Agent Orchestrator Template
A skill for main agents that need bounded delegation, safe parallel dispatch, and independent acceptance across multiple specialists.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/cjke84/agent-orchestrator-templateAgent Orchestrator Template
A framework for main agents that coordinate specialized sub-agents instead of trying to execute every part of a task alone.
Core Philosophy
The main agent is an orchestrator, not a dump pipe.
Its job is to:
- Classify the request
- Decide whether to keep it local or dispatch it
- Send a bounded task contract to the right sub-agent
- Coordinate parallel work only when safe
- Verify outputs before presenting one clean answer
Sub-agents execute scoped work. The main agent owns correctness.
OpenClaw Local Compatibility
This skill is written to fit the current local OpenClaw profile instead of overriding it.
Respect these existing limits:
- Allowed sub-agents:
codex,invest,content,knowledge,community - ACP dispatch: enabled
- Default ACP agent:
codex - Maximum concurrent sub-agents:
2
Do not invent agent ids that are not already allowed by the local OpenClaw config. If a task does not clearly map to one of the allowed agents, keep it local.
If you need more agent kinds than the local five, extend the registry at the routing config level instead of altering this skill’s description. The agents block now supported in the routing schema lets you declare agent metadata (id, description, capabilities) and refer to those ids via preferred_agent/fallback_agent. The current OpenClaw profile in references/openclaw-playbook.md is a runnable example, but you can register additional agents (ops-specialist, researcher, etc.) in examples/custom-agent-registry.yaml without touching the local workspace constraints.
OpenClaw Routing Map
Use these mappings before introducing any custom routing logic:
| Task Type + Domain | OpenClaw Agent | Notes |
|---|---|---|
explore + code | codex | Use for bounded codebase investigation and root-cause analysis. |
implement + code | codex | Default coding path. Main agent still owns acceptance. |
verify + code | main first, codex only if needed | Keep final verification local unless a bounded reviewer pass is useful. |
operate + knowledge | knowledge | Archiving, note organization, knowledge-base updates. |
explore + knowledge | knowledge | Search, retrieval, note inspection, archive lookup. |
implement + content | content | Drafting, rewriting, title/outline/content generation. |
operate + community | community | Posting, replying, engagement, community-side actions. |
explore + invest | invest | Market/stock/fundamental analysis. |
operate + invest | invest | Watchlist, simulated trading, structured finance workflows. |
| ambiguous or tightly coupled work | main | Keep local until boundaries are explicit. |
Orchestration Lifecycle
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-cjke84-agent-orchestrator-template": {
"enabled": true,
"auto_update": true
}
}
}Related Skills
memory-system
Use when setting up or improving an agent memory workflow for OpenClaw, Codex, or Obsidian with MEMORY.md, daily notes, session recovery, and optional OpenViking support.
obsidian-knowledge-organizer
An OpenClaw- and Codex-compatible Obsidian knowledge organization skill for importing articles, organizing notes, applying tags, archiving content, generating summaries, and suggesting related notes.
knowledge-organizer
Use when importing articles, organizing notes, or syncing a knowledge base across Obsidian, Feishu, and Tencent IMA with OpenClaw or Codex.
SkillUp
SkillUp is a cross-platform skill publishing tool for packaging and syncing custom skills to GitHub, Xiaping Skill, OpenClaw CN, and ClawHub.