A command for checking the health of a Google Analytics 4 (GA4) property, the account container that holds a site's or app's analytics data.

Use it to run health checks on a property identified by its ID, project name, client name, or website address.

It can reveal configuration or data-quality problems before the analytics results are used for decisions.

ga4-audit — Command for Claude Code by ivanovzlatan2

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.

Clone the repo

git clone --depth 1 https://github.com/ivanovzlatan2/data-arsenal-v1

Made for: Claude Code.

Or install data-arsenal, the plugin that ships this one along with the rest of its 5 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit/github.svg)](https://agentmods.dev/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit)

Your own site

<a href="https://agentmods.dev/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit"><img src="https://agentmods.dev/badge/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit"><img src="https://agentmods.dev/badge/commands/ivanovzlatan2/data-arsenal-v1/ga4-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,599 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.

Model	Per session	Once invoked
Fable 5.1	$0.00008	$0.02599
Opus 5	$0.00004	$0.01300
Sonnet 5	$0.00002	$0.00520
Haiku 4.5	$0.00001	$0.00260

Measured 11d ago against content hash 01e41b024d21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ga4-audit 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 11d 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.

commands/ga4-audit.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ga4-audit - Health Checks

Runs health checks on a GA4 property. Uses cloud API (50 checks) or local Data API (20 checks), depending on setup mode.

Usage

/ga4-audit <property>

<property> can be: numeric property ID, project slug, client name, or URL. See Property Resolution below.

Steps

Step 0: Language & setup

Language check: Read ~/.config/data-arsenal/config.json.

If language is set → use that language for all commentary and recommendations. Data labels and GA4 metric names stay in English.
If language is NOT set (first run) → output as plain text (NOT AskUserQuestion): "What language should I use? (English / Bulgarian / other)" Wait for user response, interpret it, save to config.json so it's never asked again.

Property resolution: Resolve <property> to a numeric property_id:

If numeric → use as property_id directly
If matches a project slug in ~/.config/data-arsenal/projects/ → read property_id from that project's config.json
If neither → run resolve_property() from _ga4_lib.py to search GA4 account by name
If still not found → ask user to clarify

Pre-flight questions — Ask all upfront before running anything (AskUserQuestion, single round):

a. Ecommerce: "Is this an ecommerce property? (yes / no / auto-detect) [default: auto-detect]" Map to --ecommerce flag value.

b. PDF report: "Generate a PDF report? (yes / no) [default: yes]" If yes, will run with --format pdf which outputs both markdown to stdout and PDF to ~/Desktop/.

Step 1: Run the audit script

Find the script in order:

~/.config/data-arsenal/scripts/ga4-audit (post-setup, primary)
scripts/ga4-audit (CWD is the repo)
If neither exists, tell the user to run /ga4-setup first

Read ~/.config/data-arsenal/config.json to check the mode field:

If mode is cloud: script calls dataarsenal.com API (50 checks)
If mode is local or missing: script runs 20 local checks

SCRIPT=""
if [ -x ~/.config/data-arsenal/scripts/ga4-audit ]; then
  SCRIPT=~/.config/data-arsenal/scripts/ga4-audit
elif [ -f scripts/ga4-audit ]; then
  SCRIPT=scripts/ga4-audit
fi

if [ -z "$SCRIPT" ]; then
  echo "ERROR: Script not found. Run /ga4-setup first."
  exit 1
fi

FORMAT="markdown"
# If user said yes to PDF:
# FORMAT="pdf"

$SCRIPT <property_id> --lang <language_code> --ecommerce <auto|yes|no> --format $FORMAT

Read the full file on GitHub · 230 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.

11d ago First seen · 230 lines · 8 tokens per session scan A 01e41b024d21

Subscribe to this mod's changes

ga4-audit is a command published in the GitHub repository ivanovzlatan2/data-arsenal-v1 (5 stars, last pushed 5mo ago), licensed MIT. It adds 8 tokens to every session and 2,599 once invoked, about $0.0000 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 2026-08-31.

Analytics and metrics

ga4-audit

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/ga4-audit - Health Checks

Usage

Steps

Step 0: Language & setup

Step 1: Run the audit script

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement