# Multi Agent Orchestrator

> Orchestrates complex multi-agent pipelines with DAG execution. Use for: orchestrate agents, agent pipeline, multi step agents, `multi-agent-coordinator`.

- Skill: `stijnman/multi-agent-orchestrator` (Agent Skill)
- Install (CLI): `npx skillmds@latest add stijnman/multi-agent-orchestrator`
- Raw SKILL.md: https://api.skillmd.com/api/skills/stijnman/multi-agent-orchestrator/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- License: MIT
- Author: Stijnman (https://skillmd.com/u/stijnman)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/stijnman/multi-agent-orchestrator

---

# Multi Agent Orchestrator
## When to Use

- User says **orchestrate agents** or task matches this capability
- User says **agent pipeline** or task matches this capability
- User says **multi step agents** or task matches this capability

## Workflow

1. Build task DAG via adaptive-workflow-composer.
2. Spawn agents per node with scoped context.
3. Execute topological order; parallelize independent nodes.
4. Aggregate; run self-refine-loop on final output.

## Integrations

- `multi-agent-coordinator`
- `parallel-tool-orchestrator`
- `self-refine-loop`

## Error Handling

| Failure | Response |
|---------|----------|
| DAG cycle | Break cycle; serialize conflicting nodes. |

## Gotchas

- Integrates self-refine-loop as skeptic reviewer agent.

## Example

**Input:** User request matching triggers above.
**Output:** Structured result per workflow with integrations invoked as needed.