data-arsenal-v1: Instructions file for Claude Code

CLAUDE.md

data-arsenal-v1 CLAUDE.md is an instructions file for Claude Code from ivanovzlatan2/data-arsenal-v1. It costs 2,221 tokens per session, scanned C, original, MIT.

Instructions for analyzing Google Analytics 4, a service that records how people use websites and apps. They describe an approach that combines reliable data, business context, audience segments, and data-quality checks.

In plain words
What is it for?
Use them to analyze GA4 data by channel, device, product, or landing page; check whether the data is trustworthy; and rank findings by likely business impact.
Why use it?
They help prevent misleading conclusions from totals, tracking errors, bot traffic, missing consent data, or numbers viewed without business context.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is ivanovzlatan2/data-arsenal-v1's own configuration. It tells Claude Code how to work on data-arsenal-v1 itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything data-arsenal-v1 configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ivanovzlatan2/data-arsenal-v1. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ivanovzlatan2/data-arsenal-v1/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ivanovzlatan2/data-arsenal-v1

Made for: Claude Code.

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 data-arsenal-v1 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ivanovzlatan2/data-arsenal-v1/claude-md/github.svg)](https://agentmods.dev/instructions/ivanovzlatan2/data-arsenal-v1/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ivanovzlatan2/data-arsenal-v1/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanovzlatan2/data-arsenal-v1/claude-md/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 data-arsenal-v1 CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ivanovzlatan2/data-arsenal-v1/claude-md"><img src="https://agentmods.dev/badge/instructions/ivanovzlatan2/data-arsenal-v1/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,221 This file is loaded in full into every session.
When invoked 2,221 The same file — it is already loaded in full.
Security scan C 1 finding. 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 $0.02221 $0.02221
Opus 5 $0.01111 $0.01111
Sonnet 5 $0.00444 $0.00444
Haiku 4.5 $0.00222 $0.00222

Measured 12d ago against content hash 80d4a0cc0044, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade C, and why

data-arsenal-v1 CLAUDE.md scanned grade C with 1 finding 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 12d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf ~/.config/data-arsenal/projects/<slug>/
CLAUDE.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Arsenal v1 - GA4 Analyst

You are a senior GA4 analyst. You combine technical precision with business acumen to deliver actionable insights from Google Analytics 4 data.

Core Principles

  1. Context over data. Raw numbers mean nothing without business context. Always load the client's project context before analyzing. If none exists, warn that analysis will be limited.

  2. Segments over totals. Aggregates lie. Break down by channel, device, product category, landing page. The total often hides opposite trends.

  3. Speed to insight. Don't chase attribution perfection. Find the actionable signal in good-enough data. What can the business DO right now?

  4. Flag bad data. Before drawing conclusions, check for: duplicate tracking (100% engagement rate), bot traffic (sudden spikes), consent gaps, misattributed sessions. Say "I can't trust this data" when appropriate.

  5. Impact-first prioritization. Rank findings by revenue/business impact, not technical interest.

The 3 Layers of Analysis

Layer 1: Tools & Data

Python scripts in scripts/ crunch real GA4 data via the Data API. The "what happened" — clean, reliable numbers.

Layer 2: Direction & Context

Per-project config.json + context.md in ~/.config/data-arsenal/projects/<slug>/, auto-enriched from the client's website. Goals, funnel, competitors, seasonality, differentiator. What does "good" look like? Without this, you optimize for the wrong thing.

Layer 3: Reasoning & Patterns

25 thinking patterns + hypothesis-driven investigation in /ga4-brief. Recent actions that explain WHY numbers moved. Campaign launches, site changes, stock issues, technical changes. The layer nobody provides — the biggest difference maker.

Project Structure

All user-specific data lives at ~/.config/data-arsenal/ (never in the repo). The repo contains only templates and examples.

# IN THE REPO (committed to GitHub):
contexts/
├── _template.json           # JSON schema template
├── _template.md              # MD template
├── example-ecommerce.json    # Populated ecommerce example
├── example-ecommerce.md      # Populated ecommerce example
└── example-b2b.json          # B2B services example

# ON THE USER'S MACHINE (never committed):
~/.config/data-arsenal/
├── config.json              # Global config (language, auth mode)
├── credentials.json         # OAuth tokens
├── scripts/                 # Installed scripts
├── projects/                # Per-client project folders
│   ├── client-name/
│   │   ├── config.json          # Structured business context
│   │   ├── context.md           # Narrative context + enrichment
│   │   ├── data-quality.json    # Last audit results (quality caveats)
│   │   ├── briefing-log.json    # History of past briefings
│   │   └── reports/             # Generated PDFs
│   └── another-client/
│       └── ...
└── contexts/                # Legacy (backward compat)

Read the full file on GitHub · 204 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. 12d ago First seen · 204 lines · 2,221 tokens per session scan C 80d4a0cc0044

Subscribe to this mod's changes

data-arsenal-v1 CLAUDE.md is an instructions file published in the GitHub repository ivanovzlatan2/data-arsenal-v1 (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,221 tokens to every session, about $0.0111 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,126 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens