Plugins

DeepSeek Harness (DSH) plugin: injects a bounded, timestamped snapshot of your local Second Brain (identity + state fingerprint + pointers) into every new session's prompt. Read-only, zero-write, fail-loud, zero dependencies. 第二大脑载入器：让每个新会话开局自带记忆快照。

Drive DSH's own built-in browser (the right-hand Sidebar's Browser tab) from the agent: list tabs, open, navigate, read the page, run JavaScript, click, fill forms, log in, and look at pictures or the pane itself with vision. No second Chromium process.

Multi-root workspaces for DeepSeek Harness: attach other repositories to a workspace, writable under workspace-write, listed in the model context with their AGENTS.md, and editable from the composer or /roots

Elephant Memory: your DeepSeek agent never forgets. An endless memory for the DeepSeek harness: the agent keeps every chat it has in a project and reads all of it at every turn through a fixed-size set of summary lines (after Victor Taelin's OptChat speci

Action cards: the agent proposes a concrete action (create a file, edit a value, run a command), you edit it and apply it in one click, and the Host executes it and reports back.

DeepSeek Harness (DSH) plugin — connects DSH to MATLAB and Simulink through the official MathWorks MATLAB MCP Server, injects MATLAB/Simulink Agentic Toolkit skills, and provisions everything with one click.

Natural, human-sounding voice for the dsh harness: server-proxied neural TTS read-aloud and agent speech tools over OpenAI-compatible endpoints, browser-native or Whisper speech input, and a Voice settings section

Use a GitHub Codespace directly as a DSH workspace: the agent reads, writes and runs commands inside the cloud Codespace.

DSH 右侧栏的媒体台：把抖音/YouTube 链接丢进来，本机 yt-dlp 下载、ffmpeg 转 16k 单声道 WAV、官方 speechToText（SenseVoice）转写，字幕进面板，Agent 一键总结。

agent 读到的内容里，有没有人在给它下命令

Cursor system prompt reverse-engineered from Cursor.app, exposed as a selectable 'cursor' agent preset for DeepSeek Harness.

A soul for DeepSeek Harness: an in-character Whale Chan agent preset with layered long-term memory and dream-like consolidation.

Command DeepSeek Harness from Telegram and Feishu (Lark): one live progress message per turn, approvals and questions as buttons, files and voice, delivery that survives outages and restarts, QR setup for Feishu, and per-person roles.

Runs a fixed set of agent benchmark cases in isolated sandboxes, scores each case with deterministic assertions, and diffs two runs to show which cases regressed after a model, prompt or DSH upgrade.

Records the files and folders an AI agent creates, modifies, deletes, renames or moves, shows them in a draggable floating panel with unread counts, and persists the records as per-workspace JSONL logs.

Owner-facing AI studio for DeepSeek Harness: project roles, task acceptance, worktree-based agent runs, host verification, independent review, decision records, and human-triggered merges.

Ponytail port: a DeepSeek Harness agent preset that makes the model finish tasks with the least tokens, with lite / full / ultra levels.

Connects a local Synthesizer V Studio 2 Pro to the agent through its own Lua script API, with five tools for discovery, a persistent bridge, voice composition, note editing and DAW (VST3/ARA + MIDI) integration. Windows 10/11 only; requires Synthesizer V Studio 2 Pro 2.1.2+ with a project open.

Generate images and videos, edit images, remove backgrounds, upscale images, upload reference media, and check Fotor credits.

One versioned vocabulary of a project's business concepts, a read-only drift scan, and the same naming rules in every agent prompt.

Enhances native DSH subagents and teams with persistent subagents, improved subagent messaging, and per-member model selection for teams. Adds no extra tools or context beyond the native features.

Adds an AIignore tab to the right sidebar: scores the open conversation and its folder across five dimensions, blocks reads of build output, lockfiles and logs before they reach the model, and writes the .aiignore rules for them one button at a time.

Adds a tier bar to the DSH composer with three thinking tiers (normal, strict, max), an exclusive loop mode whose three levels run 3, 5 or 8 self-review rounds, and a counter-review toggle that stacks on either; the model reads the current tier through the clarify_tier and forge_level tools.

Read-only terminal view tab in the conversation header: aggregates bash output, background jobs and persistent terminal sessions from the current session, subagents and Agent Team teammates into one filterable panel, with type and session-scope filters, command/output search, auto-collapse, follow-scroll and a maximize dialog; foreground bash shows final output only. Requires DeepSeek Harness 0.2.1-rc.2 or later (0.2.x).