DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Subagents — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins
S

dsh-subagents

Subagents

面向 DeepSeek Harness 的专注型子代理委派(侦察员、研究员、执行员、审查员、预言家、委派员)和多代理工作流(委员会、并行审查、审查循环)。

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add github:geekyfoxlab/dsh-subagents#733a74c7de004cd2ae376f03fdb57fcabbe31c3c
README兼容性版本

兼容性与来源证明

Subagents 以 dsh-subagents 发布,当前版本为 0.1.0。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
github
Registry 更新时间
2026/8/26

版本

0.1.0stable
2026/8/26

相关插件

正在加载相关插件…

最新版
0.1.0
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
未提供
文件数
未提供
Surface
any
许可证
MIT
发布源
github
GitHub
★ 0
周下载
0
最近提交
2026/8/26
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 agents-orchestration 分类下经过校验的插件。

Headless@deepseek-ai/dsh-headlessdsh one-shot bundle:基于 dsh-base 的直接核心 Agent/Session 运行器,不包含 Host、HTTP 或浏览器层Experimental Agent Team Web Profile@deepseek-ai/dsh-experimental-agent-team-web-profile用于 Agent Teams Remote 和 UI 插件的实验性 Web 配置层Subagent Codex@deepseek-ai/dsh-subagent-codex基于官方 app-server 协议的一次性 Codex 子代理提供程序Subagent Claude Code@deepseek-ai/dsh-subagent-claude-code基于官方 Agent SDK 的一次性 Claude Code 子代理提供方

README

dsh-subagents

Focused child-agent delegation and multi-agent workflows for DeepSeek Harness (DSH).

A faithful port of pi-subagents, rebuilt on DSH's native subagent / subagent_fork / workflow tools — so you get the curated personas and workflows without giving up DSH's built-in delegation.

  • 🇨🇳 中文文档

Why this exists

DSH already ships delegation (subagent, subagent_fork, workflow, agent_teams) and an on-demand skill system. What it does not ship is a ready-made set of who to delegate to and how to chain them.

dsh-subagents fills that gap with:

NeedYou get
A second pair of eyes before you editreviewer persona with P0/P1/P2 findings + a merge verdict
A sanity check on a risky decisionoracle persona that challenges assumptions without editing
Fast recon of unfamiliar codescout persona for entry points, data flow, and risks
Grounded external factsresearcher persona producing a sourced brief
A careful implementerworker persona that edits minimally and escalates instead of guessing
Orchestrated review/impl loopsparallel-review, review-loop, council, parallel-research, parallel-cleanup, gather-context workflows

Problems solved: no hand-rolled prompts, no remembering role tool-allowlists, no reinventing review loops. One install and you can say "use reviewer to review this diff" and get a disciplined review.

What makes it different: it's not a new agent runtime — it's a thin, dependency-light skill layer (pure ESM, zero runtime deps) that teaches the model how to use DSH's own tools, so it composes with everything else in your profile (AgentTeams, MCP servers, skills, themes).

Install

dsh plugin --profile web add dsh-subagents
# or from a local checkout:
dsh plugin --profile web add /path/to/dsh-subagents

Restart the dsh process, and you're done — no config, no slash commands.

Try this first

  • "Use reviewer to review this diff."
  • "Ask oracle for a second opinion on my current plan."
  • "Use scout to understand this code."
  • "Run parallel reviewers: one for correctness, one for tests, one for simplicity."

The model loads the matching subagents-* skill and delegates with the native tools. You don't create agents, write config, or learn commands.

Builtin roles

RoleUse when you want…
scoutFast local codebase recon: relevant files, entry points, data flow, risks.
researcherWeb/docs research with sources and a concise brief.
workerImplementation: edits files, validates, escalates unapproved decisions.
reviewerCode/plan review with P0/P1/P2 findings and a merge verdict.
oracleA second opinion before acting; challenges assumptions without editing.
delegateA lightweight general handoff close to the parent session.

Workflows

WantSkill
Debate a material decisionsubagents-council — bounded parent-mediated advisor council
Review a diff adversariallysubagents-parallel-review — several fresh reviewers, distinct angles
Implement → review → fix until cleansubagents-review-loop — capped at 3 rounds
Build a grounded multi-angle answersubagents-parallel-research — researcher + scout
Clean up AI-slop / verbositysubagents-parallel-cleanup — deslop + verbosity passes
Gather context, then clarifysubagents-gather-context — scout/researcher, then clarifying questions

How it maps to DSH

pi-subagentsdsh-subagents / DSH
subagent toolsubagent (fresh) / subagent_fork (context-aware)
workflowScriptworkflow
multi-agent teamsagent_teams (native)
builtin agents (.md frontmatter)skills subagents-scout, subagents-reviewer, …
prompt shortcutsskills subagents-council, subagents-parallel-review, …
context: fresh / forksubagent / subagent_fork
async / backgroundrun_in_background: true + job_output / job_kill
subagent({action:"list"})list_agents (children) + the skills catalog

Note on roles: DSH's subagent tool fixes persona/tool-filter at config level, not per call. So role switching here is prompt-driven: each role is a skill whose persona text you paste into the child's prompt. Hard per-role tool isolation would require a DSH agent-preset composition layer — see Limitations.

Layout

lib/index.js        host plugin — registers skills + a usage section
skills/*.md         the persona and workflow bodies
cordis.patch.yml    mounts the plugin into a profile's host composition

Requirements

  • Node ≥ 20 (ESM).
  • A DSH profile whose base bundle mounts skills and systemPrompt (standard profiles do).

Limitations

  • Role personas are soft guidance: a child inherits DSH's toolset and self-limits by the persona's tool guidance. There is no per-call tool-allowlist enforcement.
  • council cross-exams use a fresh re-launch rather than resuming the same child, because DSH one-shot subagents are not resumable (use subagent_fork + send_message for a resumable child when you need it).

Contributing

Bug reports and PRs are welcome. Please open an issue before starting non-trivial work. There is no build step — the plugin is plain ESM, so node --check lib/index.js and a mock apply() run are the smoke tests.

License

MIT. A port of pi-subagents (MIT, © Nico Bailon).