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 agentmods add agents/buithang3058/agentic-seo/seo-performancegit clone --depth 1 https://github.com/buithang3058/Agentic-SEOWrote 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/agents/buithang3058/agentic-seo/seo-performance)<a href="https://agentmods.dev/agents/buithang3058/agentic-seo/seo-performance"><img src="https://agentmods.dev/badge/agents/buithang3058/agentic-seo/seo-performance.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01308 |
| Opus 5 | $0.00009 | $0.00654 |
| Sonnet 5 | $0.00004 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
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 4d 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" This is a copy
100% identical to seo-performance — 0 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.
How it starts
The opening of the file, as written. The whole thing — 134 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.
Available Scripts
| Script | Purpose | Command |
|---|---|---|
pagespeed.py |
PageSpeed Insights API call | python3 pagespeed.py <url> --json |
parse_html.py |
HTML source analysis for issues | python3 parse_html.py --url <url> --json |
Current Metrics (as of February 2026)
LCP (Largest Contentful Paint) — Loading
| Rating | Threshold |
|---|---|
| Good | ≤2.5s |
| Needs Improvement | 2.5–4.0s |
| Poor | >4.0s |
LCP Subparts (available in CrUX since February 2025):
| Subpart | Description | Target |
|---|---|---|
| TTFB | Time to First Byte | <800ms |
| Resource Load Delay | Gap before LCP resource starts | <100ms |
| Resource Load Duration | Download time for LCP element | <700ms |
| Element Render Delay | Time from download to paint | <50ms |
INP (Interaction to Next Paint) — Interactivity
| Rating | Threshold |
|---|---|
| Good | ≤200ms |
| Needs Improvement | 200–500ms |
| Poor | >500ms |
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.
CLS (Cumulative Layout Shift) — Visual Stability
| Rating | Threshold |
|---|---|
| Good | ≤0.1 |
| Needs Improvement | 0.1–0.25 |
| Poor | >0.25 |
Evaluation Method
Google evaluates the 75th percentile of page visits — 75% of visits must meet the "good" threshold to pass.
Common LCP Issues & Fixes
| Issue | Fix | Impact |
|---|---|---|
| Unoptimized hero image | Compress, convert to WebP/AVIF, add <link rel="preload"> |
High |
| Render-blocking CSS/JS | defer/async scripts, inline critical CSS |
High |
| Slow TTFB (>800ms) | Edge CDN, server-side caching, reduce redirects | High |
| Third-party scripts blocking render | defer load, move to footer |
Medium |
| Web font delay (FOIT) | font-display: swap, preload key fonts |
Medium |
| Large DOM (>1500 nodes) | Simplify layout, lazy-load below-fold | Medium |
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.
- 4d ago First seen · 134 lines · 18 tokens per session scan A 3b08da9d475e
seo-performance is an agent published in the GitHub repository buithang3058/Agentic-SEO (2 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,308 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 100% identical to seo-performance, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
PARALLEL-AUDIT
Platform-neutral definitions for delegating independent audit slices. Same routing and scripts as references/procedures/ and AGENTS.md — this file only names who runs what when using a Task/subagent tool.
seo-schema
Schema markup expert. Detects, validates, and generates Schema.org structured data in JSON-LD format.
seo-visual
Visual analyzer. Captures screenshots, tests mobile rendering, and analyzes above-the-fold content using Playwright.
seo-performance
Performance analyzer. Measures and evaluates Core Web Vitals and page load performance.
seo-content
Content quality reviewer. Evaluates E-E-A-T signals, readability, content depth, AI citation readiness, and thin content detection.
seo-sitemap
Sitemap architect. Validates XML sitemaps, generates new ones with industry templates, and enforces quality gates for location pages.