coordinator-dx

stars-end's avatarfrom stars-end

Coordinator playbook for running multi‑repo, multi‑VM work in parallel without relying on humans copy/pasting long checklists.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 10, 2026
[Tool Routing and Orchestration]

When & Why to Use This Skill

The coordinator-dx skill is a sophisticated orchestration playbook designed to manage complex, multi-repository, and multi-VM workflows in parallel. It eliminates manual overhead by automating the coordination of multiple AI agents, ensuring environment consistency through standardized health checks (dx_doctor.sh), and preventing task collisions. This tool is essential for scaling developer operations (DevOps) and improving developer experience (DX) in agentic environments.

Use Cases

  • Parallel Multi-Repo Management: Coordinating simultaneous updates, refactors, or feature implementations across multiple distinct codebases without human intervention.
  • Automated Environment Verification: Running automated health checks across various virtual machines (e.g., MacMini, WSL, EPYC) to ensure all agents are correctly configured before starting tasks.
  • Agent Collision Prevention: Implementing a 'one repo per VM' policy and automated reporting to prevent git conflicts and resource overlaps in distributed development teams.
  • Checklist Automation: Codifying repetitive manual procedures into automated playbooks, reducing the risk of human error during complex deployment or maintenance cycles.
namecoordinator-dx
descriptionCoordinator playbook for running multi‑repo, multi‑VM work in parallel without relying on humans copy/pasting long checklists.

coordinator-dx

Coordinator playbook for running multi‑repo, multi‑VM work in parallel without relying on humans copy/pasting long checklists.

Key conventions:

  • Each VM/agent sets AGENT_NAME=<vm>-<tool> (e.g. macmini-codex, epyc6-claude-code, homedesktop-wsl-gemini)
  • For in-repo coordination, thread_id should equal the repo’s local Beads issue id (no cross-repo renames).
  • Always start a session with bash scripts/cli/dx_doctor.sh and follow the warnings (soft, advisory).

Recommended coordinator flow:

  1. Assign work by repo (prime-radiant-ai / affordabot / llm-common / agent-skills).
  2. Require agents to report:
    • git status --porcelain
    • git branch --show-current
    • output of bash scripts/cli/dx_doctor.sh
  3. Prevent collisions:
    • one repo per VM by default
    • prefer small PRs
  4. Enforce “automation not checklists”:
    • if a step is repeated, codify it in dx_doctor.sh or shared skills.