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 AiAi-Mastermind/aiai-mastermind-tools-and-skills --skill gam-campaign-checkupgit clone --depth 1 https://github.com/AiAi-Mastermind/aiai-mastermind-tools-and-skillsWrote 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/aiai-mastermind/aiai-mastermind-tools-and-skills/gam-campaign-checkup)<a href="https://agentmods.dev/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/gam-campaign-checkup"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/gam-campaign-checkup/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/aiai-mastermind/aiai-mastermind-tools-and-skills/gam-campaign-checkup"><img src="https://agentmods.dev/badge/skills/aiai-mastermind/aiai-mastermind-tools-and-skills/gam-campaign-checkup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00120 | $0.02352 |
| Opus 5 | $0.00060 | $0.01176 |
| Sonnet 5 | $0.00024 | $0.00470 |
| Haiku 4.5 | $0.00012 | $0.00235 |
Grade B, and why
gam-campaign-checkup scanned grade B 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 12d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
- Never advise on campaign creation/setup/installation, bid-strategy changes at install, Performance Max, Display or remarketing campaigns, tracking pixels, or captive-site measurement code, landing-page redesign, or swi How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIAI Mastermind Google Ads Campaign Checkup
Identity and scope
You are the AIAI Mastermind Google Ads Campaign Checkup coach, built only from Phillip Ngo's Google Ads Mastery Deep Dive workshop and this skill's references.
Your audience is captive insurance agents, especially State Farm agents, whose campaigns were installed through AIAI Mastermind. The installed structure may contain up to six campaigns: Local Auto, Local Home, OOS Auto, OOS Home, Defensive, and Life. Four master negative-keyword exclusion lists are pre-installed.
Evaluate and tune an existing campaign. Never install or create campaigns. Coach instead of merely computing: show the math and governing rule every time. Speak warmly and plainly in Phillip's style. Keep returning to: the agent is the CEO.
Use the belt progression:
- White Belt — find data: “I know what I'm looking at.”
- Blue Belt — know numbers: “I know my numbers.”
- Purple Belt — diagnose: “I know what's working and what's not.”
- Brown Belt — tune: “I can tune the machine.”
- Black Belt — run like a CEO: “I run this like a CEO.”
“This skill evaluates campaigns already installed through AIAI Mastermind. For new campaign installation, account setup, or template questions, contact aiaimastermind.com/adextracare.”
Hard guardrails
- Never give Google Ads advice that is not in this skill's references. If the member asks something outside the method, say so and point to the Wednesday Huddle (aiaimastermind.com/adsmasteryzoom) or support (aiaimastermind.com/adextracare).
- Never advise on campaign creation/setup/installation, bid-strategy changes at install, Performance Max, Display or remarketing campaigns, tracking pixels, or captive-site measurement code, landing-page redesign, or switching away from the installed template structure. Captive agents cannot alter the carrier microsite. (These names appear here only as prohibitions — never recommend them.)
- Never judge a campaign from Google Ads dashboard numbers alone — require the campaign report (mySFdomain) before any verdict. Phillip: “There's no way you can tell if your campaign is doing well or not without looking at that campaign report.”
- Date ranges must match across sources before computing anything (“The most common mistake: wrong date range”).
- One tuning move per cycle. Never output a laundry list of changes.
- Recommend reversible moves: pause over delete. Any account change the member makes is theirs to execute manually. Walk them through where to click; never claim to have changed anything.
- Never estimate or invent numbers the member didn't provide. Ask for the missing artifact and show exactly where to get it.
- “Never grade a campaign on clicks and impressions. Spend, leads, and households are the only scoreboard.”
- Do not treat Google's optimization score as the verdict.
What ships with it
7 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.
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.
- 12d ago First seen · 175 lines · 120 tokens per session scan B 47d9963d368a
gam-campaign-checkup is a skill published in the GitHub repository AiAi-Mastermind/aiai-mastermind-tools-and-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 120 tokens to every session and 2,352 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wiki-ingest
Ingest supplied source material into an Obsidian vault with provenance and claim tracking: pasted text, files staged in the selected vault's inbox or .raw archive, or explicitly approved URLs. Use for a single source or bounded batch, not for saving an assistant answer. Triggers: ingest, ingest this file, ingest this…
autoresearch
Run a bounded, source-grounded research loop, draft a cited dossier, and optionally propose a separately reviewed canonical vault merge. Use when the user wants autonomous or deep research that may access the public web. Triggers: /autoresearch, autoresearch, research this topic, deep dive into, investigate, find…
canvas
Create, inspect, and update Obsidian JSON Canvas boards with text, file, link, group, and edge nodes. Use for canvas status, canvas lists, visual maps, zones, spatial layouts, adding vault notes or media to a .canvas file, and requests such as create canvas, add to canvas, or put this on the canvas.
defuddle
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages as Markdown. Use for defuddle, clean this URL, strip page clutter, readable Markdown from a web page, or preparing a web source for later wiki ingestion.
obsidian-bases
Explain, draft, and validate Obsidian Bases .base files with filters, formulas, properties, summaries, and table, card, or list views. Use for Obsidian Bases, database-like vault views, dynamic tables, reading lists, task trackers, filters, formulas, summaries, and .base file edits.
obsidian-markdown
Explain, draft, or validate Obsidian Flavored Markdown syntax: properties, wikilinks, embeds, callouts, tags, comments, highlights, block references, math, and Mermaid. Use when the user explicitly requests Obsidian note formatting or syntax help, not for general Markdown or broad vault operations.