agentmods.dev

google-ads-builder-pmax

google-ads-builder-pmax is a skill for Claude Code from chanktb/claude-google-ads. It costs 124 tokens per session (3,307 once invoked), scanned A, original, MIT.

A builder for Performance Max, a Google Ads campaign type that can place ads across several Google channels from one campaign. It creates a detailed campaign blueprint from a store’s account information and plan.

In plain words
What is it for?
Use it to design asset groups, product listings, ad copy, search themes, audiences, sitelinks, negative keywords, media briefs, budgets, bids, and landing pages.
Why use it?
It organizes the many decisions involved in launching the campaign and checks URLs, products, ad limits, conversion goals, and spending rules.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-google-ads plugin — 15 skills, 15 commands shipped together

not rated 11repo 2mo ago A scan 124 tokens original MIT

Good fit Use it to design asset groups, product listings, ad copy, search themes, audiences, sitelinks, negative keywords, media briefs, budgets, bids, and landing pages.

Compare 6 skills from other repositories ↓
View source ↗ chanktb/claude-google-ads khuetran.com
Install

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.

Claude Code
/plugin marketplace add chanktb/claude-google-ads
Claude Code
/plugin install claude-google-ads

Made for: Claude Code.

Or install claude-google-ads, the plugin that ships this one along with the rest of its 15 skills, 15 commands.

Wrote 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.

agentmods badge for google-ads-builder-pmax

README.md
[![agentmods](https://agentmods.dev/badge/skills/chanktb/claude-google-ads/builder-pmax/github.svg)](https://agentmods.dev/skills/chanktb/claude-google-ads/builder-pmax)
Your own site
<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/builder-pmax"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/builder-pmax/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.

agentmods 80×15 button for google-ads-builder-pmax

Your own site · 80×15
<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/builder-pmax"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/builder-pmax.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,307 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00124 $0.03307
Opus 5 $0.00062 $0.01654
Sonnet 5 $0.00025 $0.00661
Haiku 4.5 $0.00012 $0.00331

Measured 9d ago against content hash b148e812eed6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

google-ads-builder-pmax 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/spec_to_xlsx.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/builder-pmax/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design a launch-ready PMax campaign from context + plan + catalog. Output is intern-ready. The highest- leverage decision is the split strategy (STEP 4) — get that right before designing assets.

Operating rules

  • Read everything from account-context.yaml (brand_terms, margin_tiers, guardrails, data_source, AOV, budget) and the plan output. No brand/vertical hardcoding.
  • Write all output to the working directory, never into the plugin.
  • Verify every Final URL is live before it enters the blueprint (campaigns fail on 404 / too-broad URLs).
  • Enforce guardrails (brand exclusion not brand negatives; conversion goals at campaign level; don't reference paused/out-of-stock products).

Model dispatch (run cheap, decide expensive) — see ${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md

  • Scout (haiku) — per-URL HEAD 200 checks (STEP 5); the spec_to_xlsx.py render; Google-accurate char-count validation passes.
  • Routine (sonnet) — STEP 2 catalog research (product types, counts, prices, best-sellers, URL map), STEP 3 expansion performance pull. Dispatch as general-purpose sub-agents; return raw catalog/URL data, don't design.
  • Judge (main session) — STEP 4 the split choice (the soul), STEP 5 asset-group + listing-group design, STEP 6 ad copy + search themes, STEP 7 audience signals, the guardrail enforcement. Catalog pulls and char-counts are mechanical; voice and strategy are not.

STEP 1 — Inputs

From the user + plan: which products/lines, the campaign's daily budget, and target ROAS phase. If the user is vague ("build pmax for X"), infer the rest from context and the catalog.

STEP 2 — Research catalog & website

Via the data_source connector/API (Shopify/Woo/...), pull product types, counts, price distribution, and best sellers. Verify collection/landing URLs are live (no 404, correct content) and record a URL map. Capture the website's product-type taxonomy (it may differ from the feed product_type — check both). If the connector is down, use the fallback chain (env creds / hub / browse) per setup; flag and continue.

Read the full file on GitHub · 171 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 171 lines · 124 tokens per session scan A b148e812eed6

Subscribe to this mod's changes

google-ads-builder-pmax is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 2mo ago), licensed MIT. It adds 124 tokens to every session and 3,307 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.

Claude CodeE-commerceMarketing and SEOclaude-skillsconversion-trackinggoogle-adspaid-search
Related

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.

finsilabs/awesome-ecommerce-skills · 32 tokens

paid-ads-amazon

Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS, or Amazon Ads performance exports.

nowork-studio/notfair-plugin · 55 tokens

beat-sync-reel

Generates Instagram Reels where product image cuts are synced to audio beats. Accepts audio as a local file, URL, or search query. Uses librosa for beat detection, FFmpeg Ken Burns for scene animation, and Pillow for text overlays. No AI video generation — fully free, fast, and scalable.

gooseworks-ai/goose-skills · 68 tokens

ebay-search

Search eBay listings - find items, auctions, deals, and compare prices.

gooseworks-ai/goose-skills · 19 tokens

einbeziehung-online-clickwrap-browsewrap

Für Einbeziehung Online Clickwrap Browsewrap: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

Klotzkette/claude-fuer-deutsches-recht · 42 tokens

kurzfristige-preiserhoehung-lieferfrist

Für Kurzfristige Preiserhöhung 309: prüft Frist, Form, Zuständigkeit und Eilbedarf; Ergebnis: Fristen- und Risikoampel. Fachgebiet: AGB-Recht-Prüfer. Route: kurzfristige-preiserhoehung-lieferfrist.

Klotzkette/claude-fuer-deutsches-recht · 72 tokens