Плагины

Dead-code detection for AI-generated codebases: graphlint builds a dependency graph, finds code unreachable from any entry point to enable codebase cleanup and functional‑effectiveness understanding, and exposes graphlint_query / graphlint_build / graphlint_config tools plus a graphlint skill to DSH agents.

GitHub Device Flow connect plus an in-conversation PR workflow: a status bar above the composer for create / AI-review / merge, and github_* tools for search, issue and PR read and write.

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

Web UI polish layer for DeepSeek Harness: normalizes unfinished or self-contradictory official UI, reconciles style conflicts between installed plugins, and unifies the visual language via official design tokens; live-customizable chat width, markdown font size, workspace scale and UI font stack.

Визуальный магазин плагинов для DeepSeek Harness — просматривайте, ищите и устанавливайте плагины сообщества

Плагин deepseek harness для песочницы tensorlake

DSH Relay превращает Telegram в удалённый канал общения и уведомлений для DeepSeek Harness.

Менеджер сессий DSH: управляйте диалогами, архивируйте/восстанавливайте, безопасно удаляйте, открывайте папки записей.

Плагин DeepSeek Harness: дополнительные рабочие директории для проекта. Агент сохраняет основное рабочее пространство как cwd, получает равные права записи/выполнения в настроенных дополнительных директориях в режиме workspace-write и уведомляется об изменениях конфигурации

Тестовая среда оценки для плагинов DSH: YAML-кейсы запускают реальные безголовые прогоны агента, проверяют вызовы инструментов, аргументы, результаты и использование токенов, с базовым порогом для регрессий в CI.

Плагин, добавляющий десктопного питомца в DeepSeek Harness, с поддержкой формата питомцев Codex; добавляйте своих питомцев через hatch-pet или Petdex.

Напоминания о внимании: значок на рамке, счётчик в заголовке вкладки и фавикон-кит, окрашенный по статусу, для сессий, ожидающих ввода или завершённых без просмотра.

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

Use DSH from iPhone/iPad: an explicit-opt-in LAN reverse proxy (Host/Origin rewrite through the loopback trust fence, WebSocket upgrades included), iOS PWA chrome (home-screen icon, standalone meta, viewport-fit), and touch/mobile CSS (safe areas, keyboard lifting, composer row fit).

Vets third-party plugins before you trust them: static scan for malicious patterns (exfiltration, credential access, obfuscation, persistence) and over-privileged path use, transitive-dependency coverage, official-package hash baseline for supply-chain tamper detection, and an optional plugin-tool call gate.

Fine-grained permission gateway: per-category tool-call review (outside-workspace directories, commands, file read/write, subagents, repeated actions) with global & per-project allow/deny exceptions, quick-tool defaults, custom rules, a bilingual approval modal with inline diff details, custom rejection reasons and a sandbox-upgrade flow.

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

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.

Desktop notifications for run completion, model questions, and approval requests with per-platform system sounds, zero runtime dependencies.

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.

Workspace-safe Office tools for agents: create/read Word, create/read/update Excel, and create/read PowerPoint decks with PNG/JPG/GIF image placement.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.