# Orchestrate > Plan and execute multi-agent work — decompose features, spawn workers, monitor progress Use when this capability is needed. - Skill: `tomevault-io/orchestrate-3` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/orchestrate-3` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/orchestrate-3/raw - Safety review: pending (external: skill-scanner PASS, skillspector PASS) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/orchestrate-3 --- Use AgentOS orchestrator to break down complex tasks: 1. Plan: `curl -X POST http://localhost:3111/api/orchestrator/plan -H 'Content-Type: application/json' -d '{"description": ""}'` 2. Execute: `curl -X POST http://localhost:3111/api/orchestrator/execute -H 'Content-Type: application/json' -d '{"planId": ""}'` 3. Status: `curl -X POST http://localhost:3111/api/orchestrator/status -H 'Content-Type: application/json' -d '{"planId": ""}'` The orchestrator decomposes tasks into subtasks with hierarchical IDs, spawns workers for each leaf task, and monitors progress with lifecycle reactions. --- > Source: [iii-experimental/agentos](https://github.com/iii-experimental/agentos) — distributed by [TomeVault](https://tomevault.io).