#283283rd of 324 in Skills, plugins and prompts
conductor
Spec-driven development plugin for Antigravity and Claude Code agents
- Stars
- 3.8k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Last release
- Mar 2026
- Language
- Python
3,266 on 3 Apr 20263,778 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Conductor is a plugin that makes a coding agent follow a Context, Spec and Plan, Implement protocol. It writes product, tech-stack and workflow files plus per-track spec.md and plan.md into a conductor/ directory in the repo. Slash commands cover setup, new-track, implement, status, revert and review.
Who it is for: Developers on Claude Code or Antigravity who want planned, reviewable agent work
Strengths
- Keeps project context as versioned markdown in the repo (product.md, tech-stack.md, workflow.md)
- Git-aware revert works on tracks, phases and tasks instead of commit hashes
- Plan is reviewed and approved before the agent writes code
- Installs as a plugin on Antigravity and Claude Code; handles new and existing projects
Weaknesses
- README warns the spec-driven approach increases token consumption, especially on larger projects
- Supports only Antigravity and Claude Code; other agents are not documented
- Protocol is defined in SKILL.md prompts, so adherence depends on the host agent
- Interactive GUI dialogs only in hosts that support them; plain terminals get text menus
What it needs
- no GPU
- Needs Antigravity or Claude Code, git
Quick answers
Is conductor open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |