Plugins

Multi-language codebase intelligence for MCP-compatible IDEs, the CLI and DeepSeek Harness: chat, search, audit, refactor, and board-ready reports from local code.

Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.

Ultra-lightweight Moli (Rust headless browser) web-fetch provider for DeepSeek Harness: renders complex SPAs, micro-frontends, and dynamic pages with ~60MB memory.

Fork companion for DSH: on any official fork, copies every direct subagent child of the source session onto the forked conversation (recursively, whole subtrees) through the official agent API, leaving each copy as a cold session the official resume path can wake — so the new conversation keeps its subagent panel and can keep messaging those children, while the originals stay with the old branch.

Configurable send and newline keys, a composer context menu with three sources (leave it to DSH and other plugins / browser menu / plugin-styled custom menu), a quick-command panel with categorized prompt lists where each prompt can append on every send or only on the first message of a session, a create-and-move row at the bottom of each category, a prompt optimizer that rewrites the draft with a separate model call, settings-panel size memory, and automatic x-opencode-session header injection for OpenCode routes. Prompt lists live in a global ~/.dsh/quick-prompts.json that is independent of the session and the project.

Zero-config lint feedback loop for JS/TS, Python, Go and Rust: lint_diagnostics / lint_workspace_errors / lint_fix tools driven by the repo's own eslint / biome / ruff / golangci-lint / cargo clippy (auto-detected from config files, repo-local node_modules/.bin resolved first, nothing bundled), plus an auto-injected post-edit findings delta on the harness fs/observed event and a bounded completion gate — edit → lint → auto-repair with one lint_fix call for dsh agents.

Multi-language codebase intelligence for DeepSeek Harness and MCP-compatible IDEs: chat, search, audit, refactor, and board-ready reports from local code.

人脑式上下文压缩逻辑，大幅减少长任务上下文占用以及token消耗

Compresses DSH time-context from ~280 chars to 46 chars by injecting a compact date line into the runtime-context snapshot; zero runtime dependencies.

DSH web plugin: a sidebar footer QR-code button that lets a phone scan and re-issue the current browser's authenticated launch URL, reusing the same ?token exchange the desktop just completed.

Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.

A better approach to editing files in DSH.

Plugin development toolkit for DeepSeek Harness with scaffolding, contract checks, plugin vetting, impact analysis, and upstream compatibility tracking.

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes you can open in Obsidian; query your history, browse recent reads, or search your own Obsidian vault and link related notes to a reading record. Nine tools, a /codevault command, and a code-reading skill.

Pre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.

Side-ask drawer opened from a completed answer's action row: follow-up questions run in an independent, auto-archived session seeded with the prior conversation text (read-only, capped at 48,000 characters), leaving the main session untouched. The side session inherits the main session's model, switchable inside the drawer, with a context-usage ring.

ClineBot and ClinePass integration for DeepSeek Harness: dedicated settings page, live quota dashboard, in-UI key saving, curated and custom model selection, and a /cline command.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Pins every request to the native max-effort tier and adds a per-model/per-mode reasoning-depth panel with a 0-20 capability slider, isolated Velocity/Apex profiles, and offline reasoning toolboxes. Distributed as an obfuscated build; commercial use allowed, reverse engineering closed.

Request-level one-time prompt injection without further context pollution. SillyTavern-style UI and data compatibility, keyword/regex/constant triggers, and a lore_lookup tool for on-demand searching.

Um painel de orquestração estilo RTS onde comandos substituem chats: um agente comandante residente decompõe cada ordem em briefings de tarefas com critérios de aceitação, tropas de subagentes tipadas (recon/engineer/medic/scribe) as executam em workspaces isolados, e cada sessão é indexada pela ordem que a iniciou.

Agent ao nível de projeto autoevolutivo para DeepSeek Harness: 16 habilidades de fluxo de trabalho SDD (esclarecimento, PRD, issue, codificação, localização, aceitação, revisão) além de memória e conhecimento de projeto que se acumulam com o tempo.

Reconhecimento de imagens configurável para modelos DSH somente de texto: as mensagens de imagem são primeiro transcritas por um modelo de visão compatível com OpenAI (URL base, ID do modelo e chave API definidos numa secção de Definições) e depois passadas ao modelo principal como texto, enquanto o suporte a entrada de imagem é anunciado. O esquema de autenticação por chave API é selecionável (cabeçalhos de pedido estilo OpenAI, Anthropic, Gemini ou Azure) e a falta de uma chave é comunicada antes de qualquer pedido ser enviado.

Upload de arquivos por arrastar e soltar no compositor de conversa, pílula de uso de tokens com rastreamento de cota e gerenciamento de arquivo de sessões — um add-on três-em-um para o dia a dia.