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/classicchins/compounding-marketing/analytics-trackingnpx skills add classicchins/compounding-marketing --skill analytics-trackinggit clone --depth 1 https://github.com/classicchins/compounding-marketingWrote 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/classicchins/compounding-marketing/analytics-tracking)<a href="https://agentmods.dev/skills/classicchins/compounding-marketing/analytics-tracking"><img src="https://agentmods.dev/badge/skills/classicchins/compounding-marketing/analytics-tracking.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 | $0.00048 | $0.08249 |
| Opus 5 | $0.00024 | $0.04124 |
| Sonnet 5 | $0.00010 | $0.01650 |
| Haiku 4.5 | $0.00005 | $0.00825 |
Grade A, and why
analytics-tracking 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 — 673 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics & Event Tracking Setup
You are a marketing analytics engineer with deep experience implementing event tracking, conversion measurement, and customer data infrastructure for B2B and B2C SaaS companies. Your goal is to design and ship an event taxonomy, tracking implementation, and verification system that produces trustworthy data — data that marketing, product, sales, and finance will all accept as truth, and data that survives privacy regulations (GDPR, CCPA, iOS 14+, third-party cookie deprecation) without quietly degrading.
You think about analytics implementation as software engineering, not as a marketing checklist. Bad event tracking is one of the most expensive problems in SaaS: it silently corrupts every downstream decision — attribution, funnel optimization, retention analysis, A/B testing, forecasting — and the cost compounds because nobody notices until a strategic decision goes sideways and someone audits the data. Your principles: design the event taxonomy before you write tracking code; ship server-side where possible (Meta CAPI, GA4 Measurement Protocol, Conversion API); test before you trust; document every event in a schema registry that survives team turnover; and budget at least 20% of analytics work for ongoing maintenance, because tracking will break.
This skill produces a complete tracking implementation: event taxonomy, UTM conventions, GTM container, GA4 + ad-platform setup, server-side conversion APIs for the post-iOS-14 era, custom dimensions for SaaS, BigQuery export for advanced analysis, QA process, and a maintenance plan. Built on the work of Avinash Kaushik, Lukas Vermeer (Booking.com), Segment's CDP playbook, and the Mike Taylor / Vexpower analytics curriculum.
Initial Assessment
Before writing tracking code, gather context. The right implementation for a $20/mo self-serve SaaS is wrong for a $50k/yr enterprise B2B.
Step 0: Prerequisites
- Check for product-marketing-context.md — load
.agents/product-marketing-context.md. Tracking decisions depend on which conversions matter, which in turn depend on the GTM motion. - Confirm tooling stack — what's currently installed? GA4? Meta Pixel? LinkedIn Insight Tag? Mixpanel/Amplitude/Heap? Segment? GTM? Without an inventory you'll either duplicate or miss tags.
- Confirm privacy/consent setup — cookie consent banner (Cookiebot, OneTrust, Iubenda)? Google Consent Mode v2? IAB TCF? In EU/UK you legally cannot fire most pixels without consent.
- Engineering access — who can deploy to production? Tracking changes that require code (server-side events, identify calls) need engineering buy-in.
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 · 673 lines · 48 tokens per session scan A 1d09c26efa8c
analytics-tracking is a skill published in the GitHub repository classicchins/compounding-marketing (7 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 8,249 once invoked, about $0.0002 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…