Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chanktb/claude-google-ads/plugin install claude-google-adsWrote 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/chanktb/claude-google-ads/measurement)<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/measurement"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/measurement/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/chanktb/claude-google-ads/measurement"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/measurement.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 | $0.00131 | $0.01625 |
| Opus 5 | $0.00066 | $0.00813 |
| Sonnet 5 | $0.00026 | $0.00325 |
| Haiku 4.5 | $0.00013 | $0.00162 |
Grade A, and why
google-ads-measurement 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 10d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads — Measurement (tracking gate)
Prove conversion tracking is correct and trustworthy, or block plan/builder-* until it is. Reuse the
live MCP detection from setup. Never raise an alarm from the action list alone.
STEP 0 — Load context
If account-context.yaml is missing, run setup first — don't validate tracking on an unconfigured account.
Read account-context.yaml: google_ads.customer_id, conversion_actions, measurement.*,
data_source (for value sanity), business.model/vertical (lead vs purchase expectations). Output goes
to the working directory; update the context's conversion_actions + measurement.* as you verify them.
Model dispatch (run cheap, decide expensive) — see ${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md
- Scout (
haiku) — STEP 0 context read; the conversion-action list pull. - Routine (
sonnet) — STEP 1 per-campaign conversion segmentation (segments.conversion_action_name), STEP 3 Ads/GA4/store value pulls. Dispatch asgeneral-purposesub-agents; return raw, don't conclude. - Judge (main session) — the WHOLE-picture verdict, every is-it-a-problem call, the double-count judgment, the PASS/WARN/FAIL that gates plan/builder. Never let a cheap tier raise the alarm — that holistic judgment is the entire point of this skill.
STEP 1 — Build the WHOLE picture before concluding (mandatory)
A conversion list read in isolation lies. The same flag is fine or fatal depending on context. Do all four:
- Actions — enabled conversion actions: name, category, primary_for_goal, counting_type,
value_settings.default_value (value tracking on/off), source. (Omit
conversion_action.typeif the MCP rejects it; see ${CLAUDE_PLUGIN_ROOT}/skills/audit/references/gaql-notes.md.) Decode the enums:category4=PURCHASE · 6=LEAD · 5=SIGNUP · 3=PAGE_VIEW · 8=ADD_TO_CART · 9=BEGIN_CHECKOUT · 11=PHONE_CALL_LEAD · 13=SUBMIT_LEAD_FORM · 16=GET_DIRECTIONS · 18=CONTACT · 19=ENGAGEMENT · 20=STORE_VISIT;counting_type2=ONE (one per click) · 3=EVERY (many per click). For ecommerce, the working primary should be category=PURCHASE with EVERY counting + value tracking on. - Usage — which actions each ACTIVE campaign actually fires/optimizes for: segment conversions by
segments.conversion_action_nameper campaign over 30-90 days (explicitYYYY-MM-DDdates). An action no campaign fires is inert. - Source & double-count — map each value-carrying action to a source
(store channel, e.g. Shopify Google&YouTube "App Purchase" / WooCommerce / GA4 import / gtag /
Merchant Center). Two value
purchases both PRIMARY and both firing = double count. One primary + one secondary = correct.
See
${CLAUDE_PLUGIN_ROOT}/references/conversion-tracking-logic.md. - Verdict — only now, per the rules below.
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.
- 10d ago First seen · 93 lines · 131 tokens per session scan A e44250008e31
google-ads-measurement is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 2mo ago), licensed MIT. It adds 131 tokens to every session and 1,625 once invoked, about $0.0007 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
google-ads
A Google Ads guide for campaigns and advertising copy aimed at the Russian market in 2026. Google Ads is Google's paid advertising platform, and the guide covers formats such as search, video, app, shopping, and display ads.
markifact-overview
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
safe-write-operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
google-ads-ecommerce
Build and optimize Google Ads campaigns for ecommerce with Performance Max, Shopping feeds, conversion tracking, and Smart Bidding strategies for ROAS.
setup-conversion-tracking
Set up Converly conversion tracking end to end. Use when the user wants to track form submissions as conversions, send leads to an ad platform like Google Ads, Meta or Google Analytics, or set up Converly for the first time.
diagnose-missing-conversions
Find out why Converly conversions aren't showing up. Use when the user says tracking isn't working, conversions are missing, a form submission didn't appear, or an ad platform isn't receiving conversions.