Borrowing it
Nothing to install: this file belongs to tan-yong-sheng/ai-vision-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tan-yong-sheng/ai-vision-mcp/main/.claude/skills/performance/SKILL.mdgit clone --depth 1 https://github.com/tan-yong-sheng/ai-vision-mcpWrote 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/tan-yong-sheng/ai-vision-mcp/performance)<a href="https://agentmods.dev/skills/tan-yong-sheng/ai-vision-mcp/performance"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/performance/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/tan-yong-sheng/ai-vision-mcp/performance"><img src="https://agentmods.dev/badge/skills/tan-yong-sheng/ai-vision-mcp/performance.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 | $0.00049 | $0.02356 |
| Opus 5 | $0.00024 | $0.01178 |
| Sonnet 5 | $0.00010 | $0.00471 |
| Haiku 4.5 | $0.00005 | $0.00236 |
Grade A, and why
performance scanned grade A with 1 finding 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
return cached || fetch(event.request).then((response) => { This is a copy
100% identical to performance — 188 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance optimization
Deep performance optimization based on Lighthouse performance audits. Focuses on loading speed, runtime efficiency, and resource optimization.
How it works
- Identify performance bottlenecks in code and assets
- Prioritize by impact on Core Web Vitals
- Provide specific optimizations with code examples
- Measure improvement with before/after metrics
Performance budget
| Resource | Budget | Rationale |
|---|---|---|
| Total page weight | < 1.5 MB | 3G loads in ~4s |
| JavaScript (compressed) | < 300 KB | Parsing + execution time |
| CSS (compressed) | < 100 KB | Render blocking |
| Images (above-fold) | < 500 KB | LCP impact |
| Fonts | < 100 KB | FOIT/FOUT prevention |
| Third-party | < 200 KB | Uncontrolled latency |
Critical rendering path
Server response
- TTFB < 800ms. Time to First Byte should be fast. Use CDN, caching, and efficient backends.
- Enable compression. Gzip or Brotli for text assets. Brotli preferred (15-20% smaller).
- HTTP/2 or HTTP/3. Multiplexing reduces connection overhead.
- Edge caching. Cache HTML at CDN edge when possible.
Resource loading
Preconnect to required origins:
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://cdn.example.com" crossorigin>
Preload critical resources:
<!-- LCP image -->
<link rel="preload" href="/hero.webp" as="image" fetchpriority="high">
<!-- Critical font -->
<link rel="preload" href="/font.woff2" as="font" type="font/woff2" crossorigin>
Defer non-critical CSS:
<!-- Critical CSS inlined -->
<style>/* Above-fold styles */</style>
<!-- Non-critical CSS -->
<link rel="preload" href="/styles.css" as="style" onload="this.onload=null;this.rel='stylesheet'">
<noscript><link rel="stylesheet" href="/styles.css"></noscript>
JavaScript optimization
Defer non-essential scripts:
<!-- Parser-blocking (avoid) -->
<script src="/critical.js"></script>
<!-- Deferred (preferred) -->
<script defer src="/app.js"></script>
<!-- Async (for independent scripts) -->
<script async src="/analytics.js"></script>
<!-- Module (deferred by default) -->
<script type="module" src="/app.mjs"></script>
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.
- 11d ago First seen · 362 lines · 49 tokens per session scan A 4a480aded500
performance is a skill published in the GitHub repository tan-yong-sheng/ai-vision-mcp (78 stars, last pushed 5mo ago), licensed MIT. It adds 49 tokens to every session and 2,356 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 100% identical to performance, differing in 188 lines, and is treated as a copy.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…