Plugins

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.

Marketplace visual de plugins para o DeepSeek Harness — navegue, pesquise e instale plugins da comunidade

Um plugin do deepseek harness para o sandbox Tensorlake

O DSH Relay permite conversar remotamente com o DeepSeek Harness pelo Telegram e receber notificações. O DSH Relay transforma o Telegram em um canal remoto de conversa e notificações para o DeepSeek Harness.

Gerenciador de sessões do DSH: gerencie conversas, arquive/restaure, exclua com segurança e abra pastas de registros.

Plugin do DeepSeek Harness: diretórios de trabalho secundários para um projeto. O agente mantém o workspace primário como cwd, obtém permissões iguais de escrita/execução nos diretórios secundários configurados sob o modo workspace-write, e é notificado sobre mudanças de configuração

Harness de avaliação para plugins do DSH: casos em YAML conduzem execuções reais do agente em modo headless, com asserções sobre chamadas de ferramentas, argumentos, resultados e uso de tokens, além de um gate de baseline para regressão em CI.

Um plugin que adiciona um pet de desktop ao seu DeepSeek Harness, com suporte ao formato de pet do Codex; você pode usar o hatch-pet ou o Petdex para adicionar seus pets.

Lembretes de atenção: selo na moldura, contador no título da aba e um favicon de baleia colorido por status para sessões aguardando entrada ou concluídas sem terem sido abertas.

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.