dsh-octo

English | 简体中文

Deepseek Harness (dsh) natively supports headless invocation of Claude Code and Codex as subagents through its built-in subagent backends, and these subagents can reuse the local account login state and the coding plans that come with the accounts. For example, if you have a Claude Code Max plan, you can have dsh call Fable-5 as a subagent.

Inspired by this, I designed this skill specifically for dsh, with these ideas in mind:

• Use built-in capabilities wherever possible for the most seamless invocation of heterogeneous subagents.
• Make dsh aware that it can call subagents, so it can aggregate multiple agents into greater intelligence.
• Design dedicated multi-agent workflows for different stages—such as planning, coding, and acceptance—to achieve high-quality collaboration.

Prerequisites

• dsh 0.1.0-rc.6.
• A deepseek-official provider configured for the main dsh model.
• Node.js, npm, and a pnpm environment available to dsh plugin.
• Claude Code and Codex installed and signed in locally, with active coding-plan subscriptions on the corresponding accounts.

Install

dsh-octo currently targets dsh 0.1.0-rc.6. Install it from a local tarball so dsh can resolve the bundle and all of its dependencies:

git clone https://github.com/tokentopo-ai/dsh-octo.git
cd dsh-octo
npm pack
dsh plugin --profile web add ./dsh-octo-0.1.0.tgz

Replace web with the profile you use, then restart it.

Once installed, use dsh exactly as usual: describe your task in normal conversation. No trigger phrase, subagent selection, or stage-by-stage command is required. The skill starts multi-agent collaboration only when it is useful.

How It Works

dsh-octo is installed as a static Cordis bundle. The bundle adds the packaged skill and the official heterogeneous subagent integrations to the selected dsh profile, while the skill decides when collaboration is appropriate and guides the main agent through it. There is no separate workflow engine for users to configure or operate.

For complex tasks, the main agent coordinates specialized subagents across the relevant stages and records their handoffs in project files so the work remains inspectable. Simple tasks stay on the main path, and unavailable subagents fall back to the main agent instead of blocking the task. Authentication remains owned by each official backend and is never copied into this project.

License

This project is currently distributed as UNLICENSED; no open-source license is granted.