minion-orchestrator

Orchestrate durable background tasks and LLM subagent workflows in a Postgres-native job queue.

45|11|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/beyonai/ByClaw --skill minion-orchestrator-beyonai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: minion-orchestrator
Source: https://github.com/beyonai/ByClaw/tree/main/middleware/openclaw/skills/gbrain/references/minion-orchestrator
Command: npx skills add https://github.com/beyonai/ByClaw --skill minion-orchestrator-beyonai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill solves the challenge of managing long-running, complex, or parallel tasks that require durability across system restarts and observability for enterprise-grade workflows.

Core Features & Use Cases

  • Unified Job Queue: Manages both deterministic shell scripts and LLM-driven subagent reasoning loops in a single, Postgres-backed interface.
  • Steerable Execution: Allows real-time intervention, pausing, resuming, and message-based steering of running agents.
  • Use Case: Use this to spawn a complex research subagent that performs parallel web searches and data synthesis, while maintaining the ability to pause or redirect the agent mid-flight if the research direction changes.

Quick Start

Submit a new background subagent job to research the latest market trends for the specified company by invoking the gbrain agent run command.

Frequently Asked Questions about minion-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I orchestrate long-running LLM subagent workflows that survive system restarts?

You can orchestrate durable background tasks and LLM subagent workflows within a Postgres-native job queue. This provides persistent state management, ensuring complex multi-step reasoning agents survive system restarts.

Can I pause or redirect a running background agent mid-flight?

Yes, steerable execution allows real-time intervention for running agents. You can pause, resume, or redirect a background agent mid-flight using message-based steering if the research direction changes.

What's the best way to manage deterministic shell scripts and LLM-driven reasoning loops together?

Using a unified job queue backed by Postgres allows you to manage both deterministic shell command execution and complex LLM-driven subagent reasoning loops within a single, native interface.

Does background job orchestration support fan-out capabilities for parallel web searches?

Yes, background job orchestration supports fan-out capabilities for complex multi-step reasoning agents. This allows you to spawn a research subagent that performs parallel web searches and data synthesis.

Why do I need a Postgres-native job queue for enterprise automation?

A Postgres-native job queue provides durable state management, progress tracking, and observability for enterprise-grade automation. This ensures long-running, parallel tasks maintain durability and tracking across complex workflows.

How do I track progress for background tasks and subagent workflows?

The orchestration interface provides persistent state management and progress tracking for both deterministic shell scripts and LLM subagent workflows. This ensures full observability for enterprise-grade background jobs.