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 swan-gtm/gtm-skills --skill google-ads-ppc-mathgit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/google-ads-ppc-math)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/google-ads-ppc-math"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/google-ads-ppc-math/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/swan-gtm/gtm-skills/google-ads-ppc-math"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/google-ads-ppc-math.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 | $0.00105 | $0.00781 |
| Opus 5.5 | $0.00042 | $0.00312 |
| Sonnet 5.5 | $0.00021 | $0.00156 |
| Haiku 4.5 | $0.00011 | $0.00078 |
Grade A, and why
google-ads-ppc-math 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 1mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PPC Forecasting and Unit-Economics Math
Applies any time the question is really arithmetic wearing a strategy question's clothes — someone wants to know what a number implies before committing spend to it.
The play
- Work from whatever inputs are actually given, and state which core rates you derived them from: CPA (spend ÷ conversions), ROAS (revenue ÷ spend), CTR (clicks ÷ impressions), CPC (spend ÷ clicks), CVR (conversions ÷ clicks). Every downstream projection is built from these five.
- For a budget or conversion forecast, chain the rates forward explicitly: daily clicks from budget and CPC, daily conversions from clicks and CVR, then scale to a monthly figure using an average month length (roughly 30.4 days) rather than a flat 30 — the drift compounds over a full year of planning.
- For a target gap (hitting a CPA or ROAS goal), show the distance three ways: where the account is now, what's required to hit the target, and the specific delta in conversions or revenue needed to close it — not just "you're below target."
- For impression share opportunity, translate the missed share into missed clicks and missed conversions using the account's own CTR and conversion rate, not an assumed industry rate — the whole point is showing what the account's actual funnel would produce with more visibility.
- Always run the sensitivity check nobody asked for: "if CPC rises 20%, your CPA becomes X." A single-point forecast without a stress case invites false confidence the moment reality drifts from the input.
- Flag inputs that don't pass a sanity check before running them forward — a CTR above what's plausible for the format, or a CPA implausibly low for a non-branded term, will just launder into an equally implausible forecast if you don't stop and ask about it first.
What good looks like
- The best version of this always shows the formula and the inputs next to the result — a table with just a final number invites "how did you get that" and erodes trust the first time someone tries to reproduce it.
- The common mistake is running a forecast on inputs that were never sanity-checked, producing a precise-looking number built on an impossible assumption. Catch the impossible input, don't just compute through it.
- Good output pairs every headline number with its sensitivity — a forecast that can't say what happens if one input moves 20% isn't a forecast, it's a guess with extra decimal places.
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.
- 1mo ago First seen · 65 lines · 105 tokens per session scan A d56a57fe51cf
google-ads-ppc-math is a skill published in the GitHub repository swan-gtm/gtm-skills (221 stars, last pushed 8d ago), licensed MIT. It adds 105 tokens to every session and 781 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
ad-campaign-analyzer
Analyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating causality.
paid-ad-copy-writer
Write paid ad copy for affiliate offers across ad platforms. Triggers on: "write ad copy", "Facebook ad for affiliate", "Google Ads copy", "TikTok ad script", "Pinterest ad", "paid traffic to affiliate", "create ad campaign", "ad headlines", "ad descriptions", "scale with paid ads", "run ads for my affiliate link"…
gooseworks
GooseWorks growth coworker and router for markets, competitors, audiences, creators, campaigns, ads, photos, graphics, video, content, email, SEO, social, leads and contacts. Use for brand facts or copy too, so offers, prices, rules, audience and bestsellers reach the brand's Marketing Brain.
adcp-advertising
Automate advertising campaigns with AI. Create ads, buy media, manage ad budgets, discover ad inventory, run display ads, video ads, CTV campaigns, and optimize ad performance. Perfect for marketing automation, programmatic advertising, media buying, ad management, campaign optimization, creative management, and…
yandex-direct
Skill "yandex-direct" from VKirill/claude-lane-stack, covering version requirements, usage, use this skill when, do not use this skill when and purpose.
yandex-direct-creatives
An advertising-writing guide for Yandex.Direct, a Russian online advertising platform. It turns keyword clusters from Key Collector, a keyword research tool, into campaigns, ad groups, and ads.