Plugins

Rate-limits LLM requests per provider and per model using a reservation-based token bucket, with queue or reject modes, plus gateway identity rules that rewrite user-agent and inject custom headers.

Renders every file mutation in the web chat as one collapsed diff card with per-line highlighting — MCP filesystem edit_file/write_file and the built-in edit/write.

Bounded, cell-addressed `doc_read`/`doc_write` for xlsx / pdf / docx / pptx / ipynb, plus an MCP server and CLI.

Settings -> Plugins switchboard: every loaded plugin card shows its package description and runtime phase, with fuzzy search and start/stop toggles that never rewrite config files.

Wraps Python virtual environment management commands: reduces the network and permission problems agents hit when managing environments through terminal commands, works across operating systems, and routes installs automatically through mirrors and local proxies. The tools are strictly confined by the granted read/write permissions.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Bounded, cell-addressed `doc_read`/`doc_write` for xlsx / pdf / docx / pptx / ipynb, plus an MCP server and CLI.

Keep your automation tasks in files you can version and review: write each task's schedule, prompt, model, permission and working folder in YAML, JSON or JS, and DSH's own Schedule is kept exactly in line, creating, updating, disabling and deleting tasks within a second of a save. Each task runs in its own conversation, persistent or fresh per run; /automations syncs on demand and names any file mistake; and a sync that finds no tasks never wipes the Schedule.

Fetches Tsinghua MadModel API tokens and renews them from the saved SSO session on a 20-minute timer in a windowless browser, writes the token into the DSH credential MADMODEL_API_KEY and creates or reuses the madmodel model provider; one manual Get captures that session through the campus login window.

Lets the model turn an answer into a web page that lives right inside the chat. The show_page tool either fills one of 8 built-in templates (report, compare, checklist, dashboard, timeline, flashcards, quiz, flow), where the model writes only the content and the plugin does layout, interaction and saving, or saves a full page the model wrote itself (calculators, games, custom layouts). Hand-written pages get the same design as base styles inside a CSS @layer, so the page's own CSS still wins. The page appears under the reply at its content height, interactive and following DSH's light/dark theme. The page's localStorage is stored in DSH per page, so what users tick or type survives reopening and new versions, and the same page open in the chat and the right sidebar stays in sync. Each edit is saved as a new version you can flip back to. After saving, the page is checked in a hidden local Chrome or Edge (script errors, horizontal overflow, dark mode not applied) and problems go back to the model. The right sidebar shows the page full-size with versions, a gallery of all pages and export to PNG, PDF or HTML. Pages run in a sandboxed, separate-origin frame with a strict CSP: no access to DSH data and no fetch, XHR or WebSocket. Works on phones with dsh-mobile.

Artifacts-like documents in the sidebar: the agent writes a self-contained HTML document, you comment on any part, send the comments back for the next version, or edit text and formatting yourself. Every change is a new version; local only. A local-only fork of tdoc (https://github.com/tornado-doc/tdoc), rewritten as a DSH plugin.

A Versions tab on the Plugins page: one-click upgrades that replace the plugin in place where they can (no uninstall, enabled state preserved, falling back to remove + reinstall with the reason logged when the profile writer lock is busy), live pnpm output with per-step timing and cancel, the full published version history with one-click rollback, every version checked against the running DSH so incompatible ones are marked and blocked, a rollback that installs the old version but cannot activate it reported separately from a lost package, profile manifest writes taken under the harness writer lock with one recoverable journal record per package after a failed upgrade, mirror-gap warnings, and a selectable npm registry saved in the profile.

Hierarchical multi-agent team coordination with lead review gates, write-scope isolation, and floating workspace.

Brings WorkBuddy free/paid models (domestic + international) into DSH without the desktop app, published as @bushizhanghan/dsh-workmate. This package is a maintained fork of Faide-cyber/dsh-workbuddy (whose upstream entry is already listed in this catalogue); do NOT co-install both, as they register the same provider id "workbuddy-ai" and will collide. v1.2.7 relocates over-long system prompts past the domestic gateway channel-risk classifier, rewrites the DSH brand string, and adds a debug dump; supports dsh 0.2.0-rc.2 through 0.2.1 (incl. prereleases).

Claude Design System theme for DeepSeek Harness: warm-grey surfaces and a clay accent, refined composer, sidebar, code blocks and Markdown, localized edit/write cards with workspace-relative paths, and an ASCII ocean on the blank-session page with three whale colour modes.

Element-level PowerPoint canvas that edits the opened .pptx in place: click, marquee-select or pick a whole slide, describe the change, and the AI writes byte-preserving OOXML patches with undo and redo.

Long-term memory for DSH stored as plain Markdown. Real user/assistant exchanges are captured into daily session files without a model call; an LLM pass then distils them into memories that are injected into the system prompt each turn. Retrieval is local (CJK bigram + BM25) in three levels — index, summary, full text — so the model only pays for the detail it asks for. Memories carry priorities; P0 and user-written entries are never changed automatically, and forgetting marks an entry stale instead of deleting it, so the whole chain stays auditable in status.md. Six tools cover recall, write, status, extract, feedback and the skill library; when a cluster of memories is ready to become a skill, a card appears at the end of the turn, writes the SKILL.md on click, and installs it only after you approve. Learning is on by default and follows the conversation model; turning the master switch off stops the LLM entirely while capture keeps working. Failures are surfaced in the prompt and in status.md instead of being swallowed. Pure JavaScript, no third-party runtime dependencies beyond the harness packages.

Browse, preview and install public Agent Skills from inside the DSH web GUI, aggregating five sources (claudeskills.info, skillsmp.com, the awesome-claude-skills repository list, the official anthropics/skills repo, and skill packs shipped by installed DSH plugins). Skills install pinned to a commit rather than a branch name, so what you previewed is what lands; the panel reports provenance, whole-tree update checks and a trash instead of deleting. Before writing anything it validates the skill name and frontmatter against the rules the harness silently enforces, lists files that SKILL.md references but the fetch did not bring, flags partial fetches, and offers overwrite, rename or skip when a name is taken.

Pulls GitHub repo content into DSH conversations at start and writes extracted long-term memory back with SHA-locked multi-file commits at conversation end; per-file read/write permissions, native settings page, turn indicators and global change notices.

Set an earlier automatic-compaction threshold per model on DeepSeek Harness: /autocompact writes a session-only override keyed by exact provider/model (off falls back to the backend defaults, default clears it), a Settings → Autocompact page manages the persisted per-model thresholds every session inherits, and a composer status entry shows the current reading.

A Neon Genesis Evangelion-inspired skin for DeepSeek Harness: Title Card (light) and Central Dogma (dark) modes over one removable override layer, 55 measured color tokens, a wallpaper paint layer whose two surface alphas are solved against a WCAG contrast budget, a boot mask and a brand mark. It also rewrites the sidebar identity line, replaces the new-session heading, hides six official entries, and reshapes the composer control row. Unofficial fan work, non-commercial: the background pictures are fetched from third-party URLs at paint time, not shipped in the repository.

Cursor and GitHub PR Review style selection toolbar: quote selected text to chat (Cmd+L), write inline comments (Shift+Cmd+L), and batch-insert from a composer dock.

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

Select a term in a DeepSeek Harness conversation and press the Search button beside it to read the explanation in place: basic meaning, purpose and usage, with the token cost of that answer. The call is auxiliary — it writes nothing to the session log.