Verified:GitHub

houmao-agent-loop-pairwise-v3

Author and initialize workspace-aware enriched tree loops with lifecycle controls.

18|3|Updated Mar 5, 2026

Search Tags:#ai agents #orchestration #loop control #mailbox gateway #routing packets #workspace planning #managed memory

Ready to run

npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise-v3

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: houmao-agent-loop-pairwise-v3
Source: https://github.com/igamenovoer/houmao/tree/main/src/houmao/agents/assets/system_skills/legacy/houmao-agent-loop-pairwise-v3
Command: npx skills add https://github.com/igamenovoer/houmao --skill houmao-agent-loop-pairwise-v3

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Houmao Agent Loop Tree V3 turns a user-requested, workspace-aware multi-agent “tree loop” workflow into durable, structured artifacts and then lets you reliably initialize and operate the run with explicit lifecycle controls.

Core Features & Use Cases

Workspace-aware loop planning: authors a workspace contract and a control plan with a canonical output directory layout.
Deterministic prestart initialization: validates routing packets (when present), verifies/enables gateway mail-notifier posture, and writes run-owned durable memo blocks via managed memory routing.
Operational run control: supports manual lifecycle actions including plan, initialize, start, peek, ping, pause, resume, recover_and_continue, stop, and hard-kill with explicit guardrails and fail-closed behavior.
Legacy-safe evolution: extends v2 behaviors without mutating the stable v2 or other related stable skills.

Quick Start

Ask for houmao-agent-loop-pairwise-v3 with a required plan output directory, then request plan and initialize for a workspace-aware enriched tree loop before starting.

Frequently Asked Questions about houmao-agent-loop-pairwise-v3

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

FAQPage Schema

How do I plan and initialize a workspace-aware multi-agent tree loop?▼

To initialize a workspace-aware multi-agent tree loop, you must author a deterministic plan artifact with a canonical output directory, verify mailbox gateway posture, and write run-owned memo blocks before issuing a controlled start command.

What is the best way to control AI agent orchestration loops during execution?▼

You can control AI agent orchestration loops using manual lifecycle actions such as peek, ping, pause, resume, recover_and_continue, stop, and hard-kill, all governed by explicit guardrails and fail-closed behavior checks.

Can I use this workflow without email or mailbox gateway capabilities enabled?▼

No, you cannot use this workflow without email or mailbox capabilities because the system enforces fail-closed checks for email mailbox capability and required participants before initializing the routing packet structure.

How does routing packet validation work for multi-agent messaging?▼

Routing packet validation for multi-agent messaging checks packet coverage manually or automatically, routing messaging and gateway responsibilities through owning skills while keeping runtime recovery state outside the authored workspace contract.

Does this skill mutate or break previous version agent loop behaviors?▼

No, this skill does not mutate previous version behaviors because it extends v2 behaviors safely without mutating the stable v2 skill or other related stable skills in your environment.