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.
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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.
[](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/481-databricks)<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/481-databricks"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/481-databricks.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.02972 |
| Opus 5 | $0.00016 | $0.01486 |
| Sonnet 5 | $0.00006 | $0.00594 |
| Haiku 4.5 | $0.00003 | $0.00297 |
Grade A, and why
481-databricks 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 4d 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 — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Databricks Engineering Ruleset
Audience: engineers building Databricks jobs, notebooks, Lakeflow pipelines, SQL warehouses, Delta Lake tables, and governed AI/data workloads
Goal: reliable pipelines with predictable performance, governed access, and safe maintenance
[!IMPORTANT] Default to a Lakehouse mental model: bronze/silver/gold (or raw/curated/serving), with explicit contracts between layers.
[!NOTE] Current Databricks terminology: Lakeflow Spark Declarative Pipelines is the current product name for what was formerly Delta Live Tables (DLT). Existing
dltcode still works, but new examples should preferfrom pyspark import pipelines as dp. Declarative Automation Bundles is the current name for what was formerly Databricks Asset Bundles (DABs).
Non-negotiables
NN-1: Unity Catalog is required for production
Production data and AI assets use Unity Catalog. Hive metastore is a legacy migration source only.
Reject in review:
USE CATALOG hive_metastorein production code- persistent data under DBFS mounts (
dbfs:/mnt/...) instead of Unity Catalog volumes / external locations - grants to
account usersor individual owners for production data - tables, volumes, functions, or models without group/service-principal ownership
NN-2: Standard access mode by default; Dedicated only by exception
Use Standard access mode for most Unity Catalog workloads. Use Dedicated only for workloads that need capabilities Standard does not support (for example some ML/GPU/R/RDD patterns), and document the reason.
Reject in review:
- No-isolation shared compute for governed production workloads
- legacy credential passthrough in Unity Catalog workspaces
- interactive all-purpose clusters running scheduled production jobs
NN-3: Declarative Automation Bundles for deployable projects
Use Declarative Automation Bundles (formerly Databricks Asset Bundles) for jobs, Lakeflow pipelines, notebooks, and deployment metadata that must move across environments. Terraform still owns account/workspace infrastructure; bundles own deployable Databricks project resources.
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.
- 4d ago First seen · 333 lines · 32 tokens per session scan A 5ca678b540fc
481-databricks is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,972 once invoked, about $0.0002 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 2026-09-03.
Other cursor rules, from other repositories
python-app
Here's how the python application is organized.
System Components and Requirements
Transforms Databricks Unity Catalog tables into a materialized knowledge graph, with ontology design and reasoning exposed as tools via MCP.
209-dbt-model-quality
Purpose: Maintain high standards for dbt models.
standards-data-eng
Mandatory standards for Python and SQL data pipelines.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.