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 saski/arnesto --skill cwv-improvement-plannergit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/cwv-improvement-planner)<a href="https://agentmods.dev/skills/saski/arnesto/cwv-improvement-planner"><img src="https://agentmods.dev/badge/skills/saski/arnesto/cwv-improvement-planner/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/saski/arnesto/cwv-improvement-planner"><img src="https://agentmods.dev/badge/skills/saski/arnesto/cwv-improvement-planner.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 | $0.00073 | $0.00590 |
| Opus 5 | $0.00036 | $0.00295 |
| Sonnet 5 | $0.00015 | $0.00118 |
| Haiku 4.5 | $0.00007 | $0.00059 |
Grade A, and why
cwv-improvement-planner 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 9d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWV Improvement Planner
Goal
Turn performance findings into a prioritized, measurable rollout plan that improves field Core Web Vitals without platform-specific assumptions.
Use This Skill When
- The user asks for a CWV plan, optimization roadmap, or performance triage.
- The context includes LCP, INP, CLS, TTFB, render-blocking resources, hydration, or preload strategy.
- The stack mentions Next.js, React, CDN/edge caching (including CloudFront), or page-speed regressions.
Cross-Platform Rules
- Use forward-slash paths only.
- Avoid OS-specific command syntax unless the repository already standardizes it.
- Keep recommendations tool-agnostic first, then add stack-specific examples when context confirms the stack.
Workflow
- Establish baseline
- Capture field metrics (RUM/CrUX) and lab traces (Lighthouse/WebPageTest/DevTools).
- Identify highest-impact templates and user journeys (for example, list -> detail -> checkout).
- Prioritize fundamentals first
- Compression and caching correctness at the edge.
- TTFB contributors and redirect chains.
- LCP resource discovery, eager loading, and prioritization.
- Render-blocking CSS/JS and hydration pressure.
- Convert findings into implementation slices
- For each issue: why it matters, what to inspect, recommended change, risk, estimated impact.
- Add acceptance criteria and rollback notes.
- Gate advanced experiments
- Treat 103 Early Hints and Speculation Rules as measured experiments with explicit guardrails.
- Define verification
- Add before/after checks in CI and post-release monitoring thresholds.
Output Template
Use this structure when generating a plan:
# Core Web Vitals Improvement Plan
## Baseline
- Field baseline: LCP, INP, CLS, TTFB by device/network/route.
- Lab baseline: trace links and key waterfall observations.
## Prioritized Work
1. [High] <topic>
- Why
- Inspect
- Change
- Risks
- Expected impact
2. [Medium] <topic>
...
## Experiments
- Hypothesis
- Scope
- Success metric
- Stop conditions
## Validation
- CI assertions
- Release checks
- RUM watch window and thresholds
What ships with it
1 file 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.
- 9d ago First seen · 79 lines · 73 tokens per session scan A 24e948e5295b
cwv-improvement-planner is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed 3d ago), licensed Unlicense. It adds 73 tokens to every session and 590 once invoked, about $0.0004 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
waitlist-page
Minimal pre-launch landing with email capture, brand logo, and optional decorative layer. Reads DESIGN.md for colors, typography, and layout rules. Best for: product launches, beta signups, early access programs, indie projects.
web-prototype
General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed assets/template.html and pasting section layouts from references/layouts.md. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.
saas-landing
Single-page SaaS landing with hero, features, social proof, pricing, and CTA. Respects the active DESIGN.md color/typography/layout tokens. Trigger keywords: "saas landing", "marketing page", "product landing".
worker-visualizer
A real-time data/particle/simulation visualizer whose heavy compute runs in a Web Worker (off the main thread), optionally sharing memory with the UI via SharedArrayBuffer, and renders to a canvas at 60fps. Produced as a single self-contained index.html. Use when the brief asks for a "web worker", "simulation"…
webgl-particle-galaxy
A real-time particle galaxy — tens of thousands of additive-blended GPU points spiraling around a bright core, their orbits solved entirely in the vertex shader (from glVertexID), so the whole cloud draws in one call. Rendered as a single self-contained index.html. Use when the brief asks for a "particle field"…
webgl-liquid-metal
A real-time liquid-metal shader — a domain-warped noise field shaded as molten chrome, with a sweeping specular highlight over an iridescent thin-film (cosine-palette) sheen. No textures. Rendered as a single self-contained index.html. Use when the brief asks for "liquid metal", "molten chrome", "iridescent"…