Skip to content
Get packs

Orchestration Team Coordinator

Lets an agent coordinate a multi-agent team: dispatch assignments, watch for blocked or idle agents, and intervene economically.

Source Download skill
Repository
mvschwarz/openrig
Stars
8,553
Licence
Apache-2.0
Files
1 file

What it does

This skill tells an AI agent to act as the coordinator of a team of other AI agents working on a shared project, rather than doing the implementation itself. The agent reads its project, mission and slice context, breaks work into assignments, dispatches them, and watches the queue for agents that finished without handing off or got stuck. It is designed to keep monitoring light: it prefers reading status from a queue and a periodic watchdog wake over constantly polling every agent, and it corrects a stalled agent by teaching the handoff protocol rather than silently doing that agent's work.

Great for

  • Developers running OpenRig multi-agent rigs who want an orchestrator agent to route work between seats
  • Teams experimenting with coordinator/worker agent patterns who want a documented monitoring discipline

Skip it if

  • Single-agent workflows or simple one-off tasks, where there is no team to coordinate and the skill adds overhead
  • Anyone without the OpenRig CLI (rig commands) installed, since the instructions depend on rig whoami, rig queue and rig ps
  • Users expecting a general-purpose project manager: the skill assumes a specific queue-based handoff protocol defined elsewhere

Try asking

  • “Coordinate the next assignments for our rig after the implementation agent finished its slice”
  • “Check which agents in this rig are idle without handing off their queue items and nudge them”
  • “Set up a watchdog-driven monitoring loop for the QA and review seats and only intervene on blocked work”
Step-by-step guide: how to use Orchestration Team CoordinatorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    orchestration-team.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip orchestration-team.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip orchestration-team.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Install it only inside an OpenRig rig; outside that environment the rig commands and referenced docs will not resolve
  • Keep the watchdog interval and filters narrow as written, since the skill warns against broad fleet-wide JSON dumps that waste tokens
  • Review the referenced docs (product-journey-sdlc.md) before relying on the lookup precedence rules, because this file alone is only part of the protocol

What's inside

  • SKILL.md

Redistributed unmodified from mvschwarz/openrig under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.