An assistant that manages Google Ads and Meta advertising accounts through their official APIs. APIs are controlled interfaces that let software read or change data in another service.

Use it to inspect ad accounts, create or adjust campaigns, and manage Google Ads or Meta campaigns after connecting the relevant accounts.

It provides one conversational interface for auditing, creating, and optimizing campaigns across both advertising platforms.

adwhiz — Skill for Claude Code and Codex by zrtch

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 zrtch/awesome-skills --skill adwhiz

Clone the repo

git clone --depth 1 https://github.com/zrtch/awesome-skills

Made for: Claude Code, Codex.

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/zrtch/awesome-skills/adwhiz/github.svg)](https://agentmods.dev/skills/zrtch/awesome-skills/adwhiz)

Your own site

<a href="https://agentmods.dev/skills/zrtch/awesome-skills/adwhiz"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/adwhiz/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/zrtch/awesome-skills/adwhiz"><img src="https://agentmods.dev/badge/skills/zrtch/awesome-skills/adwhiz.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,043 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 94% copy Near-identical to another mod 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	$0.00036	$0.03043
Opus 5	$0.00018	$0.01522
Sonnet 5	$0.00007	$0.00609
Haiku 4.5	$0.00004	$0.00304

Measured 10d ago against content hash 8bd058c0ff04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

adwhiz scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://mcp.adwhiz.ai/api/v1/tools/list_campaigns \

Origin

This is a copy

94% identical to advertising-intelligence-tool — 40 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/adwhiz/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AdWhiz — Google Ads & Meta Ads MCP Server

AdWhiz is a hosted MCP server that connects your AI coding tool to the Google Ads API and Meta (Facebook) Graph API through a secure, authenticated proxy. It exposes 99 tools across 7 categories so you can audit, create, and manage ad campaigns across both platforms using plain English.

All API calls are authenticated via your personal ADWHIZ_API_KEY and routed through the AdWhiz server at mcp.adwhiz.ai. No Google or Meta credentials are stored by the skill — authentication is handled entirely server-side after you link your ad accounts at https://adwhiz.ai/connect.

Security & Permissions Model

OAuth 2.0: User authenticates with Google and/or Meta via AdWhiz's web UI. Refresh tokens (Google) and long-lived access tokens (Meta) are encrypted at rest (AES-256-GCM) and never exposed to the agent.
API key scoping: Each ADWHIZ_API_KEY is bound to a single user's connected accounts. Cross-user access is not possible.
Write safety: All Google Ads write tools create entities in PAUSED status by default. Meta write tools require explicit status parameters.
Mutation logging: Every mutation is recorded in the get_operation_log tool for full auditability.
Read-only by default: 36 of 99 tools are strictly read-only and cannot modify your accounts.
Confirmation required: Write tools require user confirmation before executing via the agent's standard permission flow.
No arbitrary code execution: The MCP server is a hosted HTTP service. No code is downloaded or executed on the user's machine beyond the thin MCP client wrapper.

Google Ads Tools (70)

Account (2 tools) — Read-only

Tool	Description
`list_accounts`	List all accessible Google Ads accounts (auto-expands MCC child accounts)
`get_account_info`	Get account details (currency, timezone, optimization score)

Read (20 tools) — Read-only

Tool	Description
`list_campaigns`	List campaigns with status, type, budget, bidding strategy
`get_campaign_performance`	Campaign metrics: cost, clicks, conversions, CTR, CPA, ROAS
`list_ad_groups`	List ad groups with bids, filtered by campaign
`list_ads`	List ads with headlines, descriptions, final URLs
`list_keywords`	Keywords with match types, bids, quality scores
`get_search_terms`	Search terms report (actual queries triggering ads)
`list_negative_keywords`	Negative keywords at campaign, ad group, or account level
`list_assets`	Sitelinks, callouts, structured snippets
`list_conversion_actions`	Conversion actions with status, type, category
`list_budgets`	Campaign budgets with associated campaigns
`list_bidding_strategies`	Portfolio bidding strategies
`list_audience_segments`	Audience targeting criteria
`list_user_lists`	Remarketing/audience lists for targeting
`get_operation_log`	Recent mutations performed via AdWhiz
`list_recommendations`	Google Ads recommendations (add keywords, raise bids, fix ad strength)
`get_change_history`	Change audit log: who changed what and when
`list_geo_targets`	Geographic location targeting on campaigns
`list_ad_schedules`	Ad schedule (dayparting) criteria on campaigns
`list_labels`	Labels for organizing campaigns, ad groups, ads, keywords
`generate_keyword_ideas`	Keyword ideas with search volume, competition, bid ranges

Read the full file on GitHub · 265 lines

Files

What ships with it

2 files 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.

10d ago First seen · 265 lines · 36 tokens per session scan A 8bd058c0ff04

Subscribe to this mod's changes

adwhiz is a skill published in the GitHub repository zrtch/awesome-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 3,043 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). It is 94% identical to advertising-intelligence-tool, differing in 40 lines, and is treated as a copy.

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

adwhiz