Plugins

Let the Blue Big Fat Fish browse Bilibili for you: it comments on your behalf, DMs you interesting finds, writes a diary, and keeps a memory for long-term summaries. It filters videos to your taste, creates Markdown digests, and can watch comments and reply for you. In Circle Mode, it replies only inside threads explicitly invited by the video uploader in a top-level comment — ordinary viewer requests do not count, and it never starts a new top-level comment. Commenting, DMs, auto-run, and comment watch are off by default. Needs Node 22, DSH 0.1.7-rc.1+, a signed-in Bilibili account, a model route and Python.

A visual workbench for reference-image generation, cropping and component-wise Tripo 3D modeling, with per-task paid-operation approval and local asset previews.

Factory (Droid) subscription quota as native DSH model providers, with three protocol routes, your own API key through a loopback gateway, and a settings page for connection status, quota, per-model token statistics and key switching.

MCP bridge that lets ChatGPT Web create, view, continue, and supervise DeepSeek Harness agent sessions and goals while preserving DSH's native approval, sandbox, and workspace security model.

Image generation and image reading for DSH: a 创作 sidebar page (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. Requires Python 3.9+ (generation runs through scripts/generate.py); the 创作 page needs desktop DSH 0.2.1+.

Design workbench in the right sidebar. When the model builds web pages, app screens, WeChat mini programs, posters, slides or emails, each HTML file shows up as a screen on a canvas inside a device frame and refreshes when the file changes; local dev servers are proxied with hot reload intact. Mini program screens get the WeChat capsule in the top-right corner, which turns white over a dark top bar, and the design check flags text and buttons hidden under it. Click an element or drag a region to put its selector, source file and styles into the composer. It can extract a brand design system from your website or project (colors by role, fonts, type scale, radius, shadows, buttons, inputs and cards) and use it for every new design. The model adds a few tweak sliders to each design (spacing, radius, brand color, layout variants) that update all screens live and write back to the stylesheet in one click. A finished design can be turned into React, Vue, Next.js or plain HTML code, with each built screen diffed pixel by pixel against the design. Also has a design tokens panel, fifteen style presets, a style panel (font size, colors, radius, padding and more) that writes back to the HTML or hands the change to the model together with the CSS rule and line behind each property, versions saved before and after each turn with drag-to-compare and restore, export to images, PDF and PPTX (links between screens stay clickable), a LAN QR link for viewing on a phone, link arrows and a click-through demo mode, a multi-size view, in-place text editing, reference-image palettes, and a design check (overflowing, clipped or overlapping text, contrast, tap target size and more). Bundles a ui-design skill and six tools: preview_page opens a preview; check_design measures every screen at real sizes in a hidden local Chrome or Edge (bars covering content, script errors, missing assets, dead links; CSS file and line for contrast and font-size issues; cropped screenshots of serious problems); look_design hands real screenshots to the model; extract_design_system builds a design system from a site or project; handoff_design writes a handoff pack (screenshots, routes, tokens, shared components); compare_design diffs the built local page against the design and marks what differs. Adds a Design mode for new sessions (Standard mode's tools plus the skill, the six tools and a design persona); each part has its own switch on the Plugins page. When DSH is opened from a phone or another computer, local-file designs are bundled into a sandboxed frame so they still show.

Per-model appearance for the DSH Web UI: an ordered rule list matched against the current session model name, each rule carrying its own wallpaper, theme colour, layout mode, framing and wallpaper opacity and blur, plus per-surface opacity and frosted-glass blur for the main background, left panel, right panel, cards and panels, input and controls, settings panel, conversation text frame and trajectory view.

Terminal-native TUI frontend for DeepSeek Harness that presents sessions, models, plugins, jobs, subagents, todos, and provider configuration through Harness capabilities while preserving real terminal scrollback.

MCP server manager for DeepSeek Harness: add, edit, enable/disable, restart and delete MCP servers from Settings → MCP 管理, with JSON export/import, four mcp_manager_* model tools and an HTTP API; install via npx, npm or cross-platform scripts.

Ollama provider for DeepSeek Harness with model management, health checks, rule-based local routing, and cloud fallback.

Interactive terminal UI for DeepSeek Harness: tables, Mermaid and chart rendering, side conversations, and the same Cordis plugin model as dsh Web.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

Free model provider plugin for DSH with 20+ models including Gemini, MiMo, GLM, etc.

Full-screen terminal client for DeepSeek Harness built on pi-tui: session replay/resume, streaming responses, collapsible tool cards, in-terminal approvals and questions, model/preset/permission/plan/goal management, shell mode, and a trajectory ledger.

Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.

Per-subagent LLM provider/model selection with role templates.

Create and manage sandboxed JavaScript tools with a Monaco editor and model-driven tool lifecycle.

Pools every WorkBuddy account signed in on this machine into one auto-failing-over provider, serving OpenAI Chat, OpenAI Responses and Anthropic Messages from the same pool, with model aliases, usage statistics and scheduled credit automation.

A UX enhancement pack for the DSH web chat: one plugin that collects small interface conveniences, each with its own switch under Settings → UX Plus applied immediately — chat-area font size and reading width under Settings → General → Chat area, a session-row menu that copies the session ID or inherits the conversation into a new session on a chosen model, workspace and session rows ordered by recent activity with 24-hour idle auto-collapse and age labels, and settled ask_user_question cards left expanded. The switch list is generated from its own feature registry, so the pack grows as conveniences are added instead of being fixed at a count.

Second model passively reviews each turn and injects notes.

A Claude Code-style reasoning-effort slider for the DSH Web UI: stepless drag, snap-on-release, a WebGL fire trail, and real, working thinking-effort control for any custom third-party model or provider.

Security-audit methodology skill pack plus the plugin_vet supply-chain gate: eight agent skills (secret scan, dependency audit, supply-chain review, prompt-injection review, audit orchestration, threat modeling, vuln intel, incident response) in Chinese and English editions, with an npm provider bundle that mounts the skills and registers the automated plugin_vet pre-install scanner.

Transparent rankings and recommendations for the DSH plugin ecosystem: daily auto-fetched topic data, an open scoring model, and rank/search/recommend tools with a settings-page leaderboard.

Provides a better model experience, including but not limited to: filling model parameters in multiple ways, improving model compatibility, remembering reasoning efforts, subagents following the parent's model and reasoning effort in real time, and AI self-adjusting reasoning effort.