
Team Agent Orchestration
- 1.1k installs
- 238k repo stars
- Updated August 5, 2026
- affaan-m/everything-claude-code
team-agent-orchestration is a Claude Code skill for running agent squads as a team with owned work items, an agent Kanban, branch isolation, and merge gates.
About
team-agent-orchestration is a Claude Code skill for running team-based orchestration across agent squads instead of a single assistant. It structures work into work items with explicit ownership, an agent Kanban with defined columns and exit criteria, branch and worktree isolation, control-pane visibility, and merge gates. Each card follows a JSON schema with owner, state, branch, acceptance criteria, and merge gate. Developers use it when a task spans multiple agents, harnesses, branches, or worktrees and existing fan-out produces output but not mergeable product.
- Team-based orchestration for agent squads: work items, ownership, agent Kanban, merge gates, control pane
- Seven-column agent Kanban (Backlog to Archived) with a per-card JSON schema and exit criteria
- Names failure modes: agent soup, invisible work, board theater, overlapping writes, no product artifact
Team Agent Orchestration by the numbers
- 1,111 all-time installs (skills.sh)
- +251 installs in the week ending Aug 4, 2026 (Skillselion tracking)
- Ranked #970 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
team-agent-orchestration capabilities & compatibility
- Capabilities
- orchestration · project management · code review
- Works with
- github
- Use cases
- orchestration · project management
What team-agent-orchestration says it does
Use this skill when agents are being managed like a team rather than a single assistant.
**Agent soup**: many agents running, no owner or merge gate.
Merge readiness by gate, not vibes.
npx skills add https://github.com/affaan-m/everything-claude-code --skill team-agent-orchestrationAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1.1k |
|---|---|
| repo stars | ★ 238k |
| Last updated | August 5, 2026 |
| Repository | affaan-m/everything-claude-code ↗ |
What it does
Coordinate multiple agents as a team with owned work items, an agent Kanban, branch/worktree isolation, and merge gates so fan-out produces mergeable product.
Who is it for?
Multi-agent, multi-branch or multi-worktree work where fan-out must turn into mergeable product.
Skip if: Single-agent tasks or work that fits in one assistant session with no shared board.
When should I use this skill?
A task spans multiple agents, tools, harnesses, branches, or worktrees, or agent fan-out produces output but not mergeable product.
What you get
A visible board of owned work items with merge gates that turns parallel agents into merged product.
- agent Kanban board
- work-item cards
- merge-readiness report
By the numbers
- seven Kanban columns
- seven-step orchestration flow
- five failure modes
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.
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.
Related skills
FAQ
When should I use this over single-agent work?
When the task spans multiple agents, harnesses, branches, or worktrees, or fan-out is producing output but not mergeable product.
What does a card contain?
A JSON schema with id, title, owner, state, branch, worktree, acceptance criteria, merge_gate, and handoff path.