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.
npx skills add TheMattBerman/google-ads-copilot --skill google-ads-connectgit clone --depth 1 https://github.com/TheMattBerman/google-ads-copilotWrote 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/themattberman/google-ads-copilot/google-ads-connect)<a href="https://agentmods.dev/skills/themattberman/google-ads-copilot/google-ads-connect"><img src="https://agentmods.dev/badge/skills/themattberman/google-ads-copilot/google-ads-connect/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/themattberman/google-ads-copilot/google-ads-connect"><img src="https://agentmods.dev/badge/skills/themattberman/google-ads-copilot/google-ads-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02095 |
| Opus 5 | $0.00034 | $0.01047 |
| Sonnet 5 | $0.00014 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
google-ads-connect 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 9d 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 — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads Connect
This skill handles the plumbing so the other skills can focus on strategy.
Read workspace if available:
workspace/ads/account.md
What This Skill Does
- Setup check — verifies the MCP server is configured and responsive
- Customer discovery — lists all accessible accounts with names and IDs
- Customer selection — helps the operator choose the right account
- Account fingerprint — pulls basic account metadata and writes to workspace
- Health check — validates that data is flowing and queries return results
Commands
/google-ads connect setup
Full onboarding flow: check MCP → discover accounts → select account → fingerprint. Use this the first time you connect.
/google-ads connect healthcheck
Quick validation: MCP alive? Account selected? Data flowing? Use this before an audit or when something feels broken.
/google-ads connect select [customer_id]
Switch to a different account. Updates workspace memory.
Step 1: Verify MCP Server
Test: Call list_accessible_customers via the google-ads-mcp MCP server.
If it succeeds:
✅ MCP server is live
Accessible accounts: N
If it fails, diagnose:
| Symptom | Likely Cause | Fix |
|---|---|---|
| MCP tool not found | Server not configured in MCP host | Add config — see data/mcp-config.md |
| "No credentials found" | GOOGLE_APPLICATION_CREDENTIALS missing or wrong path |
Check the env var points to a valid JSON file |
| "Developer token not approved" | Token missing or pending | Check GOOGLE_ADS_DEVELOPER_TOKEN env var |
| "Project not found" | Wrong project ID | Use GOOGLE_CLOUD_PROJECT (not GOOGLE_PROJECT_ID) |
| Connection timeout | pipx or network issue | Verify pipx is installed, internet is up |
| "Manager account required" | MCC access needed | Add GOOGLE_ADS_LOGIN_CUSTOMER_ID |
Environment Variable Reference (Canonical)
| Variable | Required | Purpose |
|---|---|---|
GOOGLE_APPLICATION_CREDENTIALS |
Yes | Path to OAuth/ADC credentials JSON |
GOOGLE_CLOUD_PROJECT |
Yes | Google Cloud project ID (⚠️ NOT GOOGLE_PROJECT_ID) |
GOOGLE_ADS_DEVELOPER_TOKEN |
Yes | Google Ads API developer token |
GOOGLE_ADS_LOGIN_CUSTOMER_ID |
If MCC | Manager account customer ID (no dashes) |
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.
- 9d ago First seen · 266 lines · 68 tokens per session scan A 4097641a78a9
google-ads-connect is a skill published in the GitHub repository TheMattBerman/google-ads-copilot (231 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 2,095 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…