google-ads

google-ads is a skill for Claude Code from chanktb/claude-google-ads. It costs 125 tokens per session (1,600 once invoked), scanned A, original, MIT.

A routing skill for a suite of Google Ads tools. It determines which step of the campaign lifecycle is needed and checks the required account context and connections before handing work to another tool.

In plain words
What is it for?
Use it when you need general help with Google Ads, such as setting up an account, launching campaigns, monitoring them, or choosing the appropriate specialized operation.
Why use it?
It prevents campaign work from starting with missing setup, incomplete data, or an inappropriate next step.

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

Good fit Use it when you need general help with Google Ads, such as setting up an account, launching campaigns, monitoring them, or choosing the appropriate specialized operation.

Compare 6 skills from other repositories ↓
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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/google-ads"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/google-ads.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,600 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 $0.00125 $0.01600
Opus 5 $0.00063 $0.00800
Sonnet 5 $0.00025 $0.00320
Haiku 4.5 $0.00013 $0.00160

Measured 10d ago against content hash e1bfe71093e0, 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 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.

skills/google-ads/SKILL.md · 100 lines

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.

The single entry point. Find out where the user is in the campaign lifecycle and hand off to the right sub-skill. Enforce the order so nothing runs on a broken foundation.

STEP 0 — Locate context

Look for account-context.yaml in the working directory (or a --context <path> the user gives).

  • Missing → run claude-google-ads:setup first. Nothing else runs without context.
  • Present → continue.

STEP 0b — Connection precheck (REQUIRED — don't run skills on a half-connected account)

Read the context connections block (or detect live). Before routing, confirm the prerequisites are set up; the suite's value depends on real data, and it must never run on a gap silently (see the no-fabricate gate):

Connection Tier If missing
Google Ads (read-only GAQL MCP) MANDATORY STOP. Nothing runs. Send the user to setup to connect a Google Ads MCP.
Store (Shopify/Woo/BigCommerce) required for full value Guide to connect (MCP or an Admin token in a .env). Without it: no real AOV / true-ROAS — those outputs render UNVERIFIED — connect store.
Merchant Center (ecom) required for feed health Guide to connect. Without it: product performance only, feed health (OOS/disapproval, D14-B) = UNVERIFIED.
GA4 recommended Guide to connect. Without it: no Ads-vs-GA4 value cross-check.
GSC optional Note only.

If Google Ads is missing → stop and run setup. If a value-tier source (store/Merchant/GA4) is missing → surface a one-line "connect these for full value" banner with the how-to, then proceed at reduced scope — every output that needed the missing source is flagged UNVERIFIED, never fabricated. Don't quietly skip.

STEP 1 — Assess lifecycle stage

Run the context validator to read readiness, and scan the working dir for prior artifacts:

python ${CLAUDE_PLUGIN_ROOT}/skills/setup/scripts/validate_context.py ./account-context.yaml

Map state → the next sensible step:

Readiness Artifacts present Likely next step
not setup-complete setup (finish context)
setup-complete, no audit audit and/or measurement
measurement = FAIL measurement report back to tracking fixes (block plan/build)
measurement OK, no plan audit + measurement plan
plan exists, no spec GOOGLE-ADS-PLAN.md builder-* for the chosen types
spec exists, not pushed campaign-spec.json pusher
campaign live tracker (new) / optimizer (mature)

Read the full file on GitHub · 100 lines

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. 10d ago First seen · 100 lines · 125 tokens per session scan A e1bfe71093e0

Subscribe to this mod's changes

google-ads is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 2mo ago), licensed MIT. It adds 125 tokens to every session and 1,600 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.

Related

Other skills, from other repositories