Plugins

Customizable brand area for the Web UI: replace the whale logo and DeepSeek wordmark with local images, and edit the HARNESS badge text (double-click to change, right-click to reset).

Adds an Auto Approve permission preset to the Web UI, using a fresh restricted Reviewer Agent to allow or deny each approval request.

OpenCode Go quota ring: click-to-cycle progress ring (5h/weekly/monthly) left of the model selector, colored by urgency, with reset countdowns on hover.

DSH side of Blind Whale Farmer, a SMAPI mod in the same repo that lets an AI play Stardew Valley from a text game state through MCP tools: syncs play limits and extra instructions to the running game, adds an optional session preset or a single stardew gateway tool (both off by default), and sends "keep playing" when a Stardew session ends on a tool call that came back as plain text. Needs the mod installed in the game.

DSH plugin bundle: workflow skills, engineering presets, independent better-goal / better-subagent / better-compact / better-ask-user integration, and a minimal job exit guard. Pure ESM, no build step.

Settings page for the REA reverse-engineering tool gateway (rea-mcp-lite) that lives in the same repository: pick which tool bundles load into context, see the tool count and token cost of each bundle, save and recall named presets of your loading setup, hot-swap them without restarting DSH, and check this repository and REA for updates, including classifying the tools a new REA release added. The page is split into sections with sub-menus, filters and pagination. Requires REA (rea-agents) and the gateway registered as the rea MCP server (see repo README).

Standalone Network Engineer Assistant agent preset plus a bundled 32-doc command knowledge base skill for DPtech, H3C, Huawei and Ruijie switches and routers: KB-first retrieval, cross-vendor command translation, topology and CLI-output screenshot reading, online manual lookup with cited sources, and mandatory risk annotations for dangerous commands; answers networking topics only.

Manage tool availability and groups for each Agent Preset, load tools on demand like Skills, and reduce model context usage.

Customizes the native settings window: preset or custom window sizes, fullscreen, background transparency, and theme, solid-color, or image backgrounds, with a floating ball for quick access; saved in the local browser.

DIY the DSH UI typography and colours: 10 built-in regions plus box-select region creation, each with its own Chinese and English font, size, line-height, weight (100-900), italic switch and text colour picker; 18 Chinese and 18 English fonts ship in the pickers, every region can be overridden by one unified setting, and named theme presets can be saved, applied, renamed and deleted. Random font assignment and random colour generation work for the whole UI or per region, and 8 fonts (LXGW WenKai, Smiley Sans, ZCOOL KuaiLe, Comic Neue, Baloo 2, Fredoka, Nunito, Caveat) can be downloaded and installed with one click (only Comic Neue ships in the package) alongside your own .ttf/.otf files, with a factory-default reset that restores the shipped palette. A 字 floating ball opens the panel, which carries a collapsible quick-start guide, and position and settings persist across restarts. The ball is shown or hidden from the DSH settings floating-ball section together with the other two balls, which share one 130-skin catalogue with a per-ball sync switch.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Installs an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.

Runtime extension suite for DeepSeek Harness: cross-session mailbox with wake cold-start, agent teams (captain + members + dependency task board + team_wait), subagent spawn policy with escalation approval, task-aware routing preset, plugin market, skill manager and runtime injector.

Virtual product team agent preset: user-led conversation walks you through the full 12-step pipeline from idea to shipped, promoted and operated product, with staged gates and per-stage skills.

DSH Web background settings: upload a local image or pick a preset ambiance, with live preview and persistent settings.

Client-side writing panel for the Web UI: project volumes and stats, corpus library, full-text search, evolution version-chain diffs, and an SVG thread graph, shown only in writing-preset sessions.

Adds a "Task Planning" agent preset that asks requirements in versioned rounds, then writes step-by-step plans and prompts without implementing them itself.

Drive FilmCraft from the agent: build a project and sequences, import media, run edits as a script, then export with a preset or format. Exposes FilmCraft's command ids and its MCP server. Requires the matching ArtCraft app CLI installed locally; it is not bundled.

Self-evolving agent framework on DeepSeek Harness (dsh): 40 Cordis plugins and 4 presets covering memory, reflection, gates, metrics and an auditable evolution loop. Not a one-command install. Clone the repo and run install/install.sh --profile=web (needs bash, Node 20+, python3, DSH 0.1.7-rc.1 or newer with an initialized profile), then restart.

Codex, Grok Build, Cursor, Pi and ZCode presets with native conversations, code review, document conversion and workflow controls.

SapBuddy —— SAP ABAP AI 全能助手（DeepSeek Harness 插件）：41 个 SAP 工具 + 8 个 ABAP 技能 + SapBuddy preset + 连接设置页。一个包名装完。

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.

Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.

Adds a reasoning-level editor with OpenAI and Anthropic protocol presets (llm-pi-ai), input-modality switches and a 1M/128K context and max-output preset to model rows in Settings.