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/builder-branded-search)<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/builder-branded-search"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/builder-branded-search/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/builder-branded-search"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/builder-branded-search.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 | $0.00108 | $0.01817 |
| Opus 5 | $0.00054 | $0.00908 |
| Sonnet 5 | $0.00022 | $0.00363 |
| Haiku 4.5 | $0.00011 | $0.00182 |
Grade A, and why
google-ads-builder-branded-search 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads — Builder: Branded Search
A focused Search campaign to (1) defend your own brand at near-certain ROAS and (2) optionally conquest
competitors. Pushes cleanly via Editor CSV. Builds on builder-search patterns with brand-specific rules.
Operating rules
- Read
brand_termsandcompetitor_termsfromaccount-context.yaml(set bysetup). Read guardrails. - Write to the working directory:
blueprint.xlsx+campaign-spec.json(campaign_type: "branded_search",ad_groups[]). - Coordinate brand exclusion: ensure PMax/Shopping have brand exclusion applied so they don't claim
brand conversions (clean attribution). Honor the
pmax-brand-exclusionguardrail.
Model dispatch (run cheap, decide expensive) — see ${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md
- Scout (
haiku) — per-URL 200 checks; char-count validation; brand-misspelling expansion. - Routine (
sonnet) — pulling competitor domains from auction insights as conquesting candidates. Dispatch asgeneral-purpose; return raw candidates, don't decide. - Judge (main session) — STEP 1-2 ad-copy (brand-led, trademark-aware — never a competitor TM in ad text), STEP 3 separation, bidding, the brand-exclusion coordination call. Trademark safety is judgment; never delegate it.
STEP 1 — Brand-defense ad group(s)
- Keywords from
brand_terms(own brand + variants + common misspellings), Exact + Phrase. No broad. - Copy uses your own brand prominently, your USPs, and your real offers. Target high impression share at low CPC (brand intent converts cheaply).
- RSA: up to 15 headlines (≤30) / 4 descriptions (≤90), keyword-led, with CTA.
STEP 2 — Competitor conquesting — optional, trademark-aware, a SEPARATE campaign
- Only if
competitor_termsexist and the user wants it. Emit it as its OWN campaign-spec, not an ad group inside the brand-defense campaign — because bid strategy is campaign-level and conquesting needs Maximize Conversions, not the defense campaign's Target Impression Share. (You do NOT want to bid to dominate a competitor's SERP at absolute-top 90% — expensive, low-intent.) - Keywords from
competitor_terms(Phrase/Exact). - Trademark rules: do NOT put a competitor's trademark in the ad TEXT (headlines/descriptions/paths) —
only as keywords. Emit the competitor terms as a spec-level
trademark_avoid[]so the validator BLOCKS any in ad text. Lead with YOUR differentiators ("wholesale pricing", "free shipping", a price extension with your real prices on the competitor SERP), not the competitor's name. Expect lower CTR/QS, higher CPC. - Add YOUR
brand_termsas negatives so conquesting never overlaps the brand-defense campaign.
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.
- 12d ago First seen · 100 lines · 108 tokens per session scan A be9c2e12cd76
google-ads-builder-branded-search is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 1,817 once invoked, about $0.0005 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.