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 skills/ziniman/ai-instruct/google-analytics-4npx skills add ziniman/ai-instruct --skill google-analytics-4git clone --depth 1 https://github.com/ziniman/ai-instructWrote 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/ziniman/ai-instruct/google-analytics-4)<a href="https://agentmods.dev/skills/ziniman/ai-instruct/google-analytics-4"><img src="https://agentmods.dev/badge/skills/ziniman/ai-instruct/google-analytics-4.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 | $0.00118 | $0.05235 |
| Opus 5 | $0.00059 | $0.02618 |
| Sonnet 5 | $0.00024 | $0.01047 |
| Haiku 4.5 | $0.00012 | $0.00524 |
Grade A, and why
google-analytics-4 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 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.
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 — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Analytics 4 Implementation Guide
Applies to: Any website or web app | Updated: February 2026
A practical guide for implementing Google Analytics 4 (GA4) - covering installation, critical first-time setup, event tracking, e-commerce, consent, and advanced topics. Written for AI coding assistants: skip sections that don't apply to the user's setup.
Note: Universal Analytics (UA / GA3) was fully sunset in 2024. GA4 is the only current Google Analytics product.
Section 0: Before You Start
Answer these questions before writing any code. They determine which sections apply.
Q: Are any of your visitors in Europe (EU/EEA) or the UK? Default: no - if yes, Consent Mode v2 setup is required (see Consent Mode v2)
Q: Do you run Google Ads (search, display, YouTube, or Shopping)? Default: no - if yes, ad consent signals matter for conversion tracking and which events you mark as conversions
Q: Is your site a single-page app (React, Vue, Angular, Next.js, etc.) where the URL changes without a full page reload?
Default: check the project for package.json, next.config.*, vite.config.*, angular.json, or nuxt.config.* - if found, assume SPA and apply the Single-Page Apps section automatically
Q: Do you need to track purchases or sales? Default: no - skip E-commerce Tracking if no
Q: Do you already have a GA4 property, or is this a fresh start? Default: fresh start - if fresh start, create a property at analytics.google.com before writing any code
Q: Do you use Google Tag Manager, or add the tracking code directly? Default: direct gtag.js - recommend GTM only if the user has a marketing team managing multiple tags
AI assistant: Use these answers to skip irrelevant sections. Do not implement Consent Mode unless the user confirms EU/EEA/UK users. Do not implement e-commerce unless confirmed. If a SPA framework is detected in the project, automatically apply the SPA page_view section. Do not add
anonymize_ip- it is a no-op in GA4 (see Common Pitfalls).
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 · 538 lines · 118 tokens per session scan A 33cff546e77e
google-analytics-4 is a skill published in the GitHub repository ziniman/ai-instruct (28 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 118 tokens to every session and 5,235 once invoked, about $0.0006 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
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.
finance-investor-relations
투자 유치를 위한 IR 피치덱과 3개년 재무 모델(매출 예측·손익·현금흐름·밸류에이션)을 만들어 드립니다. 다음과 같은 요청 시 사용하세요: "IR 덱 만들어줘" "투자자 피치 자료 써줘" "재무 모델 만들어줘" "매출 예측 좀 해줘" "밸류에이션 계산해줘" "시리즈 A 투자 유치 자료 준비해줘" "투자자 보고서 정리해줘" 투자 단계(Pre-SeedSeries B)에 맞춘 12슬라이드 피치덱·재무 모델·예상 질문 Q&A를 만들고, PPT/엑셀 변환으로 이어집니다.