Skip to content
This repository was archived by the owner on Feb 4, 2026. It is now read-only.

Bring Conductor, a spec-driven development extension for Gemini CLI, to any coding agent environment.

License

Notifications You must be signed in to change notification settings

Jonkimi/Conductor-for-all

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

515 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Conductor Install

npm version

Conductor Install Banner

English | 中文 | 日本語 | 한국어

Conductor Install is a universal command-line tool that brings the Gemini CLI extension Conductor to any AI coding agent environment. It enables the context-first evolution of spec-driven development for Claude Code, OpenCode, Cursor, Kilo Code, and other leading AI Coding Assistants.

Originally developed for the Gemini CLI, the Conductor is now decoupled by this project, empowering developers to maintain context, manage tasks, and orchestrate complex features. It serves as a bridge between human intent and AI execution, ensuring "Context is King" in the era of Agentic AI.

🎯 Goals

  • Universal Compatibility: Enable the Conductor methodology outside of the Gemini CLI ecosystem.
  • Agent-Agnostic Setup: Provide a mechanism to "install" Conductor commands and templates into a project, effectively "enabling" it for consumption by multiple different coding agents.
  • Standardization: Create a unified interface for project orchestration that bridges the gap between human intent and AI execution.

✨ Key Features

  • Universal AI Compatibility: Works out-of-the-box with Opencode, Claude Code, Antigravity, Cursor, VS Code Copilot, Codex, Windsurf, Cline, Kilo Code, Roo Code, Qwen Code, Factory Droid, and Gemini CLI.
  • Context Management: Structured artifacts (spec.md, plan.md) keep your AI agent focused and context-aware.
  • Spec-Driven Development: Define what you want before asking the AI how to build it.
  • Agent-Agnostic Workflows: Switch between agents without losing project context or progress.
  • Easy Initialization: Single command setup with npx conductor-install.

🚀 Usage

1. Setup Conductor in Your Project

conductor-install [path] [options]

Positionals:
  path  Directory to install Conductor                   [string] [default: "."]

Options:
  -a, --agent    Specify the coding agent
          [string] [choices: "opencode", "claude-code", "antigravity", "cursor",
        "vscode-copilot", "codex", "windsurf", "cline", "kilo-code", "roo-code",
                                         "qwen-code", "factory-droid", "gemini"]
  -r, --repo     Git repository URL for conductor. If used without value,
                 defaults to official repository.                       [string]
  -b, --branch   Branch name for conductor repository [string] [default: "main"]
  -s, --scope    Installation scope (project or global)
                                         [string] [choices: "project", "global"]
  -f, --force    Force overwrite existing installation[boolean] [default: false]
  -h, --help     Show help                                             [boolean]
  -v, --version  Show version number                                   [boolean]

To initialize Conductor in your project, simply run the following command in your project root:

npx conductor-install

You can also specify a custom template repository and branch:

npx conductor-install --repo https://github.com/your-org/custom-conductor --branch v2

Or specify the agent directly:

npx conductor-install --agent claude-code

2. Alternative: Build from Source

If you prefer to build from source:

pnpm install
pnpm build
node dist/conductor-install.js

You will be prompted to select your AI Coding Agent:

  • Opencode
  • Claude Code
  • Antigravity
  • Cursor
  • VS Code Copilot
  • Codex
  • Windsurf
  • Cline
  • Kilo Code
  • Roo Code
  • Qwen Code
  • Factory Droid
  • Gemini CLI

This will verify the environment and install the necessary Conductor files:

  • Commands: Agent-specific prompt or command files (e.g., .opencode/commands/conductor:setup.md or .gemini/commands/conductor:setup.toml) that your agent can execute.
  • Templates: Workflow guides and style guides (e.g., .opencode/conductor/templates/).

3. Using Conductor with Your Agent

Once installed, you can instruct your AI Agent to perform Conductor tasks using the installed commands. For example:

  • /conductor:setup - Initialize the project structure.
  • /conductor:newTrack - Start a new feature or bug fix track.
  • /conductor:implement - Implement the selected track.
  • /conductor:review - Review the completed track work against guidelines and the plan.
  • /conductor:revert - Revert previous work.
  • /conductor:status - Check the status of current tracks.

Note: The exact invocation syntax depends on your specific agent's slash command or file context capabilities.

🙏 Acknowledgements

This project is inspired by and based on the Conductor methodology originally developed for the Gemini CLI. We aim to extend its benefits to the broader developer ecosystem.