DSH Plugin HubDSH 插件市场

ztl34245881-commits/dsh-task-planner

Plugin插件 Native原生 ⭐ 3 MIT Memory & Knowledge记忆与知识库Productivity & Tasks效率与任务

面向DeepSeek Harness的任务规划与经验肌肉记忆：条件反射式回忆 + LLM能力匹配 + 自动持久化经验教训

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native plugin built exclusively for DeepSeek Harness (DSH), designed to add experience-based task planning capabilities to the DSH agent. To install the plugin, you can run the dsh plugin --profile web add github:<your-user>/dsh-task-planner command directly in your DSH terminal, or clone the repository locally and add it via the dsh plugin --profile web add /path/to/dsh-task-planner command after copying. It integrates directly into the DSH command system, adding four new commands for task planning and experience memory management that work seamlessly with core DSH services out of the box.

It is built for DSH users who regularly work on similar complex tasks, helping the agent get smarter with each completed work session. Every time you run the plan_task { task, goal?, constraints? } command to start a new task, the plugin automatically drafts a lesson entry and saves it to your experience library with a draft status. When the task completes, you can update the entry with the final outcome, marking it as verified, and lessons that work repeatedly get promoted to formal skills while failed lessons get marked obsolete.

The plugin requires the core llm, shell, and tools DSH services that are included by default in all standard DSH installations. It uses the default DSH agent model for all LLM calls, so you will need to set a generous maxTokens limit of at least 8000 for reasoning tasks to work correctly. By default, all experiences are stored in ~/.dsh/planner-lessons, but you can configure a custom path and add an optional capability catalog in your cordis.patch.yml configuration file. Lessons are stored as plain Markdown, so you can edit or port them easily, and the entire project is released under the permissive MIT license.

这是一款专为DeepSeek Harness（DSH）开发的原生任务规划插件，核心能力是基于过往任务经验实现智能规划。它会构建专属经验库存储过往任务解决方案，代理接到新任务时会召回相似的过往方案，评估适配性后动态生成匹配自身能力的规划，全程不依赖硬编码的固定方案。

面向需要处理复杂重复任务的DSH用户，帮助代理在每次规划新任务后自动将本次规划草稿存入经验库，任务结束后更新执行结果。它支持手动保存、召回、列出所有经验，使用2-3字符滑动窗口分词做召回，即使关键词近似也能准确命中匹配的过往经验记录。

遵循MIT许可证开源，可通过DSH插件管理命令直接从GitHub远程安装，也可以添加本地仓库路径进行本地安装。它依赖DSH默认提供的llm、shell、tools服务，支持自定义经验库存储路径和能力清单文件，经验以纯Markdown存储，方便用户手动编辑修改。

View on GitHub在 GitHub 查看

Recommended强烈推荐 Send to your DSH发给你的 DSH 安装 
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-task-planner（ztl34245881-commits/dsh-task-planner）
仓库：https://github.com/ztl34245881-commits/dsh-task-planner
本站详情页：https://www.yhbd.top/plugins/ztl34245881-commits-dsh-task-planner/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 3 · 最近提交 2026-08-14 · 主语言 JavaScript

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。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 3 stars - very few users, little community feedback星标只有 3，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 github:ztl34245881-commits/dsh-task-planner

把 ztl34245881-commits/dsh-task-planner 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

3.1 KB · 缓存于 2026-08-23 03:42:01 · 3.1 KB

dsh-task-planner

Task planning with experience muscle-memory for DeepSeek Harness (dsh).

Give a task → the agent recalls past similar solutions (condition reflex), evaluates whether they fit, and produces a dynamic plan matched against its capabilities — never hard-coded combos. Every plan auto-drafts a lesson into the experience library; when the task closes, the agent updates the outcome. The more you work, the smarter the reflex.

Features

  • 🧠 Experience library (task_memory save/recall/list): persistent lessons as plain Markdown with signature keywords. Recall uses a 2–3-char sliding-window tokenizer, so "weekly report" still hits a "daily report" lesson.
  • ⚡ Condition-reflex planning (plan_task): recall → LLM evaluates fit (reuse & improve, or explain why not and plan fresh) → decomposed steps with capability matching → risks → next actions.
  • 🤖 LLM-driven, not rule-driven: the model decides what to use per task; the plugin only supplies context (past experiences + optional capability catalog).
  • ✍️ De-AI deliverable standard: any textual output step (docs/sheets/slides/copy/scripts) must include a humanize-then-review pass before delivery.
  • 🗂️ Auto-persist: plan_task drafts the lesson automatically (status: draft); the agent marks it verified with the outcome at loop close.
  • 🔒 Zero keys, zero absolute paths: everything is configurable; the experience library lives in ~/.dsh/planner-lessons by default.

Install

dsh plugin --profile web add github:<your-user>/dsh-task-planner

or copy the repo and add it as a local bundle:

dsh plugin --profile web add /path/to/dsh-task-planner

Config (optional, in your profile's cordis.patch.yml)

- id: dsh-task-planner
  name: dsh-task-planner
  config:
    lessonsDir: /path/to/your/lessons   # default: ~/.dsh/planner-lessons
    capabilityFile: /path/to/capability-map.md  # optional catalog fed to the LLM

Point capabilityFile at a markdown catalog of your skills/plugins (e.g. an awesome list) and plan_task will match each step against it.

Usage

  • plan_task { task, goal?, constraints? } — plan before starting complex work.
  • task_memory save { task, plan, outcome } — persist a lesson (auto-called by plan_task for the draft).
  • task_memory recall { task } — condition-reflex lookup.
  • task_memory list — show all lessons.

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 →

渲染基于仓库 ztl34245881-commits/dsh-task-planner 的 README.md。 在 GitHub 查看原文 →

Related相关推荐

← 上一个 Prev dsh-conv-search 下一个 Next dsh-nav-pointer →