Conductor: Introducing Context-Driven Development for Gemini CLI
Benjamin Franklin said: "Failing to plan is planning to fail". Yet, in the age of AI, we often dive straight into implementation without establishing a clear understanding of what we are building.
Conductor, a new extension for Gemini CLI, changes this workflow by using context-driven development. Rather than depending on impermanent chat logs, Conductor helps you create formal specs and plans that live alongside your code in persistent Markdown files.
The Philosophy: Control Your Code
Instead of diving straight into implementation, Conductor helps you formalize your intent. It unlocks context-driven development by shifting the context of your project out of the chat window and directly into your codebase.
Key Benefits
- Plan before you build: Create specs and plans that guide the agent for new and existing codebases.
- Maintain context: Ensure AI follows style guides, tech stack choices, and product goals.
- Iterate safely: Review plans before code is written, keeping you firmly in the loop.
- Work as a team: Give your AI agents the same project and best practices context.
How Conductor Works
Conductor is a structured workflow for agentic development which is ideal for tasks more complex than simple code edits. Unlike a standard chat session which is confined to a single session, Conductor uses a set of Markdown files to plan and track progress over time.
Establish Context
Define product goals, tech stack, and workflow preferences once.
Specify & Plan
Generate detailed specs and actionable to-do lists for every feature.
Implement
Agents follow the plan, checking off tasks and inserting checkpoints for review.
Support for "Brownfield" Projects
Most development work involves established codebases ("brownfield"). This is often where AI tools struggle, lacking the nuanced understanding of a project's history and architecture.
Conductor approaches this challenge by initiating an interactive session to help you create a foundational set of documents about your project’s architecture, guidelines, and goals. As you build new features, Conductor updates this shared context, ensuring its knowledge grows alongside your project.
Conductor for Teams
By centralizing technical constraints and coding standards, you ensure that every AI-generated contribution adheres to your specific guidelines, regardless of which developer runs the command.
Shared Foundation
Teams can define an established testing strategy or coding style that is automatically used by Gemini. This shared configuration accelerates onboarding and ensures consistent output across the entire engineering team.
The Lifecycle: Context → Spec → Plan → Implement
Conductor uses a precise sequence of commands to manage the development lifecycle:
1. Project Setup: /conductor:setup
Builds the base context in a conductor/ directory. Artifacts include:
product.md: Users, goals, and high-level features.tech-stack.md: Languages, databases, and frameworks.workflow.md: Team preferences (e.g., TDD).styleguides/: Detailed coding standards.
2. New Tracks: /conductor:newTrack
Initializes a feature or bug fix. Generates a track-specific directory with:
spec.md: Detailed requirements for the job.plan.md: Actionable to-do list (Phases, Tasks, Sub-tasks).
3. Implementation: /conductor:implement
The agent works through the plan.md, checking off tasks and pausing at checkpoints for human verification.
Operational Commands
/conductor:statusShow track and task progress./conductor:reviewValidate work against guidelines./conductor:revertGit-aware rollback of logical units./conductor:syncSync context after completion.Get Started
Install the extension and start using Conductor today to experience context-driven development.
gemini extensions install https://github.com/gemini-cli-extensions/conductorEmpower Your Engineering Team
By treating your documentation as the source of truth, you empower Gemini to act as a true extension of your engineering team.
