What is google-ads-apply?

A controlled way to apply approved changes to Google Ads accounts. It supports adding negative keywords, pausing keywords or ad groups, and changing campaign daily budgets through a review-and-confirm process.

Use it after an advertising draft has been reviewed and approved. It provides a dry run, confirmation step, account verification, and records of applied changes and reversals.

It limits account changes to defined actions and keeps a path for checking and reversing them, reducing the risk of applying an unreviewed change.

google-ads-apply — Skill for Claude Code by TheMattBerman

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.

Any agent

npx skills add TheMattBerman/google-ads-copilot --skill google-ads-apply

Clone the repo

git clone --depth 1 https://github.com/TheMattBerman/google-ads-copilot

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/themattberman/google-ads-copilot/google-ads-apply.svg)](https://agentmods.dev/skills/themattberman/google-ads-copilot/google-ads-apply)

Your own site

<a href="https://agentmods.dev/skills/themattberman/google-ads-copilot/google-ads-apply"><img src="https://agentmods.dev/badge/skills/themattberman/google-ads-copilot/google-ads-apply.svg" alt="Measured on agentmods" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,665 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.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.02665
Opus 5	$0.00041	$0.01333
Sonnet 5	$0.00016	$0.00533
Haiku 4.5	$0.00008	$0.00266

Measured 7d ago against content hash 85a7f347291d, 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-apply 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 7d 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-apply/SKILL.md · 276 lines

How it starts

The opening of the file, as written. The whole thing — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Google Ads Apply

Status: LIVE — Write Access Confirmed

API v20 confirmed working (2026-03-15). v18 is sunset (404), v19 unstable (500). Full write cycle proven: add campaign negative → GAQL verify → remove → verify removal. Keyword pauses and ad group pauses fully scaffolded and hardened. CLI scripts at scripts/apply-layer/. Smoke test: scripts/apply-layer/gads-smoke-test.sh <customer_id> See APPLY-LAYER.md for design details and scripts/apply-layer/README.md for the public CLI implementation guide. See OPERATOR-PLAYBOOK.md for the full operator workflow loop.

Read first:

OPERATOR-PLAYBOOK.md — full operator workflow (connect → select → review → apply → verify → undo)
APPLY-LAYER.md — design document, API specs, error handling
drafts/DRAFTS.md — draft system documentation

Read workspace:

workspace/ads/drafts/_index.md — current queue
workspace/ads/drafts/_summary.md — prioritized summary
workspace/ads/audit-trail/_log.md — previous apply sessions (if any)
workspace/ads/audit-trail/reversal-registry.json — active reversals

Commands

Apply a Draft

/google-ads apply [draft-file]

Flow:

Read the draft file
Parse all proposed actions (manifest-first for budget drafts; legacy parsing for v1 negatives/pauses)
Validate each action (correct account, valid targets, within live apply scope)
Resolve human-readable names to Google Ads resource IDs via GAQL
Display dry run with every mutation listed, action type summary, and risk assessment
Wait for operator confirmation ("confirm" or "cancel")
Execute each action via Google Ads REST API v20
Verify changes via GAQL re-query
Write audit trail (session log, master log, reversal registry)
Update draft status to "applied"
Show post-apply summary with undo instructions

Review a Draft (No Apply)

/google-ads apply review [draft-file]
/google-ads apply review --all

Flow:

Parse the draft into structured actions
Show action breakdown with counts by type and risk levels
Show confidence and dependencies
Provide a proceed/defer recommendation
Show next-step commands (dry-run or full apply)

Read the full file on GitHub · 276 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.

7d ago First seen · 276 lines · 81 tokens per session scan A 85a7f347291d

Subscribe to this mod's changes

google-ads-apply is a skill published in the GitHub repository TheMattBerman/google-ads-copilot (231 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 2,665 once invoked, about $0.0004 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.

Marketing and SEO

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens