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 skills/chanktb/claude-google-ads/setupnpx skills add chanktb/claude-google-ads --skill setupgit clone --depth 1 https://github.com/chanktb/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/setup)<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/setup"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/setup.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 | $0.00116 | $0.03516 |
| Opus 5 | $0.00058 | $0.01758 |
| Sonnet 5 | $0.00023 | $0.00703 |
| Haiku 4.5 | $0.00012 | $0.00352 |
Grade A, and why
google-ads-setup 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 5d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads — Setup
You build account-context.yaml, the single source of business truth that every other skill in this
suite reads. Nothing downstream (audit, plan, builder, pusher, tracker, optimizer) runs without it.
Operating rules
- Establish ONE working folder per business and keep everything in it — see
${CLAUDE_PLUGIN_ROOT}/references/workspace-layout.md. On first run, agree the<workdir>path with the user, create it, and writeaccount-context.yamlthere. Every downstream output goes into its dated subfolder (audits/,plans/,builds/,changes/,raw/). NEVER scatter files into the plugin folder,D:\tmp,/tmp, or the cwd root — a user who installs the plugin must get ONE tidy folder, not sprinkled files. - Secrets are POINTERS, never copies. Do NOT write raw API tokens/keys into the working folder, any output,
or
account-context.yaml. Theconnectionsregistry records where each token lives (via: env:/path#KEY,via: server:/path,via: mcp:<id>) and it's read at runtime. If the user wants creds kept locally, a gitignoredsecrets/in the workdir — never committed, never in a report. - (legacy) Write
account-context.yamlto the working directory, NEVER inside the plugin folder. Business data lives with the user, not in the code. (Use--context <path>if the user names one.) - Detect by capability, not by hardcoded server ids. Inspect the connected MCP tools and match them to roles. The same skill must work for any user's MCP setup.
- Setup is the CONNECTION HUB. Its job is to inventory EVERY data source the suite needs and consolidate
how to reach each one into the context's
connectionsblock — ONE place every downstream skill reads, so no skill ever re-discovers a connector or silently runs without data. - NO-FABRICATE DATA GATE (non-negotiable, the whole point). Missing data is connected or flagged, NEVER
invented. If a source is missing: (a) guide the user to connect or provide it (concrete steps — link
the account, point to a
.env/secrets file, a data-hub script), and (b) if it stays missing, record it as MISSING inconnectionsso every downstream skill that needs it labels that part of its outputUNVERIFIED — connect <source>and EXCLUDES it from any number it reports. Skip-then-guess produces wrong analysis; an honest gap is correct. A blank field is honest; a fabricated AOV / store-revenue / feed status is dangerous. - Confirm before writing. Show the assembled context, get a yes, then write.
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.
- 5d ago First seen · 198 lines · 116 tokens per session scan A aa813b73c1ec
google-ads-setup is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 3,516 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 2026-08-30.
Other skills, from other repositories
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.
adspirer-ads-agent
Adspirer — AI-powered advertising and performance marketing agent. Manage Google Ads, Meta Ads (Facebook & Instagram), LinkedIn Ads, and TikTok Ads via natural language. 100+ tools for paid media campaign creation, live performance analysis, PPC keyword research with real CPC data, budget optimization, ad creative…
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
cold-email-outreach
Run end-to-end B2B cold-email outreach through the Hyper MCP — enrich prospects with Apollo, scrape per-prospect signals from company sites and LinkedIn, draft personalized emails using proven hook frameworks, send via Gmail with safe defaults, and route replies into labeled folders. Use when the user wants to write…