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 wxmb01/review-skill --skill reviewgit clone --depth 1 https://github.com/wxmb01/review-skillWrote 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/wxmb01/review-skill/review)<a href="https://agentmods.dev/skills/wxmb01/review-skill/review"><img src="https://agentmods.dev/badge/skills/wxmb01/review-skill/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.
<a href="https://agentmods.dev/skills/wxmb01/review-skill/review"><img src="https://agentmods.dev/badge/skills/wxmb01/review-skill/review.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 | $0.00077 | $0.01972 |
| Opus 5 | $0.00039 | $0.00986 |
| Sonnet 5 | $0.00015 | $0.00394 |
| Haiku 4.5 | $0.00008 | $0.00197 |
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 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review
Overview
Use this skill to review a project beyond surface-level code style comments. Cover the axes that matter for the request and skip irrelevant ones.
Default to read-only analysis when the user asks to review, audit, assess, evaluate, or check work. Do not modify files unless the user explicitly asks for fixes, improvements, or implementation work in addition to the review.
Read references/review-axes.md when the request is broad, asks whether the project is "done" or "ready", or needs a full audit rather than a narrow code review.
Read references/review-playbook.md when you need scope routing, severity rules, evidence discovery strategy, readiness scoring, anti-shortcut guardrails, or risk subdomains.
Read references/review-code.md when the request is mainly about a PR, diff, commit, implementation quality, regression risk, or actionable code-review feedback.
When the stack is clear, also read one or more specialized code-review references:
references/review-code-typescript-react.mdfor TypeScript, React, and modern frontend reviewreferences/review-code-python.mdfor Python services, scripts, and async codereferences/review-code-java.mdfor Java, Spring-style backends, and JVM review Readreferences/review-templates.mdwhen you want a reusable output template such as a diff review, risk register, go or no-go summary, or remediation roadmap.
Scope Router
Choose one scope first. Scope answers "what is being reviewed", before mode answers "how to review it".
change: review a diff, PR, commit, patch set, or uncommitted changesproject: review a whole repository, product, service, system, or delivery stateartifact: review a spec, design doc, report, checklist, architecture note, or project plan
If the user asks to review a PR, commit, diff, or recent changes, stay in change scope unless the evidence forces a broader audit.
If the user asks whether the project is complete, ready, or good overall, use project scope.
If the review target is mainly a document or plan, use artifact scope even when code also exists.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 226 lines · 77 tokens per session scan A fb2062dcf3ec
review is a skill published in the GitHub repository wxmb01/review-skill (11 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,972 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
brooks-harness
Maintenance orchestrator for the brooks-lint plugin itself. Runs a sequential subagent pipeline — author → eval → QA → trigger-audit → release — to add or edit a skill, refresh the eval suite, keep the four manifests + all README translations + CHANGELOG + AGENTS/GEMINI in sync, audit trigger boundaries, and cut…
anti-defensive-writing
Reduce defensive writing in drafts and revisions by removing unnecessary caveats, disclaimers, hedges, apology-like framing, negative self-limiting statements, and over-explanations while preserving necessary scope, accuracy, safety, legal, ethical, and methodological limits. Use when drafting or revising academic…
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…
brooks-debt
Tech debt assessment that identifies, classifies, and prioritizes maintainability problems — helping teams build a refactoring roadmap — drawing on twelve classic engineering books. Triggers when: user asks about tech debt, refactoring priorities, what to clean up first, or asks "why is this so hard to change?", "what…