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/jtrackingai/analytics-tracking-automation/tracking-schemanpx skills add jtrackingai/analytics-tracking-automation --skill tracking-schemagit clone --depth 1 https://github.com/jtrackingai/analytics-tracking-automationWrote 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/jtrackingai/analytics-tracking-automation/tracking-schema)<a href="https://agentmods.dev/skills/jtrackingai/analytics-tracking-automation/tracking-schema"><img src="https://agentmods.dev/badge/skills/jtrackingai/analytics-tracking-automation/tracking-schema.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 | $0.00025 | $0.00882 |
| Opus 5 | $0.00013 | $0.00441 |
| Sonnet 5 | $0.00005 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
tracking-schema 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 5d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking Schema
Use this skill for Step 3 work only.
Inputs
One of:
- confirmed
<artifact-dir>/site-analysis.json - existing
<artifact-dir>/event-schema.json
Workflow
Role And Quality Bar
During schema work, act as an expert in event tracking design.
Your job is not to list generic events. Your job is to produce a tracking plan that is:
- aligned with common GA4 / GTM industry standards
- comprehensive enough to cover the site's meaningful business journeys
- accurate enough to be implemented and verified without guesswork
- disciplined enough to avoid noisy, redundant, or low-signal events
- easy for the user to review, approve, QA, and maintain
Favor event definitions that are business-meaningful, implementation-ready, and analytically useful. Do not preserve weak legacy patterns just for continuity. Do not inflate the schema with events that add little reporting or decision value.
If the telemetry consent prompt appears and no prior choice is recorded, stop and follow ../../references/telemetry-consent.md before continuing.
If schema context is not prepared yet:
./event-tracking prepare-schema <artifact-dir>/site-analysis.json
If the site has a live GTM container installed, make sure tracking-live-gtm has already produced <artifact-dir>/live-gtm-analysis.json before running prepare-schema.
Then:
validate-schema --check-selectors launches a real Chromium via Playwright to test each schema selector against the live site. Run it in an environment that permits outbound network and local browser execution; environments that restrict either tend to cause Playwright to hang or fail silently rather than return a clean error.
./event-tracking validate-schema <artifact-dir>/event-schema.json --check-selectors
./event-tracking generate-spec <artifact-dir>/event-schema.json
./event-tracking confirm-schema <artifact-dir>/event-schema.json
During review:
- explain what live tracking problems the schema fixes when
live-gtm-analysis.jsonis present - explain what benefits the new schema brings compared with the current live baseline
- default to a compact tracking-plan summary in this order:
Event Table,Common Properties,Event-specific Properties - keep long parameter inventories out of the main event table
- stop for user approval before GTM generation
- a broad request such as "full workflow" or "全流程" does not count as schema approval
- do not run
./event-tracking confirm-schema <artifact-dir>/event-schema.json --yeson the user's behalf unless the user explicitly confirms the schema and parameters in the current turn
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.
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.
- 5d ago First seen · 100 lines · 25 tokens per session scan A dd7e4e979a1e
tracking-schema is a skill published in the GitHub repository jtrackingai/analytics-tracking-automation (135 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 882 once invoked, about $0.0001 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
analytics
Use when instrumenting product or web analytics — GA4/PostHog SDK wiring, event taxonomy, funnels, double-counted events, consent gating, PII scrubbing. NOT charting that data (that is dashboard), NOT choosing which metrics matter (that is kpi-framework), NOT experiment math (that is ab-testing), NOT cookie-policy…
web-analytics
Analyze web traffic, SEO performance, and search engine trends using Google Search Console, Google Analytics 4, and Bing Webmaster Tools. Use when the user asks to analyze traffic, check SEO, or find keyword opportunities.
karpathy-llm-wiki
Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.
proxies
Oxylabs proxy networks: Residential, Mobile, shared Datacenter/ISP, and Dedicated Datacenter/ISP proxies with geo-targeting, IP rotation, session persistence, and port-based sticky IPs. Use when routing traffic through proxies, building scrapers with proxy auth, rotating or sticky sessions, whitelisting IPs, or…
short-drama
制作多集 AI 微短剧：建立剧集圣经和角色参考，完成分集剧本、逐镜 I2V、对白审计、配音字幕 BGM 与成片，保持跨镜跨集一致性。 当用户说“AI/横屏/竖屏/微短剧、拍短剧、分集剧本、连续剧情视频、做几集短剧”时使用。 单条非剧情视频用 auto-short-video；只写单条脚本用 video-script；只生成一个视频片段用 ai-video-gen。.
agentsop-llamaindex
Operating-system distillation of LlamaIndex — the leading RAG / document-agent framework. Activate when the calling agent must build, debug, harden, or evaluate a Retrieval-Augmented Generation pipeline over unstructured/private data, decide between RAG primitives (Index types, retrievers, query engines, routers…