openclaw-agent-orchestrator

Create and repair durable OpenClaw agents, bindings, and runtime state. Use when the user wants real subagents, durable agent entries, or proof that orchestration actions actually changed live state. Prefer verified `openclaw agents add` flows over optimistic `sessions_spawn` narration.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "openclaw-agent-orchestrator" with this command: npx skills add matthewxmurphy/openclaw-agent-orchestrator

OpenClaw Agent Orchestrator

Use this skill when the user wants real subagents or when the runtime claims it started agents but openclaw agents list and openclaw agents bindings do not show them.

Durable Agent Rule

For durable subagents in this deployment, use openclaw agents add and verify the result.

Do not use sessions_spawn with mode="session" for durable agent creation here. This runtime has already returned errors such as:

  • mode="session" requires thread=true
  • thread=true is unavailable because no channel plugin registered subagent_spawning hooks

Treat sessions_spawn as ephemeral-only unless the current runtime explicitly proves thread-bound session support.

Workflow

  1. Run scripts/verify-runtime.sh to see the current truth.
  2. If the requested durable agent does not exist, run scripts/create-agent.sh <agent-id> <name> <emoji> [theme].
  3. If the user asked for routing, add bindings with openclaw agents bind.
  4. Re-run scripts/verify-runtime.sh.
  5. Report only what is present in verified runtime output.

Guardrails

  • Never say an agent was created until openclaw agents list --json shows it.
  • Never claim bindings exist until openclaw agents bindings --json shows them.
  • Do not use crontab in this environment. Use openclaw cron ... only if a schedule is actually needed.
  • Do not say GO, starting now, or spawned successfully before a verified state change.

Commands

Verify:

./scripts/verify-runtime.sh

Create one durable agent:

./scripts/create-agent.sh oracle "Oracle" "🔮" "qa"

Create one durable agent from a copied workspace and verify:

./scripts/create-agent.sh trinity "Trinity" "🥷" "ops"
./scripts/verify-runtime.sh

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

Self-Improving Compound

Capture durable lessons from debugging, user corrections, missing capabilities, and repeated workflow friction so future sessions avoid the same mistakes. Hy...

Registry SourceRecently Updated
Automation

Agent Anchor

Agent Anchor is a crash-proof dashboard for OpenClaw that continuously saves your AI agent's state, enabling seamless recovery and task tracking after interr...

Registry SourceRecently Updated
Automation

Meyo Community

觅游社区(meyo123.com)AI Agent 社区操作技能。发帖、查互动、成长日记、查询技能市场。当用户需要操作觅游社区时使用此技能。触发词:觅游、meyo、发帖到社区、觅游社区、社区互动、成长日记。

Registry SourceRecently Updated
Automation

Yahoo Mail IMAP Export

Export large Yahoo Mail archives with the folder-rotation IMAP workflow, resumable downloads, and safe delete-after-verify handling.

Registry SourceRecently Updated