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 KaelSensei/MagicAIBuilder --skill web-performancegit clone --depth 1 https://github.com/KaelSensei/MagicAIBuilderWrote 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/kaelsensei/magicaibuilder/web-performance)<a href="https://agentmods.dev/skills/kaelsensei/magicaibuilder/web-performance"><img src="https://agentmods.dev/badge/skills/kaelsensei/magicaibuilder/web-performance.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 5.1 | $0.00043 | $0.01879 |
| Opus 5 | $0.00022 | $0.00940 |
| Sonnet 5 | $0.00009 | $0.00376 |
| Haiku 4.5 | $0.00004 | $0.00188 |
Grade A, and why
web-performance 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 7d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Performance Skill
Reference checklist for web performance: PageSpeed Insights score and Google Core Web Vitals. The standard is non-negotiable for production web pages: PageSpeed >= 90/100 on mobile, all Core Web Vitals in the green on real-user data.
When to use this skill
- Before merging any branch that ships or modifies a public web page.
- When running
/audit-code,/beautify,/feature, or/fixon a web target. - When the user asks "is this fast enough?", "what's the LCP?", or mentions PageSpeed/Lighthouse.
- When designing or reviewing UI that affects layout, images, fonts, scripts, or third-party tags.
How this skill is used
Users do not invoke skills directly. Skills are reference knowledge that the AI loads
automatically when it detects a matching task, or when a command explicitly says "use the
web-performance skill."
- Automatic: The AI loads this skill when working on web pages, UI, or front-end perf.
- Referenced by:
/audit-code,/beautify-- these commands include a performance validation step that uses this skill's checklist.
Targets (non-negotiable for production web)
| Metric | Target (mobile, p75 field) | Notes |
|---|---|---|
| PageSpeed score | >= 90 / 100 | Lighthouse mobile run |
| LCP | <= 2.5 s | Largest Contentful Paint |
| INP | <= 200 ms | Interaction to Next Paint (replaced FID) |
| CLS | <= 0.1 | Cumulative Layout Shift |
| FCP | <= 1.8 s | First Contentful Paint |
| TTFB | <= 800 ms | Time To First Byte |
| Total Blocking Time | <= 200 ms | Lab metric, proxy for INP |
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.
- 7d ago First seen · 163 lines · 43 tokens per session scan A 2e25cd66a264
web-performance is a skill published in the GitHub repository KaelSensei/MagicAIBuilder (2 stars, last pushed 5d ago), licensed MIT. It adds 43 tokens to every session and 1,879 once invoked, about $0.0002 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
react-hook-form
React Hook Form performance optimization for client-side form validation using useForm, useWatch, useController, useFieldArray, and the v7.55+ subscribe() API. This skill should be used when building client-side controlled forms with React Hook Form library. This skill does NOT cover React 19 Server Actions…
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json…
vercel-react-best-practices
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance…
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
nextjs-app-router
Full end-to-end tRPC setup for Next.js App Router. Covers route handler with fetchRequestHandler (GET + POST exports), TRPCProvider with QueryClientProvider, createTRPCOptionsProxy for RSC prefetching, HydrateClient/HydrationBoundary for hydration, useSuspenseQuery for Suspense, and server-side callers.
nextjs-pages-router
Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.