Verified:GitHub

houmao-agent-loop-pairwise

Convert explicit user intent into a master-owned Houmao tree loop plan and control run start, status, and stop.

18|3|Updated Mar 5, 2026

Search Tags:#agent orchestration #run control #tree loop planning #mailbox messaging #Mermaid control graph #supervision loop

Ready to run

npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: houmao-agent-loop-pairwise
Source: https://github.com/igamenovoer/houmao/tree/main/src/houmao/agents/assets/system_skills/legacy/houmao-agent-loop-pairwise
Command: npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

It prevents ad-hoc, ambiguous orchestration by converting explicit user intent into a single, master-owned tree loop plan and then running start/status/stop control for that run.

Core Features & Use Cases

Manual-invocation-only tree loop authoring: Turns a user request for houmao-agent-loop-pairwise into a normalized, composed tree loop topology owned by the designated master.
Run-control for a maintained accepted plan: Operates exactly one loop run through start, status, and stop without placing the user agent inside the execution loop.
Graph-structured control visibility: Produces the final Mermaid control graph showing supervision, immediate driver-worker edges, completion evaluation, and stop evaluation.

Quick Start

Ask your AI to use the houmao-agent-loop-pairwise skill to formulate a master-owned tree loop plan and then start the run.

Frequently Asked Questions about houmao-agent-loop-pairwise

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

FAQPage Schema

How do I convert explicit user intent into a normalized tree loop plan for agent orchestration?▼

Agent orchestration converts explicit user intent into a master-owned tree loop plan by normalizing the topology and composing immediate driver-worker edges, ensuring the user agent remains outside the execution loop.

How do I manage run control for a tree loop plan without placing the user agent in the execution loop?▼

Run control manages a maintained accepted plan by executing start, status, and stop operations through a two-plane control and execution split, keeping the user agent entirely outside the active execution loop.

How does supervision loop planning handle mailbox messaging and gateway routing?▼

Supervision loop planning routes mailbox messaging, gateway semantics, and follow-up actions through appropriate sub-skills, while composing driver-worker edges via local-close edge guidance to maintain structured control.

Can I visualize agent orchestration control graphs using Mermaid for tree loop supervision?▼

Mermaid control graphs visualize tree loop supervision by mapping immediate driver-worker edges, completion evaluation, and stop evaluation, providing clear graph-structured control visibility for the orchestrated run.

What is the best way to enforce a two-plane control and execution split for agent run control?▼

A two-plane control and execution split enforces structured agent run control by separating the normalized master-owned plan topology from execution, preventing ad-hoc orchestration and ambiguous command routing.

When should I not use manual-invocation-only tree loop authoring for agent supervision?▼

Manual-invocation-only tree loop authoring should not be used for implicit intent or multi-plan execution, as it strictly operates exactly one accepted run when the user explicitly requests a single master-owned plan.