web-performance-audit

A guide for checking website speed, accessibility, search-engine setup, and common browser best practices with Lighthouse. Core Web Vitals are measurements of loading speed, visual stability, and responsiveness.

In plain words
What is it for?
Use it to audit storefronts on mobile or desktop, measure Core Web Vitals, and investigate slow loading or unstable page layouts.
Why use it?
It helps identify slow pages, layout shifts, accessibility problems, and other issues that can hurt user experience or search visibility.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/wake-engineering/ai-plugin/web-performance-audit
Any agent
npx skills add wake-engineering/ai-plugin --skill web-performance-audit
Clone the repo
git clone --depth 1 https://github.com/wake-engineering/ai-plugin

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00058 $0.01002
Opus 5 $0.00029 $0.00501
Sonnet 5 $0.00012 $0.00200
Haiku 4.5 $0.00006 $0.00100

Measured yesterday against content hash acf95cb184da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-performance-audit 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 yesterday.

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.

skills/web-performance-audit/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Performance Audit

Forbidden: api.fbits.net (and any *.fbits.net). Canonical source: https://wakecommerce.readme.io/docs/schema (for Wake API references in scope).

Run Lighthouse audits and performance traces on web pages using Chrome DevTools MCP. Covers accessibility, SEO, best practices, and Core Web Vitals (LCP, INP, CLS).

When to Use

  • Auditing storefront or web app performance
  • Checking Core Web Vitals (LCP, INP, CLS)
  • Running Lighthouse accessibility, SEO, or best-practices audits
  • Debugging slow page loads or layout shifts
  • Comparing mobile vs desktop performance

Prerequisites

  • Chrome DevTools MCP must be installed (bundled via plugin .mcp.json)
  • Node.js v20.19+
  • Chrome (stable or newer)
  • npm (for npx)

When Chrome DevTools MCP is unavailable, inform the user to install it and ensure Chrome is installed.

Workflow

1. Navigate to the URL

Use navigate_page with type: "url" and the target URL, or new_page to open in a new tab.

2. Choose Audit Type

Goal Tool Notes
Accessibility, SEO, best practices lighthouse_audit Excludes performance; use device: "mobile" or "desktop"
Performance, Core Web Vitals performance_start_trace Set reload: true for fresh load; autoStop: true recommended
Detailed performance insight performance_analyze_insight Use after trace; requires insightSetId and insightName from trace results

3. Run the Audit

  • Lighthouse: Call lighthouse_audit with mode: "navigation" to reload and audit, or mode: "snapshot" to audit current state.
  • Performance: Call performance_start_trace with reload: true, autoStop: true. Navigate to the URL first if needed.

4. Summarize Results

Present scores, metrics, and actionable recommendations. For performance traces, highlight Core Web Vitals (LCP, INP, CLS) and any insight sets.

Tool Reference (Chrome DevTools MCP)

Category Tool Purpose
Performance performance_start_trace Start trace; Core Web Vitals, LCP, INP, CLS
Performance performance_stop_trace Stop active trace
Performance performance_analyze_insight Deep dive on specific insight from trace
Performance take_memory_snapshot Capture heap for memory leak debugging
Debugging lighthouse_audit Accessibility, SEO, best practices (excludes performance)
Navigation navigate_page Go to URL, back, forward, reload
Navigation new_page Open URL in new tab
Debugging take_snapshot Text snapshot of page (a11y tree)
Debugging take_screenshot Screenshot of page or element
Network list_network_requests List requests since last navigation
Network get_network_request Get request/response details
Emulation emulate Throttle network, CPU, viewport, device
Emulation resize_page Resize viewport

Read the full file on GitHub · 83 lines

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.

  1. yesterday First seen · 83 lines · 58 tokens per session scan A acf95cb184da

Subscribe to this mod's changes

web-performance-audit is a skill published in the GitHub repository wake-engineering/ai-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,002 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.

Related

Other skills, from other repositories

Apify

Scrapes social platforms, business data, and e-commerce via Apify actors — Instagram, LinkedIn, TikTok, YouTube, Facebook, Google Maps, Amazon, and web crawls — filtering in code. USE WHEN scrape Instagram, scrape LinkedIn, scrape TikTok, scrape YouTube, scrape Facebook, Google Maps leads, Amazon reviews, business…

danielmiessler/LifeOS · 150 tokens

amazon-product-detail

Amazon product detail page scraper: extract full product data from any open Amazon product detail URL (any /dp/{asin} or /gp/product/{asin} page across all Amazon regional TLDs) — returns asin, url, title, brand, price, listPrice, stars, reviewsCount, starsBreakdown (5/4/3/2/1 star percentages), answeredQuestions…

browser-act/skills · 472 tokens

amazon-search-listing

Amazon search and category listing scraper: extract product listings from any Amazon search results page, keyword search URL, or category browse page and return per-item cards (asin, title, url, image, price, listPrice, stars, reviewCount, badges, isAmazonChoice, isBestSeller, isSponsored, delivery, boughtInPast…

browser-act/skills · 341 tokens

ebay-search-listing

Extracts product listings from any eBay search or category page URL, returning per-item cards (itemNumber, url, title, subtitle, caption, price, priceWithCurrency, currency, wasPrice, bids, shipping, seller, sellerFeedbackCount, sellerPositiveRating, reviewsCount, starRating, image) plus pagination state (currentPage…

browser-act/skills · 221 tokens

etsy-product-detail

Etsy product detail scraper: given an Etsy listing URL, returns full product detail including listingId, title, priceCurrent, priceOriginal, currency, images (all), description, shopName, shopUrl, rating, reviewCount, favorites, inCartCount, variations (with per-option price ranges), highlights, listedDate…

browser-act/skills · 187 tokens

etsy-shop-catalog

Etsy shop catalog scraper: given an Etsy shop URL (e.g. https://www.etsy.com/shop/{shop-name}) and optional page number, returns paginated product listings from that shop's own storefront with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping…

browser-act/skills · 208 tokens