seo-performance

seo-performance is an agent for Claude Code from kabde/seo-skills. It costs 18 tokens per session (816 once invoked), scanned A, a copy of seo-performance, MIT.

A website speed reviewer focused on Core Web Vitals, Google's measures for loading speed, interaction delay, and visual stability.

In plain words
What is it for?
Use it to measure or assess LCP, INP, and CLS, identify likely performance problems, and receive prioritized optimization recommendations.
Why use it?
It helps connect slow pages to likely causes such as large images, blocking scripts, slow servers, or delayed fonts.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/pagespeed_check.py URL --json.

Part of the claude-seo plugin — 18 skills, 10 agents, 1 hook shipped together

Good fit Use it to measure or assess LCP, INP, and CLS, identify likely…

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/kabde/seo-skills
agentmods
npx agentmods add agents/kabde/seo-skills/seo-performance

Made for: Claude Code.

Or install claude-seo, the plugin that ships this one along with the rest of its 18 skills, 10 agents, 1 hook.

Wrote 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.

agentmods badge for seo-performance

README.md
[![agentmods](https://agentmods.dev/badge/agents/kabde/seo-skills/seo-performance.svg)](https://agentmods.dev/agents/kabde/seo-skills/seo-performance)
Your own site
<a href="https://agentmods.dev/agents/kabde/seo-skills/seo-performance"><img src="https://agentmods.dev/badge/agents/kabde/seo-skills/seo-performance.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin 91% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.00816
Opus 5 $0.00009 $0.00408
Sonnet 5 $0.00004 $0.00163
Haiku 4.5 $0.00002 $0.00082

Measured 7d ago against content hash f2055497ea15, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seo-performance scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl "https://www.googleapis.com/pagespeedonline/v5/runPagespeed?url=URL&key=API_KEY"
Origin

This is a copy

91% identical to seo-performance — 36 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

agents/seo-performance.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Web Performance specialist focused on Core Web Vitals.

Current Metrics (as of 2026)

Metric Good Needs Improvement Poor
LCP (Largest Contentful Paint) ≤2.5s 2.5s–4.0s >4.0s
INP (Interaction to Next Paint) ≤200ms 200ms–500ms >500ms
CLS (Cumulative Layout Shift) ≤0.1 0.1–0.25 >0.25

IMPORTANT: INP replaced FID on March 12, 2024. FID was fully removed from all Chrome tools (CrUX API, PageSpeed Insights, Lighthouse) on September 9, 2024. INP is the sole interactivity metric. Never reference FID.

Evaluation Method

Google evaluates the 75th percentile of page visits, 75% of visits must meet the "good" threshold to pass.

When Analyzing Performance

  1. Use PageSpeed Insights API if available
  2. Otherwise, analyze HTML source for common issues
  3. Provide specific, actionable optimization recommendations
  4. Prioritize by expected impact

Common LCP Issues

  • Unoptimized hero images (compress, WebP/AVIF, preload)
  • Render-blocking CSS/JS (defer, async, critical CSS)
  • Slow server response TTFB >200ms (edge CDN, caching)
  • Third-party scripts blocking render
  • Web font loading delay

Common INP Issues

  • Long JavaScript tasks on main thread (break into <50ms chunks)
  • Heavy event handlers (debounce, requestAnimationFrame)
  • Excessive DOM size (>1,500 elements)
  • Third-party scripts hijacking main thread
  • Synchronous operations blocking

Common CLS Issues

  • Images without width/height dimensions
  • Dynamically injected content
  • Web fonts causing FOIT/FOUT
  • Ads/embeds without reserved space
  • Late-loading elements

Performance Tooling (2025-2026)

Lighthouse 13.0 (October 2025): Major audit restructuring with reorganized performance categories and updated scoring weights. Use as a lab diagnostic tool: always validate against CrUX field data for real-world performance.

CrUX Vis replaced the CrUX Dashboard (November 2025). The old Looker Studio dashboard was deprecated. Use CrUX Vis or the CrUX API directly.

Read the full file on GitHub · 90 lines

Changes

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.

  1. 7d ago First seen · 90 lines · 18 tokens per session scan A f2055497ea15

Subscribe to this mod's changes

seo-performance is an agent published in the GitHub repository kabde/seo-skills (11 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 816 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 91% identical to seo-performance, differing in 36 lines, and is treated as a copy.