Plugins

Runs persistent bash and Linux-path file and search tools inside the current WSL distribution. A new conversation that selects WSL mode asks which of that distribution's folders to use as the workspace, and nothing is installed inside the distribution.

A biomedical Research Graph grounded in literature and experiment results. Fork hypotheses, connect evidence, advance research.

Runs a Douyin subagent that browses videos and reads comments in valley hours and reports back, with dy_* tools for publishing and replying (comments sent from the already-logged-in page with its own request signature, no IM ticket), a daily quota timer, and a settings panel under Settings → Douyin: master switch, auto mode, valley windows, rounds per day and report depth. Windows-oriented; needs the separate douyin-mcp binary (yunsur/douyin-mcp releases, path set via dy_config mcpExe) and an Edge/Chromium login; replying needs a logged-in browser on a CDP port; publishing needs extra credentials most accounts lack.

A bundle of molbio tools for molecular biology work:sequence analysis, primer and probe design (qPCR, TaqMan), in-silico PCR,cloning simulation,plasmid maps,sequencing validation,protein and CRISPR analysis,qPCR statistics,literature and lab records;installed as a preset-scoped bundle.

Local-first memory and persona plugin for DeepSeek Harness: four file-backed memory layers (pinned, memory, facts, experience), editable SOUL/MOOD persona, zero-LLM session capture, BM25 recall and a themed mood card; no standalone web panel, Python service, vector database, or API key.

Context governance for DSH: folds oversized tool results, collapses the tool surface and keeps the prompt cache warm, so long sessions stop getting more expensive.

Continues work across coding agents inside DeepSeek Harness: six sessionflow_* tools query a local session index built by sessionFlow to find past work, show where the current project left off, and hand the goal, files and open items to the next agent. Requires the separate sessionFlow core, installed from its GitHub repo. Everything stays local — no cloud, no telemetry.

Locks the model's reasoning, replies and tool-call descriptions to a chosen target language (Simplified Chinese by default) with system-prompt sections at the head, middle and tail of the prompt, offering three strength levels, an auto mode that follows the DSH interface language, a settings panel that shows the language currently in effect, and a sidebar quick switch.

Reuses the sign-in already held by the local Doubao desktop app as a DeepSeek Harness model provider, and adds a read-only quota view for the 5-hour and weekly windows. Windows x64 only: the credential is decrypted with DPAPI.

Requires the ZCode CLI installed and signed in. Relays the ZCode CLI agent into DeepSeek Harness as a model provider. A resident app-server session streams each turn, and the model catalogue is read from the CLI at runtime, so context windows, image support and provider routes follow the installed CLI and account. Stable 0.5.1 declares DSH compatibility through engines.dsh; ZCode CLI 3.16.3 is the documented reference version. Tool permission requests are denied by default; unknown approval or permission methods are always denied, and full-auto requires an explicit opt-in. DSH approval UI does not mediate this separately spawned app-server process, and the policy is not an OS sandbox.

Model channel auto-enricher for DeepSeek Harness: eliminates manually configuring contextWindow, maxTokens, \[text, image] multimodal input, and {low, high, max} reasoning effort tiers model by model after adding a provider channel, with live auto-enrichment on save, a Settings UI page, and timestamped backups.

Arknights PRTS Originium Protocol theme featuring interactive 3D crystal, tactical HUD, memory fragments, and boot sequence.

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.

An Everforest colour theme for DeepSeek Harness, for both web and desktop. Forest tones, with six dark and light palettes. Chat content (headings, code, links, tables and more) is restyled with independent colours, and every tone and saturation level is tuned individually for a warm, gentle, easy-on-the-eyes experience.

Token usage dashboard in the DeepSeek Harness sidebar: daily totals from session logs with a 12-month heatmap, per-provider breakdown over today/7d/30d/all (hourly for today) including each route's average output speed, and a per-session ranking that includes archived and deleted sessions and folds subagent usage into its parent.

Per-turn tool cost line in the chat stream: after each turn a collapsible row under the reply lists which tools ran, how many times, and how many tokens each tool injected into the context (input plus output), expandable to per-tool detail.

Shows your DeepSeek balance and what the current session has cost in a corner overlay, with budget alerts, peak-hour warnings and opt-in official price sync.

Usage panel on the blank-session hero: sessions, messages, total tokens, active days, peak hour, favourite model and a contribution heatmap, over all time, 30 days or 7 days.

Per-turn first-token latency and output speed beside the built-in usage pill, folded on the host over the durable event log: first-token time is replayed from each message's compact stream, so historical turns stay exact after a reload rather than showing an estimate.

Provides an always-on-top window feature for the DSH window, preventing it from being hidden unexpectedly, Windows only; requires PowerShell 7 (pwsh.exe) on PATH.

Separate font slots for content, code and terminal text, plus an interface font, an interface-size stepper and an inline-code size stepper, with line-height and letter-spacing controls. Typography only — it never touches colour.

Next-prompt suggestions: after each answer it predicts your next message as grey ghost text in the composer. Tab fills it without sending, and the prediction model is selectable.

Generative UI: the model calls render_ui with a React snippet and the answer renders as an interactive card in the conversation. The snippet runs in a sandboxed iframe with an opaque origin, so it cannot read the host page, its storage or its cookies, and the frame CSP blocks the network; a message from a card is only sent after the user confirms it, and a failing card shows its error with the source behind a toggle.

Predicts your next message after each turn and shows it as gray ghost text in the composer: Tab takes the whole line, Alt+Right takes one word at a time, Enter takes it and sends, Esc dismisses, and Alt+R asks the model again without repeating the old one. Typing a few characters completes from prompts already sent in the session, Up in an empty composer recalls the last one, and a plugin-page form sets the provider, model, reasoning effort, per-key toggles and generation limits.