插件

Unified management and invocation of external Agent CLIs in DSH, fully isolated from the user's native installs; preset Provider, model, reasoning effort, and permissions per CLI, callable directly or like native subagents.

Management center: link skill directories into the user skills root (enable/disable/unlink/delete) and manage MCP servers — add/edit/delete, import from other agents (Claude Code/Codex/Cursor/Gemini CLI), auto-load each project's own MCP servers via the l

Persistent, searchable, per-project memory for the DeepSeek Harness: decisions, rules, and sprint context in a queryable DuckDB file, rules enforced on every model request, with a full management UI in the Web Client

Xiaomi MiMo-powered voice for DeepSeek Harness: browser 🎤/🧠/🔊 UI, voice_transcribe/voice_understand/voice_speak tools, configurable voice map (preset/voicedesign/voiceclone). Fork of zhuiyueya/dsh-voice (MIT), Settings pattern from Anionex/dsh-vision-toolkit (MIT).

Enforces your comment policy at write time, inside DeepSeek Harness. Reads the policy from your AGENTS.md or CLAUDE.md, blocks violating writes, and re-injects the policy verbatim so the model stops drifting from it.

给 agent 用的 AnySearch 搜索工具：通用与垂直域搜索、并行批量查询、垂直域目录发现、网页转 Markdown，并在设置中提供 API Key 面板。它注册独立工具而非 web_search provider，不能与 @anysearch/anysearch-dsh 同时安装。

为 DSH Web UI 的每个对话实时计算 token 费用：本对话、其子代理与整棵会话树，价格来自内置的 models.dev 快照：七家供应商、139 个有价模型，缓存读写费率按供应商实际公布的取值，DeepSeek 则使用其官方峰谷价格表。每个完成的回答都会在对话中显示自身费用，未打开的对话则按日志计价而不是整行消失。费用按区间计价，依据写入项目目录的只追加 JSONL 账本，因此已记录的工作保留当时的费率。此外还提供：按金额预算排布的工作计划、展示值得接入哪些模型的路由方案比较、以英语/中文/俄语生成的计划文档，以及当费用未归入任何计划单元时的提醒。

flykit for DeepSeek Harness — status line, file explorer with editor and live watch, and Claude Code / Pi / Codex terminals in the web GUI. Fly your agents.

dsh 插件：本地蒸馏器——扫描全部历史会话，挖出「用户纠错 → agent 改对」片段，脱敏后蒸馏成微调数据对（JSONL）、技能草稿与 AGENTS.md 规则补丁，带人工审核队列

Verifiable authorization, execution evidence, and offline delivery verification for DeepSeek Harness

根据有界证据记录限定范围的工作流规则与纠错提醒，提供本地设置并支持可选 Brain Hub 集成。

把笔记存成你选定根目录下按分组组织的本地 Markdown 文件，带侧栏页面，并把 AGENTS 等规则 md 作为写作上下文，另有六个 agent 工具。

dsh plugin: cron scheduling — bounded tasks with calendar & interval rules, delivered to live agents

把 GeoJSON / 矢量数据渲染成侧边栏「地图」tab 里的交互地图，并让 Agent 通过工具实时操作地图：图层、样式、视图、要素识别、GeoLibre 处理算法与 Whitebox 工具箱（浏览器端 WASM 执行）。

Deepseek harness (Plug-in)

自研 DSH 记忆插件：SQLite 持久存储 + 数据库层审核守卫（enforceAudit）+ 审计日志。对话结束自动沉淀知识卡，Agent 经 memory_recall 按需召回，支持 Claude Code/Codex/Cursor 多智能体共享，零外部依赖。

Approval-gated workspace instructions and memory for DeepSeek Harness

判定 Python 代码是原创还是演绎作品：给出与上游最长相同表达片段、逐条豁免依据和风险清单。纯标准库 `ast` 分析——离线运行，不调用模型。

多智能体防内耗防御插件：读取台账去重度量、免疫压缩规则区、完成机械门禁、低成本审查 lane。

NPM-installable DSH Web plugin for safely loading and managing skills across DSH and common local Agents.

Multi-bot workbench for DeepSeek Harness: bridges the sdk-bots orchestration gateway (group chats, single bots) into the dsh web shell with official-styled UI.

Keeps every model request inside a per-provider allow-list, enforced at the agent/request waterfall: disallowed models are redirected to a fallback or refused; subagents stop inheriting stale creation-time routes; warns when consecutive requests would make a --models-max 1 llama.cpp router reload models. A one-entry list is a global single-model mode.

Explains which layer killed a failed turn: times every model request (first byte, longest silence, total) and combines that with the error to name the culprit (dsh idle watchdog vs Node undici timers vs SDK timer vs server crash, context overflow, gate queue, tool timeouts, failed compactions) and the exact setting to change; verdicts in the DSH terminal plus a /why command, subagents included.

在设置页编辑 prompt-inject.md、管理 AGENTS.md 或 CLAUDE.md 规则集、检查插件更新，并对本机包做可回滚的应用或还原。