google-ads-math

google-ads-math is a skill for Claude Code from itallstartedwithaidea/google-ads-skills. It costs 54 tokens per session (894 once invoked), scanned A, original, Apache-2.0.

A calculator and forecasting guide for Google Ads and other pay-per-click advertising campaigns. It explains measures such as CPA, the cost for each customer or conversion, and ROAS, the revenue earned per unit of ad spend.

In plain words
What is it for?
Use it to calculate CPA, ROAS, click-through rate, cost per click, conversion rate, budget projections, and target gaps. It works from numbers supplied by the user.
Why use it?
It turns provided campaign numbers into budget, cost, conversion, and revenue calculations without needing access to an advertising account. This makes targets and shortfalls easier to quantify.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the google-ads-readonly plugin — 3 skills shipped together , and of google-ads-full

Good fit Use it to calculate CPA, ROAS, click-through rate, cost per click, conversion rate, budget projections, and target gaps. It works from numbers supplied by the user.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/google-ads-skills/google-ads-math
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 itallstartedwithaidea/google-ads-skills --skill google-ads-math
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/google-ads-skills

Made for: Claude Code.

Or install google-ads-readonly, the plugin that ships this one along with the rest of its 3 skills.

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.

agentmods badge for google-ads-math

README.md
[![agentmods](https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-skills/google-ads-math/github.svg)](https://agentmods.dev/skills/itallstartedwithaidea/google-ads-skills/google-ads-math)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/google-ads-skills/google-ads-math"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-skills/google-ads-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.

agentmods 80×15 button for google-ads-math

Your own site · 80×15
<a href="https://agentmods.dev/skills/itallstartedwithaidea/google-ads-skills/google-ads-math"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/google-ads-skills/google-ads-math.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 894 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00894
Opus 5 $0.00027 $0.00447
Sonnet 5 $0.00011 $0.00179
Haiku 4.5 $0.00005 $0.00089

Measured 9d ago against content hash a7051fd1f823, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

google-ads-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 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.

skills/google-ads-math/SKILL.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PPC math engine. When the user provides numbers, run the calculations below and present results in clear tables. No API access needed — this is pure math.

Core Formulas

Cost Per Acquisition (CPA)

CPA = Total Spend / Total Conversions

Return on Ad Spend (ROAS)

ROAS = Revenue / Spend
ROAS as percentage = (Revenue / Spend) × 100

A ROAS of 3.0x means $3 revenue for every $1 spent.

Click-Through Rate (CTR)

CTR = Clicks / Impressions

Cost Per Click (CPC)

CPC = Spend / Clicks

Conversion Rate (CVR)

CVR = Conversions / Clicks

Projection Calculations

Budget Projection

Given: daily spend, CPC, conversion rate

Daily Clicks = Daily Budget / CPC
Daily Conversions = Daily Clicks × CVR
Monthly Spend = Daily Budget × 30.4
Monthly Conversions = Daily Conversions × 30.4
Monthly CPA = Monthly Spend / Monthly Conversions

ROAS Target

Given: spend, revenue, target ROAS

Current ROAS = Revenue / Spend
At Target = Current ROAS >= Target ROAS
Gap = Target ROAS - Current ROAS
Revenue Needed = Spend × Target ROAS

CPA Target

Given: spend, conversions, target CPA

Current CPA = Spend / Conversions
At Target = Current CPA <= Target CPA
To Hit Target = need (Spend / Target CPA) conversions
Additional Conversions Needed = (Spend / Target CPA) - Current Conversions

Conversion Forecast

Given: daily conversions, daily spend, forecast days

Projected Conversions = Daily Conversions × Forecast Days
Projected Spend = Daily Spend × Forecast Days
Projected CPA = Projected Spend / Projected Conversions

Impression Share Opportunity

Given: current impression share (%), total impressions

Missed Impressions = Total Impressions × ((1 - IS) / IS)
Potential Total = Total Impressions + Missed Impressions
Estimated Missed Clicks = Missed Impressions × CTR
Estimated Missed Conversions = Missed Clicks × CVR
Estimated Missed Revenue = Missed Conversions × Avg Conv Value

Read the full file on GitHub · 149 lines

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.

  1. 9d ago First seen · 149 lines · 54 tokens per session scan A a7051fd1f823

Subscribe to this mod's changes

google-ads-math is a skill published in the GitHub repository itallstartedwithaidea/google-ads-skills (34 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 54 tokens to every session and 894 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.