Define and execute feature work using a Spec-Driven Development methodology—plan tracks, implement tasks, enforce code quality, revert changes via Git, and monitor project progress.
Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.
Plans a new track (feature or bug fix), generates spec/plan documents, and updates the registry.
Reverts previous work (tracks, phases, or tasks) by identifying associated commits and performing Git reverts.
Reviews the completed track work against guidelines and the plan. Acts as a Principal Software Engineer to ensure quality and compliance.
Scaffolds the project and sets up the Conductor environment. Use this whenever a project needs to be initialized or if the Conductor configuration is missing.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimnpx claudepluginhub gemini-cli-extensions/conductor --plugin conductorBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Measure twice, code once.
Conductor is a plugin for AI coding agents (including Antigravity and Claude Code) that enables Spec-Driven Development. It turns your agent into a proactive project manager that follows a strict protocol to specify, plan, and implement software features and bug fixes.
Instead of just writing code, Conductor ensures a consistent, high-quality lifecycle for every task: Context -> Spec & Plan -> Implement.
The philosophy behind Conductor is simple: control your code. By treating context as a managed artifact alongside your code, you transform your repository into a single source of truth that drives every agent interaction with deep, persistent project awareness.
Conductor is packaged as a standard agent plugin, compatible across modern AI coding agents. Choose the installation method for your environment below.
Install directly from GitHub in a single command:
agy plugins install https://github.com/gemini-cli-extensions/conductor
If you are a developer or contributor who wants to fork the repository, write custom skills, or modify rule configurations, clone the repository locally and link it:
Clone the repository:
git clone https://github.com/gemini-cli-extensions/conductor.git
cd conductor
Link globally for Antigravity:
mkdir -p ~/.gemini/config/plugins/ && ln -sfn "$(pwd)" ~/.gemini/config/plugins/conductor
Why this method? Creating a symlink acts as a live development link. Any edits you make in your local Git branch are instantly loaded in real-time without reinstalling!
If you want to isolate Conductor strictly inside a specific Git project:
Create the local plugins directory in your target project's root:
mkdir -p .agents/plugins/
Link Conductor to your local project:
ln -sfn /absolute/path/to/cloned/conductor .agents/plugins/conductor
Register the marketplace repository and install the Conductor plugin directly in your Claude Code session:
/plugin marketplace add gemini-cli-extensions/conductor
/plugin install conductor
To safely remove Conductor from your environment:
agy plugins uninstall conductorrm -f ~/.gemini/config/plugins/conductorrm -f .agents/plugins/conductor/plugin remove conductor and /plugin marketplace remove gemini-cli-extensions/conductorConductor natively adapts its user interface to match the specific visual capabilities of your active developer environment (IDE chat box, terminal console, or web editor).
This is powered by the integrated View Layer UX Adapter:
rules/: Custom adapter rules tailored for visual IDE environments
(like Antigravity).[1] Option A, [2] Option B).This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
🐉 Specialised SRE skills for outage investigations, monitoring graphs, and post-mortems on Google Cloud Platform.
Connect to Looker and interact with your data using LookML.
Connect, query, and generate data insights for BigQuery datasets and data.
The CI/CD extension provides Gemini powered AI assisted CI/CD. It supports deployment to Cloud Run and Cloud Storage as well as creation of a robust CI/CD pipeline.
Conductor: Context-driven development for Claude Code - Measure twice, code once
Complete project development toolkit: 23 agents, 23 slash commands, 29 lifecycle hooks, and 69 reusable skills for Claude Code workflows
GSD Core is a meta-prompting, context engineering, and spec-driven development system for AI coding agents.
13 agents, 35 skills, 19 commands, 15 hooks — spec-driven, multi-agent orchestration for Claude Code with per-phase model tiers, opt-in lifecycle hooks, and optional cross-device semantic memory.
A meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
Generic agent harness for Claude Code — pipeline agents, skills, continuation hook, plus the engine setup (re-run per update).