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 Infinite-Labs-AI/infinite-skills --skill analytics-trackinggit clone --depth 1 https://github.com/Infinite-Labs-AI/infinite-skillsWrote 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/infinite-labs-ai/infinite-skills/analytics-tracking)<a href="https://agentmods.dev/skills/infinite-labs-ai/infinite-skills/analytics-tracking"><img src="https://agentmods.dev/badge/skills/infinite-labs-ai/infinite-skills/analytics-tracking/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.
<a href="https://agentmods.dev/skills/infinite-labs-ai/infinite-skills/analytics-tracking"><img src="https://agentmods.dev/badge/skills/infinite-labs-ai/infinite-skills/analytics-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00039 | $0.00483 |
| Opus 5.5 | $0.00016 | $0.00193 |
| Sonnet 5.5 | $0.00008 | $0.00097 |
| Haiku 4.5 | $0.00004 | $0.00048 |
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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analytics Tracking
Check whether marketing tracking is reliable enough to make decisions about budget, funnel performance, and growth.
Start With Decisions
Ask what decisions the data is supposed to support:
- Which channel gets more budget.
- Which campaigns convert.
- Which pages or steps leak users.
- Which leads become revenue.
- Which lifecycle messages work.
- Which experiments win.
Tracking is not trustworthy because tags fire; it is trustworthy when the decision chain is complete.
Inspect The Chain
Trace:
- Source capture: UTMs, referrer, click IDs, campaign naming.
- Event capture: page views, leads, signups, purchases, activation, qualified lead, revenue.
- Identity: anonymous to known user, lead to account, account to deal.
- Destination: analytics, ad platforms, CRM, warehouse, dashboards.
- Definitions: what counts as a conversion, lead, MQL, opportunity, customer.
- Consent and privacy boundaries.
- Reconciliation: totals across systems and expected gaps.
Flag Trust Breaks
- Events fire but are not tied to the business outcome.
- Multiple systems define the same metric differently.
- UTMs overwrite or disappear.
- Test traffic pollutes reports.
- Duplicate conversions feed paid bidding.
- PII leaks into analytics or ad tools.
- Dashboards hide uncertainty.
- Offline revenue never connects back to campaigns.
Judge Data Confidence
For each decision, state:
- Trust level: high, usable with caveats, directional only, not usable.
- Known gaps.
- Acceptable uncertainty.
- Reconciliation owner.
- Next check that would raise trust.
Output
Tracking trust read:
[one paragraph]
Decision chain:
Question -> Required signal -> Source -> Destination -> Owner
Decision trust:
| Decision | Trust level | Known gaps | Acceptable uncertainty | Reconciliation owner |
Trust breaks:
| Break | Evidence | Decision affected | Fix | Priority |
Measurement plan:
| Event | Trigger | Parameters | Destination | Success criteria |
Naming rules:
- [UTM or event rule]
Reconciliation checks:
1. [check]
2. [check]
Privacy risks:
- [risk]
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.
- 1mo ago First seen · 84 lines · 39 tokens per session scan A 839fbe3ecd7b
analytics-tracking is a skill published in the GitHub repository Infinite-Labs-AI/infinite-skills (44 stars, last pushed 2mo ago), licensed MIT. It adds 39 tokens to every session and 483 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
follow-loop
A manually triggered research workflow that gathers evidence about selected technology and luxury topics, then sends verified findings to long-term records.
pr-consumer-research
A skill for turning existing consumer, market, competitor, voice-of-customer, or product-test evidence into public-relations decisions. It links research findings to what a company can safely say in public and what it should do next.
consumer-research
A consumer research skill for studying what people buy, prefer, and say about consumer products. It helps plan studies and turn findings into useful insights.
industry-research
A skill for researching an industry and producing decision-focused analysis. It covers markets, customers, technology, costs, competitors, channels, supply chains, policy, investment, and risks.
hot-public-opinion-analysis
A public-opinion analysis skill for examining trending events, widely discussed news, industry disputes, competitor incidents, policy changes, negative narratives, rumours, and social topics.
judgment-hub
A decision-making skill for public-relations situations that require a final call, risk trade-offs, task routing, or strategic judgment.