Plugins

Rejects foreground waiting in DSH agents: waiting commands (sleep, wait, tail -f, watch, ping without -c, infinite loops), blocking wait tools (wait_agent, job_output with wait: true), progress polling (the same check command repeated within a window) and commands that need human input/confirmation (sudo without -n, ssh without BatchMode, login flows, interactive editors, docker -it) are refused with an actionable retry to run in the background or end the turn. Configurable budget and polling window, message language follows the system (zh/en), zero runtime dependencies.

Folds REA's 207 reverse-engineering tools (Ghidra / Hopper / IDA backends) into 3 commands plus 6 read-only domain entries: about 5 KB of resident tool text instead of 757 KB. Ships no engines; rea-agents, Ghidra 12.1.x and JDK 21 are installed separately.

Infinite canvas workspace in the DSH sidebar — arrange text, image, video and audio nodes, generate media with AI, and let agents drive every canvas operation through MCP tools. Ships a local bridge service, ready to use offline after install.

3D director desk sidebar plugin for DSH: stage characters, set camera moves and record timeline previews; AI agents drive the scene in real time via MCP tools.

Registers named Claw agents, isolates them from the official workspace sidebar, and provides settings plus a global new-agent template. Hard deps (install together or single install fails): dsh-claw-policy, dsh-claw-observability, dsh-claw-permissions.

Injects SOUL, IDENTITY, AGENTS, and TOOLS into Claw session prompts. Hard dep (install together or single install fails): dsh-claw-permissions.

Adds the models of your own GPU Hugging Face Space to the model selector, starts the Space when you send a message, shows its start progress, and pauses it when idle or at a time limit. Requires a Hugging Face account with a GPU Space serving an OpenAI-compatible API, a Hugging Face token stored in the DSH vault as HF_TOKEN, and a paid plan for GPU hardware; Hugging Face bills the GPU time.

A tiny always-on floating tree of the DSH workspaces, conversations and subagents that are running, waiting on you or on a schedule — live running state, who is waiting for your call, per-row model, scheduled-run countdowns, other local dsh instances with their ports, and local claude/codex CLI processes with their codex subagent threads.

A permanent status card in the top-right corner of the DSH content area: one line for where this turn's time went (model, tools, waiting), plus collapsible to-dos with a progress bar, the session goal (edit/pause/resume/clear), submitted plans that open in the preview pane, the files this session changed, subagents with their token and duration figures, and this session's background jobs: running rows carry a two-step stop button, finished ones fold into a count line that stays collapsed until opened; it yields space to the content as the area narrows and folds into a round button at the limit.

Adds a right-sidebar panel that lists the skills available to the current session, searches and tags them, combines them with your own saved prompts, appends the selection to the composer in one click, and can pin skills and prompts as always-on context injected through the system prompt.

Adds a `muse` subagent provider and the `subagent_muse` tool to DeepSeek Harness, so the main agent can hand one self-contained task to the Meta Muse Code CLI and get back only its final report. A patched fork of `@pascapone/dsh-muse-code` that loads on DSH 0.2.1: it carries local equivalents of the removed `settleRun` export and `subagents.start` method, and documents an optional proxy for the gateway stream-phase bug. Needs the `muse` CLI installed. Install either this fork or the upstream @pascapone/dsh-muse-code, not both: both register the same subagent-muse loader row.

Two-way session import between DeepSeek Harness and local coding agents: read Codex, Claude Code, Cursor, ZCode, Kimi and WorkBuddy history into DSH, and import DSH sessions into those agents.

Runs OpenCode as a DSH subagent over ACP and shows each task live in the right sidebar — its agent and model, tool calls, and the subagents OpenCode spawns itself; permission requests become DSH question cards with allow once, allow always or reject.

A shared right sidebar for the DSH web client — other plugins register tabs into the `rightbar.tab` slot instead of each pinning a `position:fixed` panel; ships a `rightbar-tab` skill for agents and an opt-in mode that moves legacy fixed panels aside.

Connect Claude Code to AgentsChat — AI Agent social network. Core tools stay lean while extended tool groups load on demand for lower token overhead and cleaner role-specific context.

Remote workspaces for DeepSeek Harness: pick an SSH host in the sidebar, mount a server directory over SFTP as a workspace, then read, write and edit those files with the normal file tools. Remote watch is polled so the file tree refreshes, image/binary previews work through byte-range reads, and remote_exec, remote_search and remote_git give agents the remote shell, search and git queries. An opt-in patch routes the agent's own bash/pwsh commands to the server. Every remote write and command follows the session sandbox mode and approval policy, and hosts are managed by the plugin itself (password, key or SSH agent).

Offline Chinese-English and English-Chinese dictionary with monolingual glosses, grouped related words, prosody analysis, and a public-domain Chinese/English literary corpus exposed to agents.

Adds a Delete Session row to every sidebar session '...' menu (the official harness has archive/pin/rename/fork only, no durable delete). One-click Force delete ejects the session from the host live catalog, stops its background work, then removes the durable log, projection cache and registry bookkeeping - no ghost rows on any connected desktop web UI. Workspace files the session created are kept; conversation logs are permanently deleted. Third-party cloud mirrors (e.g. phone apps via Agents Anywhere) hold their own copies. Bilingual zh/en UI, trust-fenced local route. Requires DSH >=0.2.1-rc.1.

Adds a conversation view that maps which skills, MCP tools and subagents a session actually used, with an attribution tree, a call table and an unused inventory.

DSH 插件：设置 → 系统指令 —— 在线编辑 DSH 真正加载的用户全局指令 $DSH_HOME/AGENTS.md（注意：单数 AGENT.md 不会被加载）。保存固定使用插件自身的最高权限写入，不需要切换当前会话的权限模式；带 Markdown 预览、版本冲突保护（409 不覆盖），并提供「立即刷新」发起真实的第一方 read 调用，让改动即时生效。

Better subagents for DeepSeek Harness: choose the default subagent model, see each subagent conversation's model in its header, and wait for subagents with a blocking wait_subagents tool instead of sleeping or polling.

The 7-7-7 execution loop for DeepSeek Harness — plan, run, capture, close, compound, with a human gate.

Connect DeepSeek Harness to shared AgentsChat rooms over MCP and WebSocket wake bridge for cross-agent messaging, peer code review, proposals, voting, and OKRs.

Windows desktop control for DeepSeek Harness agents: window and UI Automation automation, local Windows OCR, direct browser reads over the Chrome DevTools Protocol (DOM text, JavaScript, selector clicks), humanised mouse and keyboard input, browser tab management, and a live control panel. It probes the machine on first run, writes its own config, and degrades gracefully when a capability is missing. Windows 10/11 only.