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.
npx agentmods add instructions/andre-salvati/databricks-template/claude-mdgit clone --depth 1 https://github.com/andre-salvati/databricks-templateWhat 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 | $0.02478 | $0.02478 |
| Opus 5 | $0.01239 | $0.01239 |
| Sonnet 5 | $0.00496 | $0.00496 |
| Haiku 4.5 | $0.00248 | $0.00248 |
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.
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 Kit — user-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 overdatabricksCLI shell-outs or hand-rolled SDK scripts (servers). - Bundle / job changes →
databricks-bundles/databricks-jobsskills, and route job edits throughscripts/sdk_generate_template_job.py+make deploy(skills). - Library/SDK docs (PySpark, Databricks SDK, uv, ruff) →
context7MCP, not memory or web search. - Cloud spend / cost analysis →
aws-billing-costMCP (AWS_PROFILE=costs) +/project-costs. AWS docs →aws-documentationMCP. - Records disagree between two tables (batch vs SDP, dashboard vs its table, prod vs staging) → the
data-divergenceskill (skills) before writing ad-hoc diff SQL. - Use the
devprofile unless told otherwise (prodfor prod ops). If MCP tools are unavailable, fall back to CLI/SDK and flag it. - MCP calls run as the prod SP, not as you —
devis your user account, but thedatabricksMCP server is pinned toDEFAULT, which resolves to the sametemplate-spthatproduses. It can read/writeprodtables; the catalog is the guardrail (why).
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.
- 3d ago First seen · 92 lines · 2,478 tokens per session scan A dbd274108810
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.
Other instructions, from other repositories
dbt_duckdb_demo_public CLAUDE.md
Instructions for edwinweber/dbt_duckdb_demo_public, covering claude.md — project context for ai assistants, project overview, tech stack, architecture and directory structure.
dbt-mcp CLAUDE.md
Instructions for dbt-labs/dbt-mcp, covering claude.md, project overview, key paths, tool architecture and mcp apps (tools with interactive ui).
ai-genie-factory AGENTS.md
Instructions for mexmarv/ai-genie-factory, covering ai genie factory — core constraints, global rules, stack, error handling and logging.
agentic-data-kit copilot-instructions.md
Instructions for luccapinto/agentic-data-kit, covering agentic data kit — operating rules, language, how to work, data engineering principles (always apply) and data debugging quick reference.
advanced-calc-engine AGENTS.md
AGENTS.md instructions for surajpanwar/advanced-calc-engine, covering advancedcalc engine, project purpose, architecture, core rules and agent responsibilities.
analytics-with-claude-code CLAUDE.md
Instructions for adityawrk/analytics-with-claude-code, covering analytics assistant, credential discovery & connection, onboarding -- learn from queries, agent orchestration and auto-review pipeline.