Team Agent Orchestration

This is orchestration infrastructure for running multiple agents as an actual team with work items, ownership, and merge gates instead of just spawning a bunch of assistants and hoping for the best. You get agent Kanban (backlog, ready, running, review, blocked, merged), explicit acceptance criteria per card, branch or worktree isolation, and a control pane that shows who owns what and which gates failed. Use it when you're coordinating agents across branches or tools and need to avoid agent soup where useful output exists only in chat transcripts. The merge gate concept is the key piece: every work item declares the exact condition that allows integration, so you're merging by evidence instead of vibes.

skills.sh installs: 5.1K
GitHub stars: 300.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add affaan-m/ecc --skill team-agent-orchestration --agent claude-code

Installs into .claude/skills of the current project.

Files

Team Agent Orchestration

Use this skill when agents are being managed like a team rather than a single assistant. The purpose is to make team-based orchestration reliable: clear work items, explicit ownership, agent Kanban state, branch isolation, control pane visibility, and merge gates.

When To Activate

The task spans multiple agents, tools, harnesses, branches, or worktrees.
The user mentions team orchestration, agent Kanban, squad, conductor, control pane, manager, desktop app, Zellij, tmux, Hermes, Devin, Codex, Claude Code, or multi-agent work.
A project needs shared workflow state across people and agents.
Existing agent fan-out is producing output but not mergeable product.