piecuzwhynot

Dsh External Workers — Development skill for Claude Code

Development community

Give your DeepSeek Harness agent three more pairs of hands.

How to install Dsh External Workers

This entry records only its repository, not the path inside it, so there is no exact command to give. Open piecuzwhynot/dsh-external-workers and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Dsh External Workers does

Give your DeepSeek Harness agent three more pairs of hands. It sends long tasks to Claude Code, Codex and Antigravity using your own subscription logins, keeps one persistent session per lane, and never loses a job. 给 DeepSeek Harness 用的外部 agent 泳道：把长任务派给 Claude Code、Codex、Antigravity 三个 CLI，用你自己已有的订阅登录。每条泳道一个持久会话，作业重启和压缩都不会丢。

Alternatives in Development

Happy Coder — by GrocerPublishAgent - Spawn and control multiple Claude Codes in parallel from your phone or desktop 15.7k ★
Knowledge Work Plugins — Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork 9734 125 18 10.5k ★
Puppetmaster — Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory 340 ★

README

dsh-external-workers

**Persistent external agent workers for DeepSeek Harness.** Delegate long-running tasks to **Claude Code**, **Codex CLI** and **Antigravity CLI** — through their own official CLIs and your existing subscription logins — with jobs that survive a restart or a context compaction.

给 DeepSeek Harness 用的外部 agent 泳道：把长任务派给 Claude Code、Codex、Antigravity 三个 CLI，用你自己已有的订阅登录。每条泳道一个持久会话，作业重启和压缩都不会丢。

**English** | [中文](README.zh.md)

What it is

A native DeepSeek Harness (DSH) plugin. It adds six tools to your sessions, plus one `delegate_` per custom product you declare:

Tool	What it does
`delegate_claude`	Hand a task to the Claude Code worker
`delegate_gpt`	Hand a task to the Codex CLI worker
`delegate_google`	Hand a task to the Antigravity CLI (`agy`) worker
`check_external_job`	Read any job — status, result, artifacts, errors — from disk
`resume_external_job`	Continue a blocked/failed job in the same worker session
`worker_config`	List the real models each product offers, and manage its lanes (role + model + effort + speed)

**Plus a panel in the Web UI**: a row above the composer lists every job with its live status, and expands into a drawer with a **Lanes** tab (one card per lane: role, requested model, the model it last ran on, state, session, directory) and a **Jobs** tab (per-job detail: task, lane, worker session, artifacts, error, result preview). It renders **nothing at all** while there are no jobs, so a session that never delegates is untouched.

Each lane is an **independent, long-lived session** in its own product, in its own working directory (`~/.dsh/workers/`), with its own tools. One product can run several lanes — that is how `gpt` does quick edits on a fast model in one lane while a heavier model grinds through something long in another. Your DSH agent stays the orchestrator; the lanes do the work.