Plugins

Configurable per-turn budgets for supported file mutations, limiting distinct files, mutation calls, and UTF-8 payload bytes before tool execution.

DingTalk IM channel via Stream-mode WebSocket: each chat drives its own tooled agent; replies stream back as messages, no public callback URL needed.

GitHub REST API tools + browser sidebar panel: repos, search, issues, PRs, comments, account binding (credential-store), and one-click clone-as-workspace.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

Analyze a codebase and generate architecture documentation: module responsibilities, dependencies, entry points and run methods.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Provides the bili_summary tool: Bilibili video metadata, subtitle timeline, and sharp-based frame capture with built-in error handling and graceful degradation.

Connects DSH to local Beav for Xiaohongshu (RED/RedNote) and social-media AI operations: topic research, knowledge, copywriting, image, audio, and short-video workflows with approval and artifact tracking.

Floating workspace file-tree browser for the Web GUI with line-numbered syntax highlighting and Markdown preview.

Incremental diff reviewer for DSH: after approving a batch, only new changes since the checkpoint are shown, with a Web review panel and `/review` command that inject feedback back to the agent.

Voice for DeepSeek Harness（dsh） — speech-to-text input + read-aloud TTS for text-only DeepSeek, zero API key.

view modes for deepseek harness, including Verbose, Normal, Summary Mode

deepseek harness manim数学插件

Bring any file into the conversation — stashed to the workspace and referenced by path; zero type rejection

Global skill hub for dsh: aggregates Claude Code, project, and .skill-package skills into ~/.dsh/skills with reference/copy import and slash-menu usage

Rename project conversations into clear, content-based Category｜Topic titles.

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Reusable Markdown prompt profiles for DeepSeek Harness with per-turn model selection, argument substitution, and state restoration.

Scans skills and MCP configs for prompt injection, homoglyphs, hidden Unicode, dangerous shell, and credential leaks.

Jev (TypeSafe System One) gives the human a second opinion, not the agent. When DSH's model asks you a multiple-choice question, dsh-jev-advisor builds a structured Jev request and floats the recommendation, probability spread and confidence beside the op

Free OpenCode Zen models in DeepSeek Harness through native HTTP requests. No OpenCode installation, login, API key, server, container, or LiteLLM is required.

Paper library and reading workbench: arXiv search, a local plain-file library (metadata / PDF / extracted full text), and three-level reading notes (overview / understanding / critique) kept as markdown beside the PDFs; seven model tools plus a web panel.