Team Agent Orchestration

SkillAI & models

Team-agent-orchestration is a skill that lets an agent manage several other agents like a team. It structures multi-agent work into items with owners, scopes, acceptance criteria, and merge gates, tracked on an agent Kanban board from backlog through merged. Each agent works on its own

Available today. Use it from your connected AI after setup.

Have the skill available to your agent so it can be activated for multi-agent work.

Then ask your AI: use the Team Agent Orchestration skill

What your AI can do with it

  • Shape fuzzy goals into work items with owners, scopes, and merge gates
  • Track agent work on a Kanban board: backlog, ready, running, review, blocked, merged, arch
  • Isolate each agent's work on its own branch or worktree
  • Record handoff evidence such as tests, diffs, logs, and review notes
  • Enforce merge gates before agent output is integrated into the mainline
  • Choose an execution mode: single-agent, dynamic workflow, dmux/tmux, worktree fan-out, or

Getting started

  1. Have the skill available to your agent so it can be activated for multi-agent work.
  2. Describe the task in terms that span multiple agents, branches, or worktrees, or mention team orchestration, agent Kanban, or squad coordination.
  3. Let the agent shape the board: convert the goal into work items with owners, scopes, acceptance criteria, and merge gates.
  4. Pick an execution mode such as single-agent, dynamic workflow, dmux/tmux, worktree fan-out, or an external desktop orchestrator.
  5. Review the control pane for progress and blockers, and confirm the integrator merges only work that passes its merge gate.

What this skill tells your AI

The instructions your AI receives, as published by affaan-m/ecc in skills/team-agent-orchestration/SKILL.md and read by ahel’s review.

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.

Operating Model

Treat every agent as a teammate with a narrow contract:

  • Owner: the person or agent accountable for the work item.
  • Scope: files, branch, tool surface, and forbidden areas.
  • State: backlog, ready, running, review, blocked, merged, or archived.
  • Evidence: tests, screenshots, logs, review notes, or eval reports.
  • Merge gate: the exact condition that allows integration.

Agent Kanban

Use agent Kanban when work must be visible across sessions.

ColumnMeaningExit Criteria
BacklogCandidate work item, not yet shapedAcceptance criteria written
ReadyShaped and assignableOwner and branch/worktree assigned
RunningAgent is actively workingHandoff artifact and changed files exist
ReviewWork is complete but not mergedTests, diff review, and risk check pass
BlockedNeeds external input or failed gateBlocker has owner and next action
MergedIntegrated into mainlinePR merged or local main updated
ArchivedNo longer relevantReason recorded

Each card should fit this schema:

{
  "id": "agent-card-001",
  "title": "Build dynamic workflow skill",
  "owner": "codex",
  "state": "running",
  "branch": "product/dynamic-workflow-team-orchestration",
  "worktree": ".",
  "acceptance": [
    "Skill exists",
    "Tests cover required concepts",
    "Content artifact contains video and article angles"
  ],
  "merge_gate": "lint, focused tests, and catalog check pass",
  "handoff": "path/to/handoff.md"
}

Team-Based Orchestration Flow

  1. Shape the board: convert fuzzy ambition into work items with owners and merge gates.
  2. Pick execution mode: single-agent, dynamic workflow mode, dmux/tmux, worktree fan-out, or external desktop orchestrator.
  3. Assign boundaries: one owner per card, clear file scope, and no overlapping writes without an integrator.
  4. Run agents: each agent writes evidence and handoff notes, not just code.
  5. Review in sequence: tests first, then diff review, then security/risk checks, then content/product polish.
  6. Merge deliberately: one integrator resolves conflicts and updates the control pane or status artifact.
  7. Extract reusable skill: if the card pattern repeats, promote it into skills/.

Control Pane Requirements

A useful control pane for team orchestration should show:

  • Active work items and their agent Kanban state.
  • Owner, harness, branch, worktree, and last heartbeat.
  • Links to handoff artifacts, tests, screenshots, and PRs.
  • Blockers grouped by owner and unblock action.
  • Merge readiness by gate, not vibes.
  • Reusable workflow candidates that should become shared skills.

Do not add more automation until the operator can answer: who owns this, what changed, what gate failed, and what can safely merge?

Dynamic Workflow Compatibility

When a card needs dynamic workflow mode:

  • Put the task-local harness under the card owner.
  • Store inputs and outputs on the card.
  • Require an eval before moving from Running to Review.
  • Promote the harness to a shared skill only after repeat use.

Failure Modes To Watch

  • Agent soup: many agents running, no owner or merge gate.
  • Invisible work: useful output exists only in a chat transcript.
  • Board theater: a Kanban board exists but cards have no acceptance criteria.
  • Overlapping writes: parallel agents edit the same files without worktrees.
  • No product artifact: the process produces docs but no runnable or publishable surface.

Output Standard

Finish each orchestration pass with:

  • Board/card changes.
  • Merged or pending branches.
  • Tests and eval evidence.
  • Blockers with owner and next action.
  • New shared skill candidates.

Signals

GitHub stars
268k
Forks
40k
Last commit
Sep 2026

Questions

When should this skill be used?
When a task spans multiple agents, tools, harnesses, branches, or worktrees, or when agent fan-out is producing output but not mergeable product and shared workflow state is needed.
What states does the agent Kanban board track?
Backlog, ready, running, review, blocked, merged, and archived, each with defined exit criteria such as written acceptance criteria, a handoff artifact, or a merged PR.
Advanced
Item type
skill
Key
team-agent-orchestration
Source
github.com/affaan-m/ecc