databricks-template CLAUDE.md

A set of instructions for Claude Code in a Databricks project. Databricks is a platform for running data-processing jobs; this project uses PySpark, a Python interface for Apache Spark, to build those jobs.

In plain words
What is it for?
Use it when developing, testing and deploying data pipelines, jobs, data-quality checks and related Databricks services.
Why use it?
It tells the agent how the project is organized, which tools to use and how to make changes safely without bypassing the established deployment and testing process.

Instructions file

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/andre-salvati/databricks-template/claude-md
Clone the repo
git clone --depth 1 https://github.com/andre-salvati/databricks-template
Per session 2,478 This file is loaded in full into every session.
When invoked 2,478 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 $0.02478 $0.02478
Opus 5 $0.01239 $0.01239
Sonnet 5 $0.00496 $0.00496
Haiku 4.5 $0.00248 $0.00248

Measured 3d ago against content hash dbd274108810, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

databricks-template 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 3d 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 · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

A production-ready PySpark/Databricks ETL pipeline template using medallion architecture, Python packaging, unit + integration tests, Databricks Declarative Automation Bundles (DABs), and DQX data quality framework. Code is structured as a Python wheel package (not notebooks) deployed to Databricks serverless.

Tooling: MCP servers, CLI, skills → see specs/tooling.md

Developed with the Databricks AI Dev Kituser-level tooling (~/.ai-dev-kit/), never installed into or committed to this repo (why that matters). Quick decision list (full reference in specs/tooling.md):

  • Workspace / UC / Jobs / Pipelines / Apps / Serving / SQL → prefer mcp__databricks__* tools over databricks CLI shell-outs or hand-rolled SDK scripts (servers).
  • Bundle / job changesdatabricks-bundles / databricks-jobs skills, and route job edits through scripts/sdk_generate_template_job.py + make deploy (skills).
  • Library/SDK docs (PySpark, Databricks SDK, uv, ruff) → context7 MCP, not memory or web search.
  • Cloud spend / cost analysisaws-billing-cost MCP (AWS_PROFILE=costs) + /project-costs. AWS docsaws-documentation MCP.
  • Records disagree between two tables (batch vs SDP, dashboard vs its table, prod vs staging) → the data-divergence skill (skills) before writing ad-hoc diff SQL.
  • Use the dev profile unless told otherwise (prod for prod ops). If MCP tools are unavailable, fall back to CLI/SDK and flag it.
  • MCP calls run as the prod SP, not as youdev is your user account, but the databricks MCP server is pinned to DEFAULT, which resolves to the same template-sp that prod uses. It can read/write prod tables; the catalog is the guardrail (why).

Read the full file on GitHub · 92 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. 3d ago First seen · 92 lines · 2,478 tokens per session scan A dbd274108810

Subscribe to this mod's changes

databricks-template CLAUDE.md is an instructions file published in the GitHub repository andre-salvati/databricks-template (83 stars, last pushed 27d ago), licensed Apache-2.0. It adds 2,478 tokens to every session, about $0.0124 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 instructions, from other repositories