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-lcpgit 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-lcp)<a href="https://agentmods.dev/skills/corewebvitals/cwv-superpowers/diagnosing-lcp"><img src="https://agentmods.dev/badge/skills/corewebvitals/cwv-superpowers/diagnosing-lcp/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-lcp"><img src="https://agentmods.dev/badge/skills/corewebvitals/cwv-superpowers/diagnosing-lcp.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 | $0.00089 | $0.02935 |
| Opus 5 | $0.00044 | $0.01468 |
| Sonnet 5 | $0.00018 | $0.00587 |
| Haiku 4.5 | $0.00009 | $0.00294 |
Grade A, and why
diagnosing-lcp 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagnosing LCP
Invocation
Called by the cwv-superpower orchestrator at Step 2B, or invoked directly when the user names LCP as the target metric.
Inputs: a target filter (ff or u with value) and a device (default: mobile).
Run the attribution, breakdown, and trend calls below, then interpret results.
Progress: Print these ↳ sub-status lines as you execute each call:
↳ Identifying LCP element...
↳ Checking element type...
↳ Checking priority state...
↳ Breaking down LCP phases...
↳ Analyzing distribution shape... (if warranted)
↳ Checking 7-day trend...
Attribution calls
Use [FILTER_KEY] and [FILTER_VALUE] as placeholders — SKILL.md fills these based on the selected page filter.
1. LCP Element (CSS selector)
get_metrics with:
metrics: "LCP"
group: "lcpel"
[FILTER_KEY]: "[FILTER_VALUE]"
d: "mobile"
Identifies the LCP element as a CSS selector. The top result by traffic volume is the most common LCP element on the page. Use this to know exactly which DOM element is the LCP.
2. Element Type
get_metrics with:
metrics: "LCP"
group: "lcpet"
[FILTER_KEY]: "[FILTER_VALUE]"
d: "mobile"
Returns the type of the LCP element. Possible values: image, text, background-image, video. This determines which optimization strategies apply — image LCPs have different fixes than text LCPs.
3. Priority State
get_metrics with:
metrics: "LCP"
group: "lcpprio"
[FILTER_KEY]: "[FILTER_VALUE]"
d: "mobile"
Returns the priority/loading state of the LCP resource. Values:
| Value | Meaning |
|---|---|
| 0 | Not an image |
| 1 | Preloaded |
| 2 | High fetchpriority |
| 3 | Not preloaded |
| 4 | Lazy loaded |
Key insight: Priority 3 (not preloaded) is the most common fixable LCP issue — the image exists but the browser discovers it late. Priority 4 (lazy loaded) is actively harmful for LCP because loading="lazy" defers the load until the element is near the viewport, which directly delays the largest paint.
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 · 274 lines · 89 tokens per session scan A ed369d1134f2
diagnosing-lcp is a skill published in the GitHub repository corewebvitals/cwv-superpowers (12 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 2,935 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.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
devtools
Drop-in inspector panel for any json-render app. Use when the user wants to debug a generative UI, inspect the spec tree, edit state at runtime, see dispatched actions, follow stream patches live, browse a catalog, or pick DOM elements to find their spec keys. Triggers include "add devtools", "debug json-render"…
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
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…