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 corewebvitals/cwv-superpowers --skill diagnosing-clsgit clone --depth 1 https://github.com/corewebvitals/cwv-superpowersWrote 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/corewebvitals/cwv-superpowers/diagnosing-cls)<a href="https://agentmods.dev/skills/corewebvitals/cwv-superpowers/diagnosing-cls"><img src="https://agentmods.dev/badge/skills/corewebvitals/cwv-superpowers/diagnosing-cls/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/corewebvitals/cwv-superpowers/diagnosing-cls"><img src="https://agentmods.dev/badge/skills/corewebvitals/cwv-superpowers/diagnosing-cls.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 | $0.00086 | $0.02644 |
| Opus 5 | $0.00043 | $0.01322 |
| Sonnet 5 | $0.00017 | $0.00529 |
| Haiku 4.5 | $0.00009 | $0.00264 |
Grade A, and why
diagnosing-cls 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 8d 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing CLS
CLS has no phase breakdown — BREAKDOWN.CLS is ["CLS"]. Diagnosis works by identifying the shifting element and matching it to a cause pattern through cross-dimensional analysis (device type, visitor type, network speed).
Invocation
Called by the cwv-superpower orchestrator at Step 2B, or invoked directly when the user names CLS as the target metric.
Inputs: a target filter (ff or u with value) and a device (default: mobile).
Progress: Print these ↳ sub-status lines as you execute each call:
↳ Identifying shifting element...
↳ Comparing mobile vs desktop...
↳ Comparing new vs repeat visitors...
↳ Checking network speed sensitivity...
↳ Checking 7-day trend...
↳ Analyzing distribution shape... (if warranted)
Attribution calls
All calls use the page filter [FILTER_KEY]: "[FILTER_VALUE]" established by the caller.
1. Shifting element identification
get_metrics metric: CLS, group: clsel, [FILTER_KEY]: "[FILTER_VALUE]"
Returns CLS contribution per CSS selector. The top result is the biggest CLS contributor — this is the shifting element to diagnose.
2. Mobile vs desktop split
get_metrics metric: CLS, [FILTER_KEY]: "[FILTER_VALUE]", d: "mobile"
get_metrics metric: CLS, [FILTER_KEY]: "[FILTER_VALUE]", d: "desktop"
Mobile-only CLS causes:
- Images without responsive sizing (no
width/heightattributes or CSSaspect-ratio) - Ads without reserved space collapsing or expanding on small viewports
- Font metric differences more pronounced on small screens
Desktop-only CLS (rare):
- Sidebar widgets loading late and pushing main content
- Sticky headers recalculating on wider viewports
3. New vs repeat visitor split
get_metrics metric: CLS, [FILTER_KEY]: "[FILTER_VALUE]", fv: "1"
get_metrics metric: CLS, [FILTER_KEY]: "[FILTER_VALUE]", fv: "0"
fv values: 0 = repeat visitor, 1 = new visitor, 2 = not measured (via settings).
A significant gap where new visitors have worse CLS points to uncached resources causing shifts (web fonts, third-party scripts loaded fresh).
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.
- 8d ago First seen · 215 lines · 86 tokens per session scan A a74587c1f0cd
diagnosing-cls is a skill published in the GitHub repository corewebvitals/cwv-superpowers (12 stars, last pushed 2mo ago), licensed MIT. It adds 86 tokens to every session and 2,644 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 2026-08-30.
Other skills, from other repositories
inspecting-hermes-desktop-dom
Read the live Hermes desktop DOM/CSS over CDP.
fixing-motion-performance
Audit and fix animation performance issues including layout thrashing, compositor properties, scroll-linked motion, and blur effects. Use when animations stutter, transitions jank, or reviewing CSS/JS animation performance.
optimize-web-animations
Profile, audit, and optimize frontend page performance with emphasis on animation work, memory-leak risks, long-session slowdowns, CSS animations, canvas/WebGL requestAnimationFrame loops, marquees, skeletons, GSAP/Three/Matter effects, timers, listeners, and observers. Use when the user asks to make animations…
weapp-tailwindcss-troubleshoot
A troubleshooting guide for weapp-tailwindcss and its CLI when generated styles, class conversion, builds, or hot reload do not work as expected.
Dark Mode Bug Finder
Detect dark mode rendering issues including contrast failures, missing theme tokens, image inversions, and transition glitches across components.
web-animation-perf
Prevent layout/transition/reflow thrash in JS-driven CSS animations. Use when building or debugging continuous motion (rotation, orbit, parallax, scroll-linked effects, marquee, carousels) and when symptoms appear like jank, stutter, lag, animation drift, ghosting, "elements collapsing toward center", "going slow"…