Plugins

Runs Superpowers as an agent preset and gives each skill its own subagent model from a Settings table, so TDD, debugging and verification no longer all inherit the parent model.

Invoke DSH skills with a $name gesture instead of /name, with a composer picker and the same blue text-reference decoration as /name.

Per-workspace activation control: a dialog opened from the workspace row menu switches individual plugins, MCP servers, and skills on or off, and the host applies the choice in that workspace's own agent scope — a disabled skill leaves the model catalog, an MCP server has its mcp__<server>__ tools denied, and a plugin has the tool names its entry declares denied.

Cross-session lesson book (the agent wrong-answer notebook) for DeepSeek Harness: injects a memory index capped at 2 KB verbatim into every turn, adds mem_recall and mem_save model tools whose write gate demands four sections, a locatable reference and explicit human approval before anything reaches disk, registers the /memory command, and keeps every lesson as a zero-dependency Markdown entry in the .memory/ directory.

Holds a drafted message until the main agent is idle, no subagent is running and no background job is live, then sends it. Each hold takes an optional send time and a choice to queue, wait or steer, and lives on the host with its attachments so a restart does not lose it.

Session-context surfaces ported from T3 Code: a session-row hover card showing machine, git branch, model, agent preset, approval policy and token usage, a status pill covering pending approval, awaiting input, working, error and subagent work, a provider and model chip, a per-session header strip, a lineage breadcrumb, row-menu actions that copy the context or run DSH compaction, and a preference row in DSH Settings for choosing which facts appear. Nothing is added to the composer.

Project-level AGENTS.md loader for DeepSeek Harness: injects .dsh/AGENTS.md (and custom paths) into the agent system prompt, with a settings page.

Global on/off switch for injecting workspace instruction files (AGENTS.md / CLAUDE.md) into the model context · 全局开关：是否把工作区指令文件注入模型上下文

Speaker button left of the model selector in the composer tool row — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-hold the icon and then click anywhere on the page to pick another reading start position; press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Connect a DeepSeek Harness profile to Stuga: its MCP tools, the key's workspace and its conventions in the system prompt, and playbook skills for reviewed edits.

Persistent memory for dsh in the style of Hermes Agent: a memory tool that keeps a user profile and the model's own notes, delivered to every chat as a logged context message — at the start, after a change and after compaction — and a session_search tool that reads earlier chats only after the user approves, with a Memory panel to see and edit what is kept.

Fish 自建 DSH 插件全家桶聚合包：一键插入全部本人自建插件的插件行（approval-guide / session-title-refresh / git-sync / settings-nav-order / visual-companion / agent-teams）。

A股数据 API 官方 DeepSeek Harness 插件 —— 桌面端 / Web UI 输个包名即装，24 个 A股工具（行情 / K线 / 财务 / 资金 / 龙虎榜 / 板块 / 因子选股），免费工具无需 Key

AgentTeams 多智能体团队协作（DeepSeek Harness 插件）：自然语言组队、成员与任务依赖 DAG、信箱通信、右侧栏树状监测 —— 上游 NanmiCoder/dsh-agent-teams 的补充版，新增自定义美术目录、九厂商 × 九岗位头像与厂商商标徽标。

Drag-and-drop document reading for DeepSeek Harness: land PDF / Word / PowerPoint files in the workspace and give the agent outline, search and read tools so it can answer questions from them.

多个AI Agent各干各的，消息靠你手动搬？建一个飞书群把它们拉进来，自动认领、自动交接。直连互@与Gateway路由双路线，兼容OpenClaw/AutoClaw/CherryStudio等8个框架，含8条实测踩坑，MIT

DeepSeek Harness deepwork mode bundle for ocmm-style agentic workflows.

NetEase Cloud Music (music.163.com) player and AI DJ for DeepSeek Harness: a sidebar page with in-app playback, QR sign-in, and agent tools that curate the queue.

Maintained fork of dsh-prompt-enhance, brought up to DSH 0.1.7 — the plugin would not even load on current hosts (InputState.imageIds became attachmentIds, so the composer button crashed the input box; settings.get() was removed; /enhance read a session id the agent no longer exposes). Rewrites default to reasoningEffort off, which measured 252 output tokens for a draft where the model default spent 2897, and a Settings page for all 17 fields is bundled. Verified on a real 0.1.7-rc.2 host: activation, a live HTTP enhancement request, /enhance in the GUI, and the Settings page reading and persisting configuration. 204 tests.

为短上下文窗口的对话提供更轻量的 Agent 预设，能降低78%的固定开销。由 Deepseek 制作

Gear-based autonomy governor for the DeepSeek Harness agent: the entropy-sdk EntropyRuntime core (gear ladder G0-G4, utility gate, slow-up/fast-down policy, tamper-evident audit chain) bound to the Harness tool registry, with a live Web UI and paper-ready

DeepSeek Harness plugin: host-owned process & port lifecycle for local agents. start/stop/list/logs/wait-ready, tracked port reclaim, Processes rightbar + dock chip.

DeepSeek Harness plugin: host-owned long-horizon task board for local coding agents. Next≤3, in-flight, done+verify, inject file + STATUS.md + rightbar/dock chip.

DeepSeek Harness plugin: bounded-file memory for local agents. ME.md + project MEMORY.md vault, cache-stable inject, plain-line inbox, Memory rightbar. No embeddings, no LLM calls.