Catalog
affaan-m/team-agent-orchestration

affaan-m

team-agent-orchestration

Run team-based orchestration for agent squads: work items with owners and scope, agent Kanban state, branch isolation, control pane visibility, and merge gates. Use when coordinating multiple agents in parallel across branches or worktrees — multi-agent fan-out, agent Kanban, squad coordination, or merging agent output into one product.

NewUpdated Sep 27, 2026

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.

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.

Column Meaning Exit Criteria
Backlog Candidate work item, not yet shaped Acceptance criteria written
Ready Shaped and assignable Owner and branch/worktree assigned
Running Agent is actively working Handoff artifact and changed files exist
Review Work is complete but not merged Tests, diff review, and risk check pass
Blocked Needs external input or failed gate Blocker has owner and next action
Merged Integrated into mainline PR merged or local main updated
Archived No longer relevant Reason 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.
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

84/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

82

Clarity

83

Completeness

79

Summary

A framework for coordinating multiple agents working in parallel across branches or worktrees. It defines team-based orchestration patterns including agent Kanban state management, work item ownership, scope boundaries, merge gates, and control pane visibility. The skill is procedural rather than operational—it teaches HOW to organize agent work, not what code to generate.

Detected Capabilities

team workflow coordinationstate management documentationmerge gate definitionagent handoff artifact creationcontrol pane design guidance

Trigger Keywords

Phrases that agents use to match this skill to user intent.

multi-agent orchestrationteam workflow stateagent Kanban boardsquad coordinationmerge gate definitionagent handoffworktree fan-outcontrol pane setup

Use Cases

  • Coordinate multiple agents working on separate branches or worktrees
  • Track agent progress using Kanban state across team sessions
  • Define and enforce merge gates before integrating agent outputs
  • Manage overlapping work through explicit ownership and scope boundaries
  • Establish shared workflow state visible to both agents and operators
  • Promote repeated orchestration patterns into reusable skills

Quality Notes

  • Clear operating model with explicit roles (owner, scope, state, evidence, merge gate)
  • Well-structured Kanban schema with specific column definitions and exit criteria
  • Practical JSON card schema shows concrete data structure agents should maintain
  • Proactive identification of failure modes (agent soup, invisible work, board theater) helps teams avoid anti-patterns
  • Comprehensive control pane requirements guide operator visibility without over-automation
  • Explicit guidance on dynamic workflow compatibility and when to promote patterns into skills
  • No file writes or shell execution—purely advisory and procedural, making it safe for any team context
  • Scope boundaries clearly defined (owners, branches, worktrees, forbidden areas)
  • Output standards specify what 'done' looks like (board changes, merged branches, evidence, blockers, skill candidates)
Model: claude-haiku-4-5-20251001Analyzed: Sep 27, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v3.0

    Contract changed: description

    ✦ AIDescription refined to emphasize parallel multi-agent work across branches and fan-out patterns, with explicit merge-gate coordination language.

    triggering2026-09-27

    LATEST
  2. v2.0

    Contract changed: description

    ✦ AISkill description expanded to clarify activation context for agent squad coordination.

    triggering2026-09-09

    View This Version
  3. v1.1

    Content updated

    ✦ AISKILL.md content unchanged; safety grade moved A → B.

    2026-07-14

    View This Version
  4. v1.0

    2026-06-04

    View This VersionInitial version

Use affaan-m/team-agent-orchestration in your dev environment

Command Palette

Search for a command to run...