Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chanktb/claude-google-ads/plugin install claude-google-adsWrote 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/chanktb/claude-google-ads/plan)<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/plan"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/plan.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 5.1 | $0.00116 | $0.01522 |
| Opus 5 | $0.00058 | $0.00761 |
| Sonnet 5 | $0.00023 | $0.00304 |
| Haiku 4.5 | $0.00012 | $0.00152 |
Grade A, and why
google-ads-plan 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 8d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Google Ads — Plan
Turn a budget + business context into a concrete plan and an honest forecast. Read everything from the context and the audit/measurement outputs — no hardcoding, no guessing where data exists.
STEP 0 — Load context + GATE
- Read
account-context.yaml(budget, AOV, margin_tiers, brand_terms, vertical, guardrails) and the latestaudit+measurementoutputs from the working directory. If the context is missing, runsetupfirst — never plan spend without it. - Measurement gate: if
measurement= FAIL, STOP — do not plan spend on broken tracking. Tell the user to fix tracking first. WARN is allowed but carried into the plan as a risk note. - Confirm
campaign_defaults.daily_budget(or ask). Output is written to the working directory.
Model dispatch (run cheap, decide expensive) — see ${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md
- Scout (
haiku) — theforecaster.pyrun; reading existing campaign budgets. - Routine (
sonnet) — STEP 1 mode-detection pull (existing campaigns + spend), STEP 4 deriving CPC/CVR from account data. Dispatch asgeneral-purposesub-agents; return raw, don't decide the mode. - Judge (main session) — STEP 0 measurement gate, the campaign mix + sequencing, budget split, forecast interpretation (band not promise), ramp roadmap, risks. The data is cheap; the plan is judgment.
STEP 1 — Detect mode: LAUNCH vs EXPANSION
Read existing ENABLED campaigns + their spend/performance. The plan differs sharply:
- LAUNCH (no/low history) — start simple, lean on benchmarks, conservative ranges, one or two campaign types, no target ROAS during learning.
- EXPANSION (established account) — read actual scale and find gaps. Read the real budget scale, don't assume small (e.g. a mature account may run $1k+/day across many campaigns). Recommend additions/reallocations against what already exists, not a from-scratch structure. State which mode you detected and why.
What ships with it
1 file 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.
- 8d ago First seen · 90 lines · 116 tokens per session scan A 0e65e33508de
google-ads-plan is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 2mo ago), licensed MIT. It adds 116 tokens to every session and 1,522 once invoked, about $0.0006 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
google-ads
A Google Ads guide for campaigns and advertising copy aimed at the Russian market in 2026. Google Ads is Google's paid advertising platform, and the guide covers formats such as search, video, app, shopping, and display ads.
markifact-overview
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
safe-write-operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
google-ads-ecommerce
Build and optimize Google Ads campaigns for ecommerce with Performance Max, Shopping feeds, conversion tracking, and Smart Bidding strategies for ROAS.
setup-conversion-tracking
Set up Converly conversion tracking end to end. Use when the user wants to track form submissions as conversions, send leads to an ad platform like Google Ads, Meta or Google Analytics, or set up Converly for the first time.
diagnose-missing-conversions
Find out why Converly conversions aren't showing up. Use when the user says tracking isn't working, conversions are missing, a form submission didn't appear, or an ad platform isn't receiving conversions.