ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified

Agent Orchestrator Template

A skill for main agents that need bounded delegation, safe parallel dispatch, and independent acceptance across multiple specialists.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/cjke84/agent-orchestrator-template
Or

Agent 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:

  1. Classify the request
  2. Decide whether to keep it local or dispatch it
  3. Send a bounded task contract to the right sub-agent
  4. Coordinate parallel work only when safe
  5. 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 + DomainOpenClaw AgentNotes
explore + codecodexUse for bounded codebase investigation and root-cause analysis.
implement + codecodexDefault coding path. Main agent still owns acceptance.
verify + codemain first, codex only if neededKeep final verification local unless a bounded reviewer pass is useful.
operate + knowledgeknowledgeArchiving, note organization, knowledge-base updates.
explore + knowledgeknowledgeSearch, retrieval, note inspection, archive lookup.
implement + contentcontentDrafting, rewriting, title/outline/content generation.
operate + communitycommunityPosting, replying, engagement, community-side actions.
explore + investinvestMarket/stock/fundamental analysis.
operate + investinvestWatchlist, simulated trading, structured finance workflows.
ambiguous or tightly coupled workmainKeep local until boundaries are explicit.

Orchestration Lifecycle

Metadata

Author@cjke84
Stars3562
Views0
Updated2026-03-29
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-cjke84-agent-orchestrator-template": {
      "enabled": true,
      "auto_update": true
    }
  }
}
Safety NoteClawKit audits metadata but not runtime behavior. Use with caution.