agentmods.dev

google-ads-cli-toolkit CLAUDE.md

google-ads-cli-toolkit CLAUDE.md is an instructions file for Claude Code from nicolasmaldonadoj/google-ads-cli-toolkit. It costs 1,909 tokens per session, scanned A, original, MIT.

A Spanish-language instruction guide for an agent working with Google Ads, Google's online advertising platform, and optionally Google Tag Manager and Google Analytics 4. It explains the expected role, setup questions, and audit workflow.

In plain words
What is it for?
Guiding Google Ads setup, checking whether access credentials are ready, and starting an account audit in Spanish.
Why use it?
It gives nontechnical business owners clear guidance when they do not know Python, Google's API, or the required account credentials.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

not rated 20 4mo ago A scan 1,909 tokens original MIT
View the source file nicolasmaldonadoj/google-ads-cli-toolkit
Install

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.

agentmods
npx agentmods add instructions/nicolasmaldonadoj/google-ads-cli-toolkit/claude-md
Clone the repo
git clone --depth 1 https://github.com/nicolasmaldonadoj/google-ads-cli-toolkit

Made for: Claude Code.

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-cli-toolkit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/nicolasmaldonadoj/google-ads-cli-toolkit/claude-md.svg)](https://agentmods.dev/instructions/nicolasmaldonadoj/google-ads-cli-toolkit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/nicolasmaldonadoj/google-ads-cli-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/nicolasmaldonadoj/google-ads-cli-toolkit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,909 This file is loaded in full into every session.
When invoked 1,909 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01909 $0.01909
Opus 5 $0.00955 $0.00955
Sonnet 5 $0.00382 $0.00382
Haiku 4.5 $0.00191 $0.00191

Measured 6d ago against content hash 44e93a5a1485, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

google-ads-cli-toolkit CLAUDE.md 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 6d 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.

CLAUDE.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Playbook del agente

Este archivo es para ti, Claude Code (u otro agente IA). El humano que abrió este repo no necesariamente sabe Python ni la API de Google Ads. Tu trabajo es guiarlo.

Tu rol

Cuando alguien abre este repo contigo, asume que la persona quiere tomar control programático de su Google Ads (y opcionalmente GTM/GA4). Su contexto típico:

  • Es dueño/operador de un negocio que pauta en Google Ads.
  • Posiblemente trabajó (o trabaja) con una agencia o freelancer y perdió confianza, o quiere visibilidad real sobre su cuenta.
  • No sabe Python. No conoce la API. Sabe seguir instrucciones claras en español.

Habla siempre en español. Sé claro, paciente y específico. No hagas suposiciones técnicas — pregunta.

Primer mensaje al usuario

Cuando te activan en este repo, saluda en español, confirma su objetivo y pregunta en qué punto del setup está. Algo como:

Hola. Este repo te ayuda a tomar control de tu Google Ads desde la terminal. Para empezar necesito saber dónde estás:

  1. ¿Ya tienes una cuenta MCC ("Manager") en Google Ads?
  2. ¿Ya tienes un Developer Token aprobado?
  3. ¿Ya creaste un OAuth client en Google Cloud?
  4. ¿Ya generaste un refresh token?
  5. ¿Ya llenaste el archivo .env?

Empezamos desde el primer "no". Si nunca has hecho nada de esto, dímelo y arrancamos por el paso 1.

Empieza desde el primer "no". No saltes pasos sin confirmación.

Setup paso a paso

Cuando el usuario diga "no" en uno de los pasos, abre docs/SETUP.md y reproduce textualmente las instrucciones del paso correspondiente. Espera confirmación del usuario antes de avanzar al siguiente. Nunca asumas que el paso terminó hasta que el usuario lo confirme o un script lo verifique.

Cuando el usuario llegue al paso 6 (validación), corre python scripts/02_audit.py y resume los hallazgos en lenguaje no-técnico.

Después del setup: auditoría

Una vez .env está completo, corre la auditoría:

python scripts/02_audit.py

Read the full file on GitHub · 183 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. 6d ago First seen · 183 lines · 1,909 tokens per session scan A 44e93a5a1485

Subscribe to this mod's changes

google-ads-cli-toolkit CLAUDE.md is an instructions file published in the GitHub repository nicolasmaldonadoj/google-ads-cli-toolkit (20 stars, last pushed 4mo ago), licensed MIT. It adds 1,909 tokens to every session, about $0.0095 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.

Analytics and metricsMarketing and SEOai-agentclaude-codecliga4google-adsgoogle-ads-api
Related

Other instructions, from other repositories

Google-Ads-MCP CLAUDE.md

Claude Code instructions for WEYERSK/Google-Ads-MCP, covering claude.md, what this is, commands, architecture and the write-safety contract (safety.py).

WEYERSK/Google-Ads-MCP · 1,461 tokens

google-ads-mcp CLAUDE.md

Instructions for itallstartedwithaidea/google-ads-mcp, covering google ads mcp — googleadsagent.ai, quick orientation, commands, install and run mcp server (stdio — claude desktop/cursor).

itallstartedwithaidea/google-ads-mcp · 1,591 tokens

google-ads-mcp-plus CLAUDE.md

Claude Code instructions for monsieurgoodmood/google-ads-mcp-plus, covering claude.md — operating guide for this google ads mcp, 1. the one thing that matters most, 2. start every session with serverstatus, 3. tools and read — always available.

monsieurgoodmood/google-ads-mcp-plus · 3,204 tokens

mureo AGENTS.md

AGENTS.md instructions for logly/mureo, covering agents.md, project overview, build & test, runner — no package.json, no dependencies, no build step and architecture.

logly/mureo · 10,185 tokens

marketing-skills AGENTS.md

Instructions for hyperfx-ai/marketing-skills, covering agents.md, what this repo is, available skills, foundation and paid ads.

hyperfx-ai/marketing-skills · 2,695 tokens

ads-mcp CLAUDE.md

Instructions for amekala/ads-mcp, covering adspirer — performance marketing plugin, getting started, available commands and safety.

amekala/ads-mcp · 238 tokens