | prettier, black, gofmt, rustfmt, clang-format, eslint | Naming coherence across a feature, comment accuracy, API surface consistency |
| Duplication | PMD (copy-paste detection) | Semantic duplication, structural duplication across services |
| Test quality | coverage thresholds (CI), eslint-plugin-jest | Test intent, meaningful assertions, missing edge cases, test isolation |
| Architecture | — (no tool covers this) | Dependency direction, layer violations, coupling, modularity, fit with existing patterns |
| Dependency health | cargo-deny, npm audit, snyk, safety | Whether a newer version introduces breaking 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.
- 12d ago First seen · 227 lines · 48 tokens per session scan A 6de94cb638bb
review-automation-patterns is a skill published in the GitHub repository mickeyyaya/refactoring-skills (6 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 2,582 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.
Other skills, from other repositories
gemini-review
Google Gemini CLI code review with Gemini 2.5 Pro, 1M token context, CI/CD integration.
squid-implement-night
Run the full agent-team pipeline end-to-end for one feature whose Tasks Plan is already approved by /squid-plan, handing the human a validated, ready-to-squash-merge PR. Trigger after /squid-plan.
pr-babysitter
Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
aster-review-ci
Run aster code reviews non-interactively in CI, GitHub Actions, or from another agent. Covers aster review --pr, --json, --stream, --comment, diff-from-stdin, token handling, and filtering findings. Use when wiring aster into a pipeline, posting PR comments, or parsing review output programmatically.
review
Review before merge. Stage-1 spec-compliance gate, then risk-selected Stage-2 review axes from the canonical set. analyst always runs, callers can pin extra always-on axes, and explicit deep review runs the full 16-axis set. Run after /test. Do NOT invoke code-qualities-assessment, doc-accuracy, golden-principles, or…