consort
v0.3.97Consort: a Spec-First Branched-Database TDD agent framework for building transactional applications on Lakebase (Databricks' serverless Postgres/OLTP database, not the Delta Lakehouse). A deterministic orchestrator drives role agents through a spec-first design lane and a test-driven build lane whose every cycle runs against a live copy-on-write branch of a real Postgres database, with human-in-the-loop gates that fail closed. For application backends on Postgres, not ETL or analytics. Run /consort:start to launch the workflow.
By Databricks27 GitHub starsUpdated 2 weeks ago
Directory evidence
- Runtimes
- Claude Code
- Parsed components
- 4 skill or MCP entries
- Source updated
- Sep 23, 2026
- Manifest status
- Canonical path parsed
The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →
Install consort for Claude Code
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install consort@agent-plugin-marketplacePaste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.
The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.
Get the source manually
git clone https://github.com/databricks-solutions/consortClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .claude-plugin/plugin.json├── skills/architectural-design-principles/SKILL.md├── skills/software-design-principles/SKILL.md├── skills/ui-ux-design-principles/SKILL.md└── .mcp.json
Included Skills3
System-level engineering canon, the architecture counterpart to software-design-principles. Layered architecture + dependency direction, ports and adapters (repository / ORM-as-adapter), the twelve-factor app for cloud-native development, evolutionary architecture with fitness functions, and evolutionary database design (schema that evolves by migration on paired branches). Imported by workflow skills (consort, lakebase-scm-workflows). Use when: shaping a system boundary, deciding what is a backing service, mapping config to the environment, or authoring the fitness functions that keep the architecture honest as it evolves.
Foundational engineering canon – SOLID, DRY, clean code, layered architecture, cross-cutting concerns, NFRs. Imported by workflow skills (consort, lakebase-scm-workflows). Use when designing a module, reviewing a PR, planning a refactor, mapping cross-cutting concerns to layers, or arguing about API shape.
Experience-level engineering canon, the UI/UX counterpart to software-design-principles (code-level) and architectural-design-principles (system-level). Usability heuristics, visual hierarchy, accessibility, interaction and feedback, information architecture, design systems and tokens, and testable UI. Imported by the consort UX Designer (authoring design-guide.{md,json} + ia.md and the adherence gate) and by the Driver building UI. Use when: shaping a design guide or information architecture, reviewing a user-facing surface, choosing a UI framework, or making the UI testable.
MCP servers1
- command
- node
- args
- ${CLAUDE_PLUGIN_ROOT}/dist/apps/mcp-server/index.js
MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.
Plugin manifests1
{
"name": "consort",
"description": "Consort: a Spec-First Branched-Database TDD agent framework for building transactional applications on Lakebase (Databricks' serverless Postgres/OLTP database, not the Delta Lakehouse). A deterministic orchestrator drives role agents through a spec-first design lane and a test-driven build lane whose every cycle runs against a live copy-on-write branch of a real Postgres database, with human-in-the-loop gates that fail closed. For application backends on Postgres, not ETL or analytics. Run /consort:start to launch the workflow.",
"version": "0.3.97",
"author": {
"name": "Databricks"
},
"repository": "https://github.com/databricks-solutions/consort",
"keywords": [
"lakebase",
"databricks",
"postgres",
"branch-pairing",
"branching",
"tdd",
"scm",
"release-management",
"agentic-development",
"human-in-the-loop"
],
"skills": "./skills/",
"hooks": {
"SessionStart": [
{
"hooks": [
{
"type": "command",
"command": "d=\"${CLAUDE_PLUGIN_ROOT:-}\"; { [ -n \"$d\" ] && [ -f \"$d/package.json\" ] && [ ! -f \"$d/node_modules/.package-lock.json\" ]; } && { echo 'consort: finishing plugin dependency install (the cached npm ci was interrupted or timed out)...' >&2; ( cd \"$d\" && npm ci ) || echo 'consort: dependency install failed; run npm ci in the plugin dir manually.' >&2; }; true"
}
]
}
]
}
}For maintainers
If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.
[consort on Agent Plugins Marketplace](https://pluginsmp.com/plugins/consort)