双手互搏
Two hands spar over every change. Only real decisions reach you.

_简体中文

Zhou Botong is one of wuxia's great eccentrics: a legendary martial artist with the temperament of a mischievous child. When ordinary practice becomes too ordinary, he invents something delightfully absurd — the Technique of Ambidexterity (双手互搏).

He teaches each hand to act independently. One hand attacks; the other answers. Each uses a different martial art. The same person becomes both opponents, and the sparring continues until neither hand can surprise the other.

It sounds like a party trick. It is actually a discipline: split creation from criticism, give both sides room to think, and let disagreement expose what either side would miss alone.

Hubo puts that little duel inside your coding agent.

The name comes from 互搏 (hùbó): to spar with each other. Not two agents politely taking turns, and not a reviewer saying “looks good” from the doorway. Two hands spar over every change. Only real decisions reach you. They exchange evidence until the code — not either agent's ego — wins.

Without Hubo, an agent implements the feature, runs a test, reviews its own reasoning, and hands the result to you. The author, tester, and reviewer all share the same blind spots.

With Hubo:

your task
   ↓
work agent ── implementation + evidence ──▶ review agent
     ▲                                      │
     └──── fix or reasoned pushback ◀───────┘
                      repeat
                         ↓
              reconciled result — or you

You see the work only after every concrete finding is resolved, unless the remaining question genuinely requires your judgment.

Hubo has two explicit modes:

Both modes keep two persistent roles in the same conversation and use the same shape: produce, challenge, revise or defend, repeat.

The default mode keeps these roles:

The loop ends when:

• the reviewer clears the work and every finding is reconciled; or
• the agents identify a product, requirement, or technical-direction decision that only you can make.

The reviewer may spawn specialists. The worker may delegate implementation. But at the top level the shape remains the same: one hand makes, one hand tests the making.

Both modes require explicit invocation in their trigger instructions; ordinary coding prompts remain ordinary. Codex also enforces this through plugin policy.

Works with

OpenClaw

Claude Code

Codex

OpenCode

Bash

GitHub Copilot CLI

Run these as two separate prompts:

/plugin marketplace add h0ngcha0/hubo

/plugin install hubo@hubo

Then run /reload-plugins or start a new conversation.

codex plugin marketplace add h0ngcha0/hubo
codex plugin add hubo@hubo

Restart Codex and start a new conversation so the skill is discovered.

copilot plugin marketplace add h0ngcha0/hubo
copilot plugin install hubo@hubo

Start a new Copilot CLI session after installing.

openclaw plugins install hubo --marketplace h0ngcha0/hubo

Restart the OpenClaw gateway after installing.

npx skills add h0ngcha0/hubo --skill hubo hubo-review --agent opencode -g -y

Start a new OpenCode session after installing.

Install both Hubo skills directly into any supported host:

npx skills add h0ngcha0/hubo --skill hubo hubo-review -g

• Claude Code: /hubo (or /hubo:hubo) and /hubo:hubo-review.
• Codex CLI: $hubo:hubo and $hubo:hubo-review.
• ChatGPT or Codex desktop: type @, then select Hubo or Hubo Review.
• GitHub Copilot CLI: /hubo:hubo and /hubo:hubo-review.
• OpenClaw: /skill hubo and /skill hubo-review.

• Claude Code or GitHub Copilot CLI: /hubo and /hubo-review.
• Codex: $hubo and $hubo-review.
• OpenCode: /hubo and /hubo-review; use /skills to open the skill picker.
• OpenClaw: /skill hubo and /skill hubo-review.

For example:

/hubo implement optimistic updates for the cart
/hubo:hubo-review review the authentication changes on this branch

MIT © 2026 h0ngcha0