google-ads-tracker

google-ads-tracker is a skill for Claude Code from chanktb/claude-google-ads. It costs 104 tokens per session (836 once invoked), scanned A, original, MIT.

A read-only skill for monitoring live Google Ads campaigns, especially campaigns that are still in their learning phase. It reports budget pacing, delivery, performance changes, conversions, and account anomalies without changing the campaigns.

In plain words
What is it for?
Use it after launching campaigns or during routine checks to review spending, learning status, CPC, CPA, ROAS, conversions, delivery, and disapproved assets.
Why use it?
It separates observation from optimization, making it easier to detect genuine problems without confusing recent intentional edits with failures.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; positional $N argument.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-google-ads plugin — 15 skills, 15 commands shipped together

Good fit Use it after launching campaigns or during routine checks to review spending…

Compare 6 skills from other repositories ↓
Install

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.

Claude Code
/plugin marketplace add chanktb/claude-google-ads
Claude Code
/plugin install claude-google-ads

Made for: Claude Code.

Or install claude-google-ads, the plugin that ships this one along with the rest of its 15 skills, 15 commands.

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-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/chanktb/claude-google-ads/tracker.svg)](https://agentmods.dev/skills/chanktb/claude-google-ads/tracker)
Your own site
<a href="https://agentmods.dev/skills/chanktb/claude-google-ads/tracker"><img src="https://agentmods.dev/badge/skills/chanktb/claude-google-ads/tracker.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 836 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 $0.00104 $0.00836
Opus 5 $0.00052 $0.00418
Sonnet 5 $0.00021 $0.00167
Haiku 4.5 $0.00010 $0.00084

Measured 7d ago against content hash 033196ed344b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

google-ads-tracker 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 7d 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/tracker/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Watch live campaigns and surface what's happening. Changes nothing in the account — that's the optimizer's job. Especially useful right after a pusher launch (the learning window).

Operating rules

  • Observe-only: report and alert, never mutate. Read everything from account-context.yaml.
  • Honor guardrails: a change-event-cooldown means don't raise an anomaly right after a deliberate change.
  • No false absence (GUARD-6 from audit): prove completeness before reporting "no delivery / no conversions".

Model dispatch (run cheap, decide expensive) — see ${CLAUDE_PLUGIN_ROOT}/references/model-tier-dispatch.md

  • Scout (haiku) — STEP 0 context read; identifying newly-launched vs established by start date.
  • Routine (sonnet) — STEP 1 per-campaign performance + change_event pull. Dispatch as a general-purpose sub-agent; return raw rows + the daily trend, don't flag.
  • Judge (main session) — STEP 2-4 learning-phase read, pacing call, and especially anomaly-vs-expected (apply the cooldown — a recent deliberate change is NOT an anomaly). The pull is cheap; deciding what's normal variance vs a real alert is judgment.

STEP 0 — Load

Read account-context.yaml (customer_id, guardrails, margin_tiers for ROAS context). If it's missing, run setup first — never observe on an unconfigured/half-connected account. Identify which campaigns are newly launched (recent change_event / start date) vs established.

STEP 1 — Pull recent performance

Per campaign over the relevant window (explicit YYYY-MM-DD dates): spend, conversions, conv value, ROAS, CPC, CPA, impression share, and the daily trend. Pull recent change_event history too.

STEP 2 — Learning-phase status (new campaigns)

  • Is the campaign accumulating conversions toward the learning floor (~15-30/period)? Project days-to-exit.
  • Flag campaigns stuck below the floor (will never stabilize at current budget → note for optimizer to consolidate, but tracker only flags).
  • During learning, do NOT read short-term ROAS swings as problems — say so explicitly.

Read the full file on GitHub · 59 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. 7d ago First seen · 59 lines · 104 tokens per session scan A 033196ed344b

Subscribe to this mod's changes

google-ads-tracker is a skill published in the GitHub repository chanktb/claude-google-ads (11 stars, last pushed 1mo ago), licensed MIT. It adds 104 tokens to every session and 836 once invoked, about $0.0005 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.

Related

Other skills, from other repositories