DeepSeek Harness plugin

dsh-subagent-pool

DSH named-subagent pool: maintain a library of reusable subagents (model, reasoning effort, agent preset) on a settings page and call them by name with subagent_run

Jump to install

Source facts

Repository
xiagaogaozi/dsh-subagent-pool
Latest update
Aug 19, 2026
Category
Workflow & Automation
GitHub stars
0
Format
plugin
Catalog evidence
Upstream dsh.bundle evidence
Evidence path
package.json#dsh.bundle
Checked against
0.1.0-rc.8
Upstream check date
2026-08-20

This evidence comes from the upstream catalog. This site has not installed, run, or security-reviewed the plugin.

Install

Start with a prompt that asks an agent to review the GitHub repository and source. Switch to the command if you want to install it yourself.

Copy this prompt into DSH, Codex, or another agent and ask it to review the GitHub repository and source first.

Do not install or run any commands yet. Read this plugin's GitHub repository, README, and relevant source code. Then answer the questions below clearly and directly so I can decide whether it fits my needs:

1. What is this plugin, and what problem does it solve?
2. Who is it for, and what are its typical use cases?
3. How is it used after installation? Include one minimal example.
4. What known limitations or privacy, security, compatibility, or maintenance risks does it have?
5. Give a clear recommendation: recommend, conditionally recommend, or do not recommend, with reasons.

Distinguish statements documented by the repository, inferences from source code, and unknowns. If evidence is insufficient, say so explicitly. Do not guess or simply repeat the README.

GitHub: https://github.com/xiagaogaozi/dsh-subagent-pool
Plugin: dsh-subagent-pool
Author: xiagaogaozi

Check the source files

Read the README and other files from this plugin directory before installing.

File explorer2 files
README.mdSource · read only

dsh-subagent-pool

DeepSeek Harness 的命名子代理池插件:在设置页「子代理」维护一批可复用的子代理(每个 = 名字 + 描述 + 模型 + 推理等级 + 预设),主代理在对话中按描述判断"什么时候用谁",用 subagent_run(name, task) 按名字调用——模型/推理等级/预设自动套用,调用即干活返回结果。

<img width="863" height="870" alt="image" src="https://github.com/user-attachments/assets/781e3000-ad8c-44ee-9abc-da7885b1a398" />

安装

dsh plugin --profile web add "file:local-plugins/<path>/<tarball>.tgz"

(或按部署习惯的本地 tarball 流程安装;插件含 host 与 client 两部分,装完重启 dsh。)

使用

1. 设置 → 子代理 → 添加(名字/描述/模型/推理等级/预设)→ 保存 2. 主代理的系统提示里会出现子代理目录({{subagent_pool}} 变量) 3. 需要时调用:subagent_run(name="林晚", task="……")

配置项语义

字段说明
名称唯一模板名,subagent_run 按它查找
描述发给主代理:什么时候才调用(调度契约)
模型子代理模型覆盖(provider/model),空 = 跟随主代理
推理等级off / high / max,空 = 跟随模型默认
预设子代理挂载的 agent preset,空 = 继承主代理

技术要点

  • 设置页走同源 HTTP 路由(/plugins/dsh-subagent-pool/profiles)——harness.handle 私有桥只在动态插件 VM 可用,普通安装包不可用
  • 预设挂载 = recompose + agent-preset/selected 会话事件(两步缺一不可,否则恢复时回退继承预设)
  • 推理等级 = 子代理 ctx 上的 agent/request waterfall(与 DSH 官方 installModelSelection 同款)
  • 调用形态:一次性(每次新会话,干完即弃)
  • UI 全部使用官方 dsh-client-ui-primitives 组件与图标 + --dsw-* token

License

MIT