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 skills add jtrackingai/analytics-tracking-automation --skill tracking-discovergit 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-discover)<a href="https://agentmods.dev/skills/jtrackingai/analytics-tracking-automation/tracking-discover"><img src="https://agentmods.dev/badge/skills/jtrackingai/analytics-tracking-automation/tracking-discover.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 5.1 | $0.00030 | $0.00521 |
| Opus 5 | $0.00015 | $0.00260 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
tracking-discover 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 7d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking Discover
Use this skill for analysis-only work and fresh workflow bootstrap.
Inputs
- target URL
- output root directory
- optional Shopify storefront password
Commands
In this repository, use the repo-root wrapper:
./event-tracking analyze <url> --output-root <output-root>
analyze launches a real Chromium via Playwright to fetch the target site over HTTP. 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.
Before run-new-setup or analyze, if the tool needs a telemetry consent answer and no prior choice is already recorded, stop and follow ../../references/telemetry-consent.md. Do not choose on the user's behalf, and do not continue until they answer.
Partial mode:
./event-tracking analyze <url> --output-root <output-root> --urls https://example.com/page-a,https://example.com/page-b
Required Output
Produce and share:
<artifact-dir>/site-analysis.json<artifact-dir>/workflow-state.json
Report:
- pages analyzed
- skipped URLs
- warnings
- detected
dataLayerevents - detected live GTM container IDs
- detected platform
Closeout Style
- default to a short human-readable analysis summary before listing files
- summarize coverage, platform, GTM detection, and notable warnings first
- do not dump raw page HTML, raw JSON, or full URL inventories unless the user explicitly asks for them
- list generated files and the next command only after the summary
Stop Boundary
Unless the user explicitly asks for the next phase, stop after analysis. If telemetry consent is still unanswered, stop before analysis starts and wait for the user's explicit choice.
If the user wants to continue, the default next command is:
./event-tracking status <artifact-dir>
References
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.
- 7d ago First seen · 73 lines · 30 tokens per session scan A 4b97c805400d
tracking-discover is a skill published in the GitHub repository jtrackingai/analytics-tracking-automation (136 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 30 tokens to every session and 521 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 2026-08-30.
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
A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.
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…