Плагины

Named credential manager: the model uses API keys, tokens, and logins by reference; secret values are injected into each shell run as `DSH_CM_*` env vars, resolved per execution, and never enter the conversation.

DeepSeek Harness EAC（DSH）的一只小鲸鱼娘，住在 DSH 界面右下角，帮你盯着 DeepSeek 和 Sub2API 的账户余额。QQ 弹弹，支持拖拽吸附、左吸附翻转、数字滚动动画和余额来源即时切换，随界面自动启用。重点适配 DeepSeek Harness EAC 的 Web 插件机制与设置面板，

AI-for-Science research workflow skill for DeepSeek Harness, aimed at researchers and grad students using agentic AI: multi-angle literature review with per-angle files, experiment design with a caveat list, figures and paper reading; each job returns files plus a cross-verification brief for a second model. Zero deps, MIT.

Cross-session memory for DeepSeek Harness via the official storage domain: memories persist through ctx.storage (storageDomain table) and are injected into the system prompt through a registered section (memory:recall), with memory_save / memory_forget tools so the agent reads and writes its own memory (maxMemories configurable).

Conversation history rail on the left edge of the chat: each tick is one real user request, hover to preview its text, click to jump to that turn.

Select text in a finished assistant reply to add numbered annotations beside the quote; drafts submit with composer text and images as one user message, and the model replies to each annotation in order.

Remotion video creation and verified rendering plugin for DeepSeek Harness

Per-model reasoning-effort configuration for third-party providers: suggestions fused from a model knowledge base and raw /models endpoint evidence with confidence labels, edited inside the official Models page card.

Visual drag-and-drop workflow builder for DSH — orchestrate tool calls, sub-agents, and conditional branches on a React Flow canvas.

Turns each DSH workspace into a project: every new session auto-injects a project-workspace convention (read code before acting, empty folder means a brand-new project); a per-session Project toggle in the composer downgrades the session to a plain workspace with an explicit notice, with the state kept in the session log.

Renders live multi-agent session activity as a pixel-art office in a Web UI side panel - each session is an ox/horse worker typing at its desk when busy or wandering off when idle, with click-to-view work monitors and in-place approval cards.

Anchors an approve/answer bubble to each DSH Web sidebar session row — one-click handling of authorization, questions, plan reviews and blocked goals without opening the conversation.

Message timeline rail for DeepSeek Harness web chat: evenly spaced ticks for each user message on the right edge, click to jump, hover to preview.

Per-file-type multimodal chains: preset processing models per wildcard convert image/video/audio files into prompt tokens before they reach the text-only session model, with per-preset fallback chains and a Multimodal settings page.

A 轨迹解读 (trajectory interpretation) tab that summarizes each user round — what was wanted, how the assistant thought and executed, files/commands/errors — via a rules engine plus optional LLM narrative; user messages stay verbatim.

DSH Web GUI Mod 管理器：按预设/来源包/分类三级浏览，批量热开关、变更预览与撤销、AI 筛选，以及基于任意现有预设创建新预设。

Map dsh workspaces onto Discord — watch every session live, drive and steer agents, and reach the harness's own commands from anywhere, with no inbound port.

Low-intrusion Settings presentation layer for DSH: group plugins, hide single settings / whole plugins, search settings, and restore hidden items — entirely through DSH's additive client-slot + settings-namespace seams.

Cost tracking plugin for the DeepSeek Harness Web GUI — snapshot-anchored per-turn pricing, account balance, and live cost estimates.

Aseprite-style pixel art studio: the AI draws sprites stroke by stroke with selections, layers, animation frames, gradients, symmetry and reference layers, each step rendered live as ANSI terminal frames.

Update copilot for DeepSeek Harness: one scan covers the dsh core, official bundles, and every profile plugin; explains what changed and how risky each update is, then updates only what you confirm.

A structured multi-panelist review workflow for the DeepSeek Harness: N panelists score in isolated subagents, blind to each other; a chair reconciles disagreement by anchor match then Δ-level adjudication; an independent critic audits the process. Works for design, code, paper or project review.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.

Evidence-first vulnerability research workbench for DeepSeek Harness: native audit views, 29 OMV tools, Evidence.v1 findings, reproducible runs, Campaign workflows, and isolated PoC evidence.