google-analytics

google-analytics is a skill for Codex from san-npm/skills-ws. It costs 74 tokens per session (4,641 once invoked), scanned A, original, MIT.

A guide for setting up and analysing Google Analytics 4, Google’s service for measuring how people use websites and apps. It covers events, user details, advertising connections, consent settings, reports, and data exports.

In plain words
What is it for?
Use it to plan or fix GA4 tracking, configure Google Tag Manager and Consent Mode, define key events, create audiences and reports, connect Google Ads, or query exported data.
Why use it?
It helps replace inconsistent tracking with a clear measurement plan and shared event names. That makes actions such as sign-ups, purchases, and onboarding easier to analyse.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Use it to plan or fix GA4 tracking, configure Google Tag Manager and Consent Mode, define key events, create audiences and reports, connect Google Ads, or query exported data.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/san-npm/skills-ws/google-analytics
Install

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.

Any agent
npx skills add san-npm/skills-ws --skill google-analytics
Clone the repo
git clone --depth 1 https://github.com/san-npm/skills-ws

Made for: Codex.

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 google-analytics

README.md
[![agentmods](https://agentmods.dev/badge/skills/san-npm/skills-ws/google-analytics/github.svg)](https://agentmods.dev/skills/san-npm/skills-ws/google-analytics)
Your own site
<a href="https://agentmods.dev/skills/san-npm/skills-ws/google-analytics"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/google-analytics/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.

agentmods 80×15 button for google-analytics

Your own site · 80×15
<a href="https://agentmods.dev/skills/san-npm/skills-ws/google-analytics"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/google-analytics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,641 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 $0.00074 $0.04641
Opus 5.5 $0.00030 $0.01856
Sonnet 5.5 $0.00015 $0.00928
Haiku 4.5 $0.00007 $0.00464

Measured 2mo ago against content hash 98500975e94d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

google-analytics 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 2mo 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.

skills/google-analytics/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Analytics 4

Workflow

1. Measurement Plan

Before touching GA4, define what matters:

Layer Question Example
Business objective What's the goal? Increase trial signups 20%
KPI How do we measure? Trial signup rate, activation rate
Events What do we track? sign_up, tutorial_complete, plan_selected
Dimensions What context? plan_type, referral_source, user_role

2. Event Taxonomy

Use a consistent naming convention. Never use spaces or capitals in event names.

Naming pattern: object_action (noun_verb)

# Core events (auto-collected — don't recreate)
page_view, session_start, first_visit, user_engagement

# Recommended events (use GA4 standard names)
sign_up, login, purchase, add_to_cart, begin_checkout

# Custom events (your business logic)
trial_started
feature_activated
plan_upgraded
invite_sent
onboarding_completed
support_ticket_opened

Implementation (gtag.js):

// Custom event with parameters
gtag('event', 'trial_started', {
  plan_type: 'pro',
  referral_source: 'pricing_page',
  value: 49
});

// User property (set once per user)
gtag('set', 'user_properties', {
  account_type: 'enterprise',
  company_size: '50-200'
});

GTM dataLayer push:

dataLayer.push({
  event: 'plan_upgraded',
  plan_from: 'free',
  plan_to: 'pro',
  mrr_delta: 49
});

3. GTM Implementation & Consent Mode v2

If you load GA4 through Google Tag Manager (web container), use exactly one GA4 base tag plus event tags — never also hardcode gtag.js for the same property (that is the #1 cause of doubled events).

Tag structure:

  • Google tag (G-XXXXXXX) — fires once on Initialization - All Pages (formerly the "GA4 Configuration" tag; renamed to the unified Google tag). Set shared fields/user properties here.
  • GA4 Event tags — one per custom event, triggered by a Custom Event trigger matching your dataLayer event name. Map dataLayer values into Event parameters (these become GA4 event params; register them as custom definitions — section 4 — to use them in reports).
  • Pass enhanced-measurement-overlapping events carefully; disable GA4 enhanced measurement options you are sending manually to avoid duplicates (e.g. don't send a manual page_view if enhanced measurement page views are on).

Read the full file on GitHub · 327 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2mo ago First seen · 327 lines · 74 tokens per session scan A 98500975e94d

Subscribe to this mod's changes

google-analytics is a skill published in the GitHub repository san-npm/skills-ws (4 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 4,641 once invoked, about $0.0003 per session on Opus 5.5. 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.

Related

google-analytics compared with skills from other repositories

google-analytics next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
google-analyticssan-npm/skills-wsSkill41mo agoMITA74Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code