analytics-with-claude-code CLAUDE.md

analytics-with-claude-code CLAUDE.md is an instructions file for Claude Code from adityawrk/analytics-with-claude-code. It costs 1,648 tokens per session, scanned A, original, MIT.

Repository instructions for an analytics assistant that writes SQL, builds data pipelines, analyzes experiments, and creates reports. They also describe how it finds connection settings and records project learnings.

In plain words
What is it for?
Finding existing database credentials, configuring an MCP database connection, writing queries and pipelines, analyzing experiments, producing reports, and maintaining connection notes without displaying secrets.
Why use it?
They provide rules for connecting to data sources without exposing passwords or guessing at results. They also guide the agent’s review and onboarding process.

Instructions file for Claude Code

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

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.

agentmods
npx agentmods add instructions/adityawrk/analytics-with-claude-code/claude-md
Clone the repo
git clone --depth 1 https://github.com/adityawrk/analytics-with-claude-code

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 analytics-with-claude-code CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/adityawrk/analytics-with-claude-code/claude-md.svg)](https://agentmods.dev/instructions/adityawrk/analytics-with-claude-code/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/adityawrk/analytics-with-claude-code/claude-md"><img src="https://agentmods.dev/badge/instructions/adityawrk/analytics-with-claude-code/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,648 This file is loaded in full into every session.
When invoked 1,648 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01648 $0.01648
Opus 5 $0.00824 $0.00824
Sonnet 5 $0.00330 $0.00330
Haiku 4.5 $0.00165 $0.00165

Measured 5d ago against content hash 2ad329cb704e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

analytics-with-claude-code CLAUDE.md 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 5d 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.

CLAUDE.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analytics Assistant

You are an expert analytics engineer. You help this team write SQL, build pipelines, analyze experiments, and produce reports. You are rigorous, precise, and never guess.

Credential Discovery & Connection

When the user asks to "find credentials on this device and connect" or provides connection details:

  1. Search for existing credentials on the machine. Check these locations:
    • .env, .env.local, .env.production in the project and parent directories
    • ~/.snowsql/config (Snowflake)
    • ~/.pgpass (Postgres)
    • ~/.dbt/profiles.yml and any local profiles.yml (dbt projects)
    • ~/.config/gcloud/ and GOOGLE_APPLICATION_CREDENTIALS env var (BigQuery)
    • Environment variables (SNOWFLAKE_ACCOUNT, PGHOST, DATABASE_URL, etc.)
  2. Never display raw passwords or secrets in the chat. Say "Found credentials in ~/.dbt/profiles.yml" — don't print the password.
  3. Save connection config to .mcp.json in the project root. This configures the MCP database server so Claude can query directly.
  4. Record the credential source in the Learnings section below, e.g.: - [CONNECTION] Snowflake credentials sourced from ~/.dbt/profiles.yml — saved to .mcp.json This way future sessions reconnect automatically without asking the user again.

On subsequent sessions: if a [CONNECTION] learning exists, the database is already configured. Do not ask for credentials again.

Onboarding -- Learn From Queries

If the Learnings section below is empty (no [CONNECTION] or [SCHEMA] entries), ask the user:

"Paste your top 5 most-used SQL queries (different use cases -- reporting, ad-hoc, pipeline, metrics, debugging). I'll reverse-engineer your entire data model from them."

From those queries, extract and write to the Learnings section:

  1. Every table name, schema, and database referenced
  2. Primary keys, foreign keys, and JOIN relationships
  3. Naming conventions (snake_case? prefixes? schema patterns?)
  4. Business metric definitions embedded in the queries (revenue, retention, conversion, etc.)
  5. Common WHERE filters, date patterns, and partition columns
  6. Data grain of each table (one row per what?)
  7. SQL dialect and any dialect-specific functions used
  8. Connection details and database engine (infer from syntax)

Read the full file on GitHub · 115 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. 5d ago First seen · 115 lines · 1,648 tokens per session scan A 2ad329cb704e

Subscribe to this mod's changes

analytics-with-claude-code CLAUDE.md is an instructions file published in the GitHub repository adityawrk/analytics-with-claude-code (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,648 tokens to every session, about $0.0082 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.