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.
git clone --depth 1 https://github.com/prashishh/seo-geo-report-enginenpx agentmods add skills/prashishh/seo-geo-report-engine/web-vitalsWrote 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/prashishh/seo-geo-report-engine/web-vitals)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/web-vitals"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/web-vitals/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/prashishh/seo-geo-report-engine/web-vitals"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/web-vitals.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 | $0.00154 | $0.01173 |
| Opus 5 | $0.00077 | $0.00587 |
| Sonnet 5 | $0.00031 | $0.00235 |
| Haiku 4.5 | $0.00015 | $0.00117 |
Grade A, and why
web-vitals 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 10d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
web-vitals
Gets the real, online Core Web Vitals for a live URL and reads them honestly. This is the
measurement skill; the optimization methodology lives in core-web-vitals and performance.
Why a separate skill
core-web-vitals and performance describe how to FIX speed. This skill answers "where do we
actually stand right now?" using live data from Google's PageSpeed Insights API — both the
field (CrUX, real Chrome users, what Google ranks on) and lab (Lighthouse, a single
controlled load) numbers. Never report lab numbers as if they were field reality.
Tool
Stdlib, no install. Hits the free PageSpeed Insights API:
./bin/mkt 2>/dev/null # (just to resolve a usable python)
python3 tools/connectors/pagespeed.py <url> # mobile
python3 tools/connectors/pagespeed.py <url> desktop
python3 tools/connectors/pagespeed.py <url> both # mobile + desktop
It returns: performance_score, field_cwv (LCP / INP / CLS / FCP / TTFB with a good /
needs-improvement / poor verdict each), field_overall, the lab timings, and the top
opportunities. API key: the call works anonymously but is rate-limited (HTTP 429). For
repeated use add a free GOOGLE_PSI_API_KEY to config/secrets.env (one click at
developers.google.com/speed). The tool retries with backoff and prints a clear message if throttled.
Workflow (PERCEIVE → ANALYZE → VALIDATE → ACT)
-
PERCEIVE. Run the tool for the target URL, mobile first (Google indexes mobile). Pull
bothwhen desktop matters too. If the field block is empty, the URL lacks enough CrUX traffic — say so, and fall back to the lab numbers explicitly labeled as lab-only. -
ANALYZE. Grade each Core Web Vital against the thresholds:
- LCP (loading): good ≤ 2.5s · poor > 4.0s
- INP (interactivity): good ≤ 200ms · poor > 500ms
- CLS (visual stability): good ≤ 0.10 · poor > 0.25
Lead with the field verdict (that's the real-user truth and the ranking signal); use lab +
opportunitiesto explain why a failing metric fails. A page can pass field while failing lab, or vice-versa — call that out, don't average them.
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.
- 10d ago First seen · 81 lines · 154 tokens per session scan A 0a1c27754538
web-vitals is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 154 tokens to every session and 1,173 once invoked, about $0.0008 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
accessibility-audit
Run an accessibility audit for a SEOJuice-tracked website. Shows WCAG issues, severity distribution, and auto-fixable items. Use when the user asks about accessibility, WCAG compliance, a11y, or screen reader support.
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
cold-outbound-sequencer
Use when the user asks to "build a B2B cold-outbound sequence", "design reply-triage branching", "plan a domain warmup / sending throttle", or "make my outbound CAN-SPAM / opt-in compliant"; produces a multi-step outbound sequence with reply-triage branches (positive / objection / referral / not-now / opt-out), a…
inbox-placement-monitor
Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP…
subject-line-lab
Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; produces a labeled subject + preheader variant set and a per-variant heuristic pre-score card — spam-trigger flags, length/truncation across desktop + mobile…