agent-plane

Deep reference on agent plane config format, executor types, skill/tool structure, and conventions. Load when you need to look up how the platform works.

Patterns and templates for generating valid agent plane agent directories. Load when ready to create files.

Build terminal REPLs for agent-plane using the Python UI SDK. Use when the user asks about building a REPL, terminal chat, or CLI frontend for an agent.

Deploy agent-plane to Databricks Apps with Lakebase and UC Volumes. Use when setting up infrastructure, deploying, redeploying, troubleshooting, or connecting to a remote agent-plane instance on Databricks.

Detect Python agent frameworks from code imports and map them to agent plane executor types. Load when the user has existing agent code to integrate.

Investigate a topic in depth, find sources, and synthesize findings.

Systematically diagnose and fix bugs using logs, stack traces, and targeted investigation.

Review code for bugs, security issues, and style problems. Provide actionable feedback.

Explain a concept, process, or decision in plain language at the appropriate level.