jiruidai/dsh-meta-orchestrator
DeepSeek Harness 的模型原生元代理插件,利用底层模型的推理与规划能力,在运行时合成针对特定任务的工作流,并协调工具与子代理。
Project Overview项目介绍
This is a native plugin built exclusively for DeepSeek Harness (DSH) that enables DSH agents to dynamically generate task-specific workflows at runtime, instead of relying on hard-coded pipelines or fixed agent topologies. After installation, the plugin adds a short instruction block to the agent’s system prompt, plus three recording tools and five pre-built workflow pattern playbooks. It installs via DSH’s standard plugin management system from npm, and only uses stable public DSH plugin interfaces, so it does not break when DSH core receives routine updates. This makes it safe to add to any recent DSH installation.
When handling a user request, the agent first analyzes the request to see if it needs full orchestration. Simple requests skip the planning step entirely to avoid unnecessary overhead, while complex multi-step tasks go through a formal workflow: pick a workflow pattern, write down the plan with success criteria, execute the plan with DSH’s native tools, and revise the plan if the task changes. It is designed for DSH users who work on complex multi-step projects and want their workflows to be explicit, versioned, and durable across restarts.
This plugin is released under the open-source MIT license, with no associated costs or closed-source dependencies. It only requires a working DSH 0.1.0-rc.6 or newer installation, and does not add any extra runtime or background processes. Currently, it does not have a client-side user interface, so all workflow state must be viewed through conversation history, tool outputs, or local storage files. Recorded workflows are never deleted when you uninstall the plugin, so you can roll back or remove it safely at any time.
这是一个专为 DeepSeek Harness (DSH) 开发的原生插件,核心功能是让 DSH 代理在运行时根据具体任务动态合成工作流,而非依赖硬编码的流程或固定的代理拓扑。插件会引导代理先分析请求、选择合适的工作流模式、编写明确的执行计划,再使用 DSH 原生工具执行任务,支持在执行过程中根据实际情况调整计划,并对所有计划版本进行持久化存储。它遵循 DSH 插件标准规范,可通过 DSH 的包管理机制直接安装启用。
针对多步骤复杂任务,该插件遵循「先规划后执行」的固定逻辑,对于简单请求会直接由代理处理,不会触发不必要的编排流程。它适合所有在 DSH 中处理多步骤复杂工作、希望工作流程明确可追溯、而非隐式执行的用户。用户可以在配置中选择默认开启自动编排,也可以仅在需要时手动触发,使用方式灵活,适配不同场景的需求。
该插件采用 MIT 许可开源,无额外成本,仅依赖 DSH 0.1.0-rc.6 及以上版本,不需要额外的运行时或后台进程。它目前暂不支持客户端可视化界面,工作流状态只能通过对话、工具返回结果和存储文件查看。所有计划变更都会以追加形式记录,重启 DSH 后可正常恢复会话,删除插件也不会丢失已记录的工作流。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-meta-orchestrator(jiruidai/dsh-meta-orchestrator)
仓库:https://github.com/jiruidai/dsh-meta-orchestrator
本站详情页:https://www.yhbd.top/plugins/jiruidai-dsh-meta-orchestrator/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 6 · 最近提交 2026-08-14 · 主语言 TypeScript
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- Only 6 stars - very few users, little community feedback星标只有 6,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add dsh-meta-orchestrator
把 jiruidai/dsh-meta-orchestrator 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
A DeepSeek Harness plugin that teaches the agent to synthesize a task-specific workflow at runtime — instead of hard-coding pipelines or fixed agent topologies. For anyone running multi-step work in DSH who wants the plan the agent follows to be explicit, versioned, and durable rather than implicit.
🧭 How it works
Normally an agent just starts working on your request. With this plugin, it plans first, then works the plan — and the workflow is dynamic: written by the model itself, per request:
- Analyze — the agent reads the request; if it is genuinely ambiguous, it asks before doing anything.
- Pick a pattern — it chooses one of five proven ways to organize the work: ⛓️ steps in order (
prompt-chaining), ⚡ fan out independent parts (parallel-workers), 🔀 classify, then dispatch (router), 🎯 delegate and review (supervisor), 🔁 draft → score → improve (evaluation-loop). Each pattern's detailed playbook is loaded only when picked. - Write the plan down — it calls
orchestratewith the stages, the roles it will delegate, and verifiable success criteria. The plugin validates the structure and saves it durably. That is all the plugin ever does: it records plans, it never executes them. - Do the work with DSH's own tools — subagents, todos, workflow scripts, plan mode. The plugin adds no runtime of its own.
- Adapt or close — if reality diverges,
adapt_workflowrevises the plan (every revision is versioned); when the work is done,complete_workflowrecords how each success criterion turned out.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
wloops/dsh-git-worktree
huxint/dsh-team
miuzel/dsh-graph
LeemanCheung/dsh-task-dag
NEXTINDIE/DeepSeek-Harness-for-VS-Code
lincong1987/dsh-model-switch
Tikzen/dsh-agent-arena