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 agentmods add skills/nimajafari/lighthouse-skill/lighthousenpx skills add nimajafari/lighthouse-skill --skill lighthousegit clone --depth 1 https://github.com/nimajafari/lighthouse-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/nimajafari/lighthouse-skill/lighthouse)<a href="https://agentmods.dev/skills/nimajafari/lighthouse-skill/lighthouse"><img src="https://agentmods.dev/badge/skills/nimajafari/lighthouse-skill/lighthouse.svg" alt="Measured on agentmods" 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 | $0.00059 | $0.02589 |
| Opus 5 | $0.00030 | $0.01295 |
| Sonnet 5 | $0.00012 | $0.00518 |
| Haiku 4.5 | $0.00006 | $0.00259 |
Grade A, and why
lighthouse 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 4d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lighthouse
Run Google Lighthouse to measure web quality and verify that fixes actually moved the numbers. Lighthouse audits a URL across Performance, Accessibility, SEO, and Best Practices and returns a 0–100 score per category plus a list of failing audits with specific guidance.
When to use this skill
This skill measures. Sibling quality skills fix. The workflow is a loop:
measure (this skill) → fix (performance / accessibility / seo / best-practices) → re-measure
Reach for this skill to: get a baseline score, find the specific failing audits, set a performance budget, gate a build in CI, or prove a change improved (or regressed) a metric. Don't guess at improvements — measure, change one thing, measure again.
How it works
- Pick a target URL — a deployed URL, or a local dev/preview server (
http://localhost:3000). - Run Lighthouse — prefer
scripts/run-lighthouse.sh <url>; it runs several times, takes the median, and emits compact JSON (full reports are huge and waste context). - Read category scores + failing audits from the JSON.
- Map each failing audit to a fix using the relevant quality skill.
- Re-run and report the before/after delta.
Install & run (CLI)
The Lighthouse readme installs it globally (needs Node 22 LTS+), and it drives a local Chrome/Chromium you must have installed:
npm install -g lighthouse
# or: yarn global add lighthouse
lighthouse https://example.com --view # basic run; --view opens the HTML report
Lighthouse auto-detects an installed Chrome; point it at a specific binary with the
CHROME_PATH environment variable.
For a quick one-off without a global install, npx lighthouse <url> also works — the
published CLI bin supports it, though the official docs only cover the global install.
Machine-readable run for an agent (JSON to a file, quiet, headless):
npx lighthouse https://example.com \
--quiet \
--chrome-flags="--headless=new" \
--only-categories=performance,accessibility,seo,best-practices \
--output=json --output-path=./lh.json
What ships with it
4 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.
- 4d ago First seen · 205 lines · 59 tokens per session scan A 791850ff9d0e
lighthouse is a skill published in the GitHub repository nimajafari/lighthouse-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 59 tokens to every session and 2,589 once invoked, about $0.0003 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
accessibility
Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
best-practices
Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".
performance
Optimize web performance for faster loading and better user experience. Use when asked to "speed up my site", "optimize performance", "reduce load time", "fix slow loading", "improve page speed", or "performance audit".
seo
Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".
core-web-vitals
Optimize Core Web Vitals (LCP, INP, CLS) for better page experience using field and lab evidence. Use when asked to "improve Core Web Vitals", "fix LCP", "reduce CLS", "optimize INP", "page experience optimization", or "fix layout shifts".
web-quality-audit
Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".