Skip to content

Conversation

@edithatogo
Copy link

  1. Updated approach from previous contributor to codex-based tools.
  2. Added support for Qwen Code
  3. Added support for VSCode-based tools, inc. Google Antigravity

For what it's worth, I'm using Conductor with VSCode, Google Antigravity, Codex and Qwen Code. Definitely slightly different experiences, and more powerful models handle it better- Codex has the closest experience, followed by Google Antigravity. Qwen Code is problematic. Haven't actually tested in either Copilot GUI or CLI, nor in Claude Code.

jasonkneen and others added 30 commits December 19, 2025 07:06
Introduces Claude Code plugin manifests, slash command definitions, and Agent Skills-compatible skill files for Conductor. Adds detailed documentation for Claude Code usage and interoperability with Gemini CLI and Agent Skills. Updates README to reflect multi-platform support and installation options.
This adds Conductor as a reusable AI agent skill following the skills
standard adopted by Claude CLI, OpenCode, and Codex.

The skill provides:
- SKILL.md with core concepts and quick start guide
- Protocol references for each command (setup, newTrack, implement, status, revert)
- Install script that copies assets from templates/

Benefits:
- Global installation (~/.claude/skills/conductor/)
- Works with multiple AI CLIs (Claude, OpenCode, Codex)
- Auto-discovery by AI agents when relevant
- Reuses existing templates (no duplication)
- Make description more action-oriented (create feature, write spec, etc.)
- Add setup mention for unconfigured projects
- Installer now asks user where to install (OpenCode/Claude CLI/Both)
- Remove skill/references/*.md (790 lines of duplication)
- SKILL.md now points directly to commands/conductor/*.toml
- install.sh creates symlinks to repo's commands/ and templates/
- Update README with interactive installer options

This ensures zero duplication - the skill references the original
TOML files and templates, and updates automatically with git pull.
The original TOML protocols reference Gemini CLI commands like
/conductor:implement. Added rule to instruct the agent to use
agnostic language instead (e.g., 'ask me to implement').
Copilot AI and others added 3 commits January 11, 2026 10:09
- Add Universal File Resolution Protocol to GEMINI.md
- Update setup.toml to create conductor/index.md with project context links
- Update setup.toml to create track index.md files with track context links
- Update newTrack.toml to use Universal File Resolution Protocol
- Update newTrack.toml to create track index.md files
- Update implement.toml to use Universal File Resolution Protocol
- Update status.toml to use Universal File Resolution Protocol
- Update revert.toml to use Universal File Resolution Protocol
- Replace hardcoded file paths with abstract labels (Product Definition, Tech Stack, etc.)
- Implement tracks directory abstraction for flexible track organization

Co-authored-by: edithatogo <[email protected]>
feat: adopt Universal File Resolution Protocol from upstream
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants