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 ShiplightAI/agent-skills --skill reviewgit clone --depth 1 https://github.com/ShiplightAI/agent-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/shiplightai/agent-skills/review)<a href="https://agentmods.dev/skills/shiplightai/agent-skills/review"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/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/shiplightai/agent-skills/review"><img src="https://agentmods.dev/badge/skills/shiplightai/agent-skills/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00146 | $0.01276 |
| Opus 5 | $0.00073 | $0.00638 |
| Sonnet 5 | $0.00029 | $0.00255 |
| Haiku 4.5 | $0.00015 | $0.00128 |
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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Orchestrator
The single entry point for application reviews. It triages what matters, then
runs one or more domain reviews and merges them into a unified report. Each
domain lives in references/<domain>.md and is loaded only when selected.
When to use
- User wants a review but isn't sure which kind
- Pre-launch readiness assessment
- Post-incident review planning
- A targeted request for one domain ("check my app's security", "review SEO")
Modes
- Triage (default,
/review) — ask context questions, recommend a plan, run it. - Full suite (
/review --all) — run every applicable domain. - Targeted (
/review <domain>) — jump straight into one domain, skipping triage. E.g./review security,/review seo. Accepts an optional depth flag (--quick/--thorough).
Domains
Each row maps to a reference file. Load the file only when the domain is selected.
| Domain | Reference | Run it when… (trigger signals) |
|---|---|---|
| security | references/security.md |
auth/login changes, sensitive data, OWASP, headers/CORS/CSP, supply chain |
| privacy | references/privacy.md |
collects PII, tracking/analytics, consent banners, GDPR/CCPA |
| compliance | references/compliance.md |
regulated industry, audit prep, HIPAA/SOC 2/PCI-DSS/GDPR, payments or health data |
| design | references/design.md |
UI shipping without a designer, responsive, accessibility, typography, i18n |
| resilience | references/resilience.md |
error handling, network/API failures, empty/edge states, degradation |
| performance | references/performance.md |
slow pages, Core Web Vitals, bundle size, runtime/render perf |
| seo | references/seo.md |
public site, meta tags, structured data, crawlability, sitemaps |
| geo | references/geo.md |
discovered via AI assistants, LLM citation readiness, llms.txt, entity clarity |
Shared conventions (phases, scoring, confidence, severity, output paths) live in
references/report-format.md — every domain follows them.
What ships with it
9 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 · 112 lines · 146 tokens per session scan A 99e91222f8fd
review is a skill published in the GitHub repository ShiplightAI/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 146 tokens to every session and 1,276 once invoked, about $0.0007 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
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.
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…