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 frankxai/claude-skills-library --skill core-web-vitalsgit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/core-web-vitals)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/core-web-vitals"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/core-web-vitals/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/frankxai/claude-skills-library/core-web-vitals"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/core-web-vitals.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 | $0.00106 | $0.01242 |
| Opus 5.5 | $0.00042 | $0.00497 |
| Sonnet 5.5 | $0.00021 | $0.00248 |
| Haiku 4.5 | $0.00011 | $0.00124 |
Grade A, and why
core-web-vitals 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 12d 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Web Vitals
The rule: report measurements or report that you could not measure. A performance claim with no number attached is noise, and a number you did not observe is worse than no number.
Targets
Field thresholds (what Google grades on, 75th percentile of real users):
| Metric | Good | Needs work | Poor |
|---|---|---|---|
| LCP — Largest Contentful Paint | ≤ 2.5s | 2.5–4.0s | > 4.0s |
| INP — Interaction to Next Paint | ≤ 200ms | 200–500ms | > 500ms |
| CLS — Cumulative Layout Shift | ≤ 0.1 | 0.1–0.25 | > 0.25 |
Lab numbers from Lighthouse on a dev build run hotter than field numbers. Treat a lab pass as necessary, not sufficient, and say which kind you measured.
Budget for a marketing or landing page, on top of the metrics:
- First-load JS for the route: ≤ 200 kB gzipped. Next.js prints this per route in the build output — that is a free measurement, always take it.
- Hero image: served in AVIF or WebP, sized to its container,
priorityset. - Web fonts: at most two families,
font-display: swap, preloaded if above the fold, subset to the characters actually used.
How to measure
Cheapest first. Stop when you have a number.
1. Build output (always available, zero setup).
# Next.js — the per-route First Load JS table is the budget check
npm run build 2>&1 | tail -40
Flag any route whose First Load JS grew in this change, and by how much.
2. Lighthouse against a running server.
Use the repo's own Lighthouse when it has one (pnpm exec lighthouse, or a
script in package.json). Otherwise the pinned version below is fetched into
the npm cache, outside the lockfile. When the repo's contract says tooling
comes only from its lockfile (a frozen-install rule in AGENTS.md/SYSTEM.md),
skip this step and say Lighthouse was not run and why; do not add the
dependency to make the number appear.
npx --yes [email protected] http://localhost:3000/<route> \
--only-categories=performance \
--preset=desktop \
--output=json --output-path=./.lighthouse.json --quiet --chrome-flags="--headless"
node -e "const r=require('./.lighthouse.json');const a=r.audits;console.log(
'perf', Math.round(r.categories.performance.score*100),
'| LCP', a['largest-contentful-paint'].displayValue,
'| CLS', a['cumulative-layout-shift'].displayValue,
'| TBT', a['total-blocking-time'].displayValue)"
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.
- 12d ago Changed · +7 lines 097574370ff8
- 1mo ago First seen · 104 lines · 106 tokens per session scan A 3df6b11e14be
core-web-vitals is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed yesterday), licensed MIT. It adds 106 tokens to every session and 1,242 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
domain-modeling
A practice for building and maintaining a project’s domain model: the shared terms, concrete scenarios, and recorded architecture decisions that describe what the software is about.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
ask-matt
A skill router that helps choose the right workflow or skill for the current task. It maps work from an initial idea through building and shipping, with separate paths for research, prototypes, and multi-session projects.
wizard
A template and process for building an interactive Bash script that guides a person through manual setup, credential, dashboard, migration, or cutover steps.