Databricks CLI

What it does

When your agent uses it

• Running databricks commands
• Managing Databricks infrastructure
• Deploying bundles
• Querying serving endpoints

Example prompts

• “databricks”
• “databricks cli”
• “unity catalog”
• “/databricks-cli”

Requirements

• A credential in DATABRICKS_TOKEN

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Bundle settings files (if running from bundle directory)
2. 2Environment variables (DATABRICKS_HOST, DATABRICKS_TOKEN, etc.)
3. 3.databrickscfg profiles

What it can do on your machine

Read from SKILL.md and the folder at commit 56a3b4a. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • databricks
  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • accounts.cloud.databricks.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • DATABRICKS_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Databricks CLI loads about 2.1k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 157 tokens; SKILL.md has 567 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~157

When it runs · the whole SKILL.md, loaded when a task matches

~2.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aehrc/pathling at commit 56a3b4a, republished under its Apache-2.0 licence (© aehrc). 567 words, ~2,133 tokens.

name

databricks-cli

description

Expert guidance for using the Databricks CLI to manage Databricks workspaces, clusters, jobs, pipelines, Unity Catalog, SQL warehouses, serving endpoints, secrets, bundles, and all other Databricks resources. Use this skill when running databricks commands, managing Databricks infrastructure, deploying bundles, querying serving endpoints, managing Unity Catalog objects, or automating Databricks workflows. Trigger keywords include "databricks", "databricks cli", "dbfs", "unity catalog", "databricks bundle", "databricks jobs", "databricks clusters", "sql warehouse", "serving endpoint", "databricks secrets".

databricks <command-group> [<command>] [<subcommand>] [args] [--flags]

# Workspace-level
databricks auth login --host https://<workspace>.cloud.databricks.com

# Account-level
databricks auth login --host https://accounts.cloud.databricks.com --account-id <id>

[my-sp-profile]
host = https://<workspace>.cloud.databricks.com
client_id = <service-principal-client-id>
client_secret = <service-principal-oauth-secret>

databricks auth profiles          # List all profiles
databricks auth env -p PROD       # Show profile settings
databricks auth token -p PROD     # Show current token
databricks auth describe          # Current auth config details

# Inline (Linux/macOS)
databricks jobs create --json '{"name": "my-job", ...}'

# From file
databricks jobs create --json @job-config.json

databricks clusters get <id> | jq -r .cluster_name

databricks api get /api/2.0/clusters/list
databricks api post /api/2.0/clusters/create --json '{"cluster_name": "test", ...}'
databricks api post /api/2.0/clusters/edit --json @edit-cluster.json

databricks clusters start <id> --no-wait
databricks jobs run-now <job-id> --timeout 30m

databricks <resource> get-permission-levels <id>
databricks <resource> get-permissions <id>
databricks <resource> set-permissions <id> --json @perms.json
databricks <resource> update-permissions <id> --json @perms.json

databricks jobs list --limit 10 --page-token <token>

© aehrc, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 9 other files (references) in .claude/skills/databricks-cli of aehrc/pathling.

• SKILL.md
• references/account.md
• references/bundles.md
• references/compute.md
• references/identity.md
• references/jobs-pipelines.md
• references/ml-serving.md
• references/sql-analytics.md
• references/unity-catalog.md
• references/workspace.md

Open the folder on GitHubat commit 56a3b4a