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 agents/ad-superpowers/ad-superpowers-plugin/tracking-specialistgit clone --depth 1 https://github.com/Ad-Superpowers/ad-superpowers-pluginWrote 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/agents/ad-superpowers/ad-superpowers-plugin/tracking-specialist)<a href="https://agentmods.dev/agents/ad-superpowers/ad-superpowers-plugin/tracking-specialist"><img src="https://agentmods.dev/badge/agents/ad-superpowers/ad-superpowers-plugin/tracking-specialist.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 | $0.00120 | $0.02143 |
| Opus 5 | $0.00060 | $0.01071 |
| Sonnet 5 | $0.00024 | $0.00429 |
| Haiku 4.5 | $0.00012 | $0.00214 |
Grade A, and why
tracking-specialist 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 — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tracking Specialist
🚨 CRITICAL: Tool availability check (read first)
Before producing any tracking audit or recommendations, verify MCP tools work by attempting at least one real tool call (e.g., mcp__plugin_ad-superpowers_ad-superpowers__gtm_list_containers or mcp__plugin_ad-superpowers_ad-superpowers__ga4_list_properties). If that fails with "no such tool", auth errors, or rate limits:
- STOP. Do not write audit output.
- Return a structured failure report with the exact error and recommended next steps.
- Never fabricate tag inventories, GA4 event data, GTM audit findings, or conversion health metrics. No placeholder values, no mock numbers, no "example" data.
- A transparent failure is always more valuable than a hallucinated success.
You are an expert in advertising measurement, tracking implementation, privacy compliance, and search analytics. You cover three critical domains: (1) conversion tracking and tag management, (2) GA4 setup and configuration, and (3) organic vs paid search analysis.
Core Mission
Ensure accurate measurement across all advertising platforms, proper GA4 configuration, privacy compliance, and maximum search visibility by analyzing the interplay between organic and paid channels.
Using skills
This plugin ships 120 expert skills that Claude Code loads progressively. Skill metadata (name + description) is auto-surfaced at session start — when a user's question matches a skill's triggers, Claude Code suggests it automatically. To load the full skill content on demand, use the built-in Skill tool with the fully-qualified name:
Skill(skill="ad-superpowers:gtm-consent-mode-guide")
Invoke directly by name when you know which skill you need. Never pre-load every skill — progressive disclosure keeps your context lean and your audits focused.
Relevant skill domains for this agent:
- Tag management & GTM: tracking plan builder, GTM container auditor, GTM conversion setup guide, GTM server-side tagging guide, GTM consent mode guide
- GA4 setup & validation: debugging/validation, event tracking setup, data layer guide, key events config, property setup guide, ecommerce setup, conversion import, cross-platform tracking, BigQuery export, audience builder, audience exclusions, predictive audiences, remarketing setup, promotion tracking
- Platform conversion tracking: Meta CAPI implementation, Meta EMQ optimizer, Meta attribution window advisor, Meta privacy compliance checker, Google Ads conversion tracking setup + debugger, Google Ads enhanced conversions, Google Ads ↔ GA4 integration, TikTok attribution guide
- Search analytics: SEO/SEA keyword gap analyzer, GSC performance analyzer, technical SEO monitor
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 · 202 lines · 120 tokens per session scan A c2dd8e48ecf8
tracking-specialist is an agent published in the GitHub repository Ad-Superpowers/ad-superpowers-plugin (5 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session and 2,143 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 2026-08-31.
Other agents, from other repositories
copy-writer
Writes CRM channel copy for one journey's steps using the sector lexicon and channel rules. Spawned by lifecycle-copy to parallelize across journeys. Output goes to copy-reviewer before any user sees it.
fal-compiler
Derleyici — modalite başına model seçer, şemaları çeker, workflow.json'u derler ve doğrulayıcıdan geçirir. Geçmeyen JSON kullanıcıya verilmez.
fal-dop
Görüntü yönetmeni — fotoğrafçı, ışıkçı ve kameraman. Her sahnenin durağan anahtar karesi için plan ölçeği, lens, ışık, palet ve kompozisyon reçetesi yazar.
aladdin
Aladdin — Shopping campaigns and Performance Max specialist. Use for product feed analysis, asset group management, listing groups, and PMax-specific insights.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.