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 squadcodercom/squadcoder --skill ad-measurement-trackinggit clone --depth 1 https://github.com/squadcodercom/squadcoderWrote 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/squadcodercom/squadcoder/ad-measurement-tracking)<a href="https://agentmods.dev/skills/squadcodercom/squadcoder/ad-measurement-tracking"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/ad-measurement-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/squadcodercom/squadcoder/ad-measurement-tracking"><img src="https://agentmods.dev/badge/skills/squadcodercom/squadcoder/ad-measurement-tracking.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00195 | $0.03845 |
| Opus 5.5 | $0.00078 | $0.01538 |
| Sonnet 5.5 | $0.00039 | $0.00769 |
| Haiku 4.5 | $0.00019 | $0.00384 |
Grade A, and why
ad-measurement-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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad Measurement & Conversion Tracking (Cross-Platform)
The measurement layer is the foundation under every paid channel. If tracking is wrong, every bid strategy, budget decision, and creative test downstream is wrong too. This skill is the shared backbone the platform skills (Meta, Google, TikTok, etc.) reference for "how do we count a conversion and feed it back to the algorithm."
Golden rule: measure once, define events consistently across all platforms, send server-side where possible, dedupe so you never double-count, and respect consent. Get this right before scaling spend.
1. Measurement architecture (the mental model)
Three layers, in this order:
- Source of truth — GA4 (+ optionally a warehouse/BigQuery export) and your backend/CRM. This is where business conversions live, immune to any single ad platform's self-attribution.
- Ad-platform signal layer — each platform's pixel + server-side API (Meta Pixel + CAPI, Google tag + Enhanced Conversions, TikTok Pixel + Events API). These feed the bidding algorithms. They will over-report because every platform claims credit.
- Tag delivery layer — Google Tag Manager (web container) and ideally server-side GTM (sGTM) as a single first-party endpoint that fans out to all platforms. This is where consent, hashing, and deduplication are enforced once.
Decision order for any new conversion: define the event → fire client-side (pixel) → mirror
server-side (CAPI/Events API/server-side GTM) with a shared event_id → verify dedup → confirm in
GA4 + platform Events Manager.
2. GA4 events & conversions
GA4 is event-based — everything is an event with parameters. Structure:
- Automatically collected:
page_view,session_start,first_visit,scroll,click(outbound),file_download,video_*(Enhanced Measurement — turn on in the data stream). - Recommended events — use Google's reserved names so GA4/Ads can interpret them:
view_item,add_to_cart,begin_checkout,add_payment_info,purchase,generate_lead,sign_up,login,search. Don't invent names where a recommended one exists. purchaserequirescurrency+value+transaction_id(dedupe key) +items[].- Custom events — only for genuinely custom actions; register custom dimensions/metrics for any parameter you want to report on (GA4 ignores unregistered params in reports).
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 · 259 lines · 195 tokens per session scan A 1a3bfb2e655b
ad-measurement-tracking is a skill published in the GitHub repository squadcodercom/squadcoder (12 stars, last pushed 3mo ago), licensed MIT. It adds 195 tokens to every session and 3,845 once invoked, about $0.0008 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
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
semantic-compression
Re-encode verbose prose into a dense telegraphic register — punctuation as connectives, label frames, verbless assertions — without losing normativity or precision. Use when compressing system prompts, tool/function descriptions, skill bodies, or agent instructions; reducing token count or context bloat; making…
write-zot-themes
Help the user create, install, or package zot themes, including theme-only extensions.
writing-git-commits
Write clear, focused Git commit messages and keep commits easy to review.
hatch3r-board-groom
Ongoing backlog refinement for existing board items. Re-prioritize, reclassify, re-scope, archive stale items, decompose oversized issues, merge duplicates, refresh dependencies, and remediate board health findings.
hatch3r-cli-toolbox
Category-indexed reference for 34 specialist CLI tools beyond the always-on five (ripgrep, jq, gh, fd, fzf). Use to pick the right tool for HTTP clients, ai-chat, structural-search, sed-style edits, data ops, browser automation, container ops, and more.