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 agentmods add skills/themattberman/google-ads-copilot/google-adsnpx skills add TheMattBerman/google-ads-copilot --skill google-adsgit 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)<a href="https://agentmods.dev/skills/themattberman/google-ads-copilot/google-ads"><img src="https://agentmods.dev/badge/skills/themattberman/google-ads-copilot/google-ads.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00070 | $0.03757 |
| Opus 5 | $0.00035 | $0.01878 |
| Sonnet 5 | $0.00014 | $0.00751 |
| Haiku 4.5 | $0.00007 | $0.00376 |
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 5d 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads Copilot
Google Ads is a language game disguised as a dashboard.
Most accounts do not fail because the buttons are wrong. They fail because the account is mixing different kinds of intent together, buying junk curiosity, and hiding signal inside bad structure.
This system exists to fix that.
The job
- Interrogate the account
- Build an Intent Map
- Cut waste
- Isolate signal
- Turn learning into structure, copy, and budget decisions
- Preserve memory so the system compounds
- Stage proposed actions as reviewable drafts
Architecture: Read → Draft → Apply
READ LAYER → DRAFT LAYER → APPLY LAYER (future)
Live data via MCP Proposed actions Controlled write-back
or manual exports in staging docs after human approval
↕ ↕ ↕
WORKSPACE MEMORY (workspace/ads/)
- Read: Pull live data via
google-ads-mcpMCP server (connected mode) or accept manual CSV/paste/screenshots (export mode). - Draft: When analysis produces actionable findings, write concrete proposed actions to
workspace/ads/drafts/for human review. - Apply: Future — execute approved drafts via Google Ads API writes.
Commands
| Command | Purpose |
|---|---|
/google-ads connect |
First-time setup, health check, account selection (connected mode) |
/google-ads daily |
Fast operator summary of what matters today |
/google-ads search-terms |
Find waste, signal, messaging clues, and routing problems |
/google-ads intent-map |
Build/update the account's intent model |
/google-ads negatives |
Recommend negatives with scope + risk notes |
/google-ads tracking |
Diagnose whether the account is trustworthy enough to optimize |
/google-ads structure |
Recommend campaign/ad group structure changes |
/google-ads rsas |
Generate/refine RSA directions from real query language |
/google-ads budget |
Budget/scaling decisions based on signal quality |
/google-ads plan |
Plan or rebuild account architecture |
/google-ads audit |
Full operator review across all major layers |
/google-ads landing-review |
Diagnose landing page → conversion path (tracking vs UX) |
/google-ads draft-summary |
Prioritized summary of all pending drafts |
/google-ads apply |
Execute approved drafts (v1: negatives + pauses only) |
What ships with it
11 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.
- references/benchmarks.md 765 B
- references/budget-playbook.md 950 B
- references/deliverable-templates.md 1.7 KB
- references/intent-map.md 796 B
- references/landing-page-playbook.md 7.6 KB
- references/negatives-playbook.md 3.0 KB
- references/operator-thesis.md 996 B
- references/query-patterns.md 596 B
- references/rsa-playbook.md 890 B
- references/structure-playbook.md 1.2 KB
- references/tracking-playbook.md 6.2 KB
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.
- 5d ago First seen · 321 lines · 70 tokens per session scan A 900aa156e0a4
google-ads is a skill published in the GitHub repository TheMattBerman/google-ads-copilot (231 stars, last pushed 2mo ago), licensed MIT. It adds 70 tokens to every session and 3,757 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…
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…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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.
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…