Plugins

Adds a versioned DPIA workbench to DeepSeek Harness for source-linked facts, follow-up answers, reassessment, and reviewable reports. Needs Python 3.9+ with `python-docx`, `pypdf`, and (for PDF templates) `reportlab` + `pdftoppm`.

Registers the domestic-China trip-planning skill: hour-level daily timelines, 12306 and Trip.com booking deep links, offline KML, and seven HTML themes. Requires Python 3.9+ on PATH (the bundled scripts are standard-library only).

Host-wide MCP server panel: imports the servers declared in Claude Desktop, Claude Code, Cursor and Codex CLI configs, searches six upstream catalogs and installs from whichever of them declares an install plan, asks only for the fields a server actually declares, and checks each row for whether the mount, the handshake and its tool list really work.

Adds an animated ASCII whale ocean behind empty chats, with neutral frosted-glass input, visual color selection, light/dark support, and configurable whales, fish, grid and wakes.

Per-turn TPS and TTFT statistics for DeepSeek Harness: model time, tool time, time-to-first-token, and output speed per turn.

Pins passages selected in a conversation into a per-conversation right-sidebar panel, marks them in the transcript, jumps back to the source passage on click, and quotes a pinned passage into the composer from the selection toolbar or by typing @; the panel tags, searches, filters and exports the pins as a Markdown outline.

Embeds chat.deepseek.com directly inside DeepSeek Harness desktop with persistent login sessions and dual-entry chat panels.

Russian for the dsh web GUI: the whole interface plus the menus of 520 third-party plugins — 584 sections, 67,666 strings.

Turn another computer into a remote Agent teammate: the worker runs its own DSH and a full Agent loop locally, so dispatched tasks keep running when the link drops and its model credentials never leave that machine. The hub dispatches through 8 remote_* tools, receives only a handoff summary plus an artifact manifest, and pulls finished products on demand — intermediate artifacts stay on the worker. Pairing-code onboarding, direct or relay transport for NAT, Web panel on both sides.

Turns a DSH deployment into one node of a decentralized agent network — signed agent cards, peer and zone discovery, direct message-routing model tools, and joinable session nodes in the web sidebar.

Multi-agent roundtable discussion: each member runs as a subagent on its own model and speaks in turn, a host summarizes each round, and termination writes meeting-minutes Markdown.

Deep-reading workflow for books: import EPUB/Markdown/TXT/PDF into chapters, read one chapter per subagent so the source text never enters the main session, keep \[n]-anchored chapter memories for cross-session continuation, and export notes or an EPUB.

Requirements interview before work starts: judges whether a request is clear, asks focused questions when it is not, in strict mode denies editing tools until the user confirms a four-part summary in chat, and keeps confirmed preferences in two-layer memory.

Finishes 头歌 (EduCoder) homework over the platform JSON API, with no browser automation. educoder_sweep scans every course for homeworks that still have unfinished challenges — complete homeworks are skipped without reading a single challenge, so a full-account scan costs no model tokens — and can finish them; multiple-choice challenges also cost no model tokens, because the platform returns the answer key in any submission response, while code challenges are generated by the model, uploaded with evaluate:0 and graded once per challenge, then retried using the error report the platform returns. Three tools: educoder_sweep, educoder_homework, educoder_account.

Keeps project decisions in plain markdown instead of chat history: one main document plus per-module documents, every entry carrying a file:line citation. The agent interviews you to turn open questions into settled decisions, and a five-dimension score (task complexity, extensibility, maintainability, code quality, reusability) is derived from the documents and shown on a button beside the model picker. A session can bind several projects; projects are sized small/medium/large, which widens the entry limits, and a reusable-pipeline section in the main document is injected when its trigger words appear.

Cross-session usage and cost observatory for DSH — token trends from hourly lines to 90-day and 1-year heatmaps, per-model DeepSeek peak/off-peak pricing reconciled against the official balance, GLM/Kimi/MiniMax subscription-quota windows with burn-rate forecasts, cache-hit ring, project rankings, CSV export, and a dsh-tui terminal face.

Input prediction for the DSH composer: your next prompt suggested as ghost text after each turn, accepted with Tab. (autocomplete / input prediction / prompt suggestion)

Turn a set of DSH plugins into one pasteable share code, then install it plugin by plugin — with a QR code to carry it to a phone.

Discovers rule files from every convention OMP supports and injects them into the system prompt as an always-apply layer plus a rulebook index, then enforces them with time-traveling stream rules that abort violating output mid-turn, deny a matching tool call, fold a reminder into that call's result, or ask a judge model about the finished reply. The same tool lets the model write new rules, and an audit panel on the Plugins page says why each rule is in force.

Surfaces important facts and trade-offs from the current task, with on-demand explanations and optional discussion in the main session.

Browse, search and install skills from the public SkillHub catalogue, then enable, disable, update or remove them without leaving Harness. Category chips carry the upstream total for each category; the details drawer has tabs for the file tree, version history, permissions, third-party security-scan results and upstream metrics. An installed skill is written into the harness skill root as an ordinary local skill, and disabling one moves its directory out of that root rather than flagging it.

Todoist-style todo management in the sidebar with projects, labels and priorities, CJK-aware natural-language quick-add, repeat rules, a stats dashboard, import and export, seven agent tools and due-time reminders.

Turns each long dsh conversation into a three-level trail (topic to progress steps to milestone timeline) and shows it in a draggable overlay, where one click jumps back to the matching message in the transcript. Topics are distilled by the DeepSeek model with a zero-cost rule-based fallback, can be renamed, locked, merged by drag and drop, and support per-conversation notes plus a vector drawing board.

Scheduled reminders and delayed send for DSH: /later delivers what you type as yourself at the time you pick, while the timer panel (or /schedule) posts a reminder row — even with the page closed. (scheduled send / reminders / delayed send)