Plugins

Evolve skills, agents, prompts, code and plugins from inside DeepSeek Harness, with AgentDescent.

许愿特化器 · Wish Specializer — DSH 插件：让模型更出色地，不误解你的意思地，完成你的“愿望”。在短提示词+自带的Wish预设（PTC也可以）+重度的情况下，可以起到巨大的表现增益

DSH Web 输入框接管（v0.3.0-beta.4 · 复杂任务能力包：3D/法向量/交互/数据/并发/性能细节逐项过关 + 可自动化验收 + 中英双语 · 适用于 dsh-0.1.6-alpha.1）：发送前用独立 AI（传话者）把提示词优化成可直接发给工作 AI 的命令（四档强度、按难度定流程长度、按会话隔离、极简迷你窗）

Adds an optimize button beside the composer that analyzes and rewrites the prompt draft with SSE streaming, conversation-context awareness (template vs intent-polish strategies), an edit-continuity memory chain, undo, and model routing with fallback and a connectivity test.

One-click optimization of a raw instruction into a professional prompt: three output styles, situation-aware role/task/goal profiling, multi-sample selection scored by a model judge, self-iterating learning (session memory + smart defaults + user overrides), /template for 22 sub-scenes with zero model calls, input-box ✨ one-click optimize/undo, prompt_optimize tool, auto-optimize hook, a runtime status page, a settings panel (dsh 0.2.0) and auto-detected zh/en documents.

Token optimization for DeepSeek Harness with searchable MCP tool discovery and lazy loading, configurable compaction controls and status reporting, tool-output reduction, long-text vision summarization, and opt-in conversation archiving with paginated retrieval.

Per-round reasoning_effort optimizer for dsh — auto-downgrades reasoning for simple tool calls and lifts back for heavy work, cutting thinking time between tool calls.

Turns a one-line DSH draft into a complete task brief (role / goal / constraints / output format). The engine is a byte-verified port of linshenkx/prompt-optimizer (three modes, 10 templates identical to upstream); history is consent-gated with version chains and structural comparison; every run reports its token usage. Nothing is written back or sent without a click.

Layered token-optimization pipeline for DeepSeek Harness: output ladder, MCP lazy loading,compaction driver, cache-hit reporting. Built on real DSH plugin APIs; ~40-60% input saved in long sessions.

模型路由与成本优化器：简单问题 flash 直答、故障自动降级、会话 token/缓存/成本实时面板 | Model router & cost optimizer for DeepSeek Harness: flash quick-answers for simple questions, failure fallback, live token/cache/cost panel

Network optimization for the DSH web UI: reduces transfer size with caching and compression to greatly speed up page loading, plus a connection-drop indicator and automatic reconnection. Ideal for users pursuing peak performance or using unstable networks.

Polishes the draft in the composer into a clearer, better-structured prompt from the ✨ button or Alt+O; streams the result live over SSE with reasoning shown first, and follows the session's default model with zero configuration or any OpenAI-compatible endpoint.

Agnes image and video generation for DeepSeek Harness: two agent tools, an AI prompt optimizer, and a sidebar panel whose API key is entered in the panel and never shipped in the code.

Behavior-management plugin for DeepSeek Harness: tool-call discipline prompt section, failure-triggered parallelism convergence (pool drops to 1, auto-restores), consecutive-failure user intervention. Complements dsh-token-optimizer; works standalone.

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.

Agent-structured prompt optimizer for DeepSeek Harness: rewrites composer drafts into role/task/context/constraint/format with normal, slim, and expand modes, a confirm modal with score, continue-optimize, and local, hybrid, DSH, or cloud-API engines.

Input-bar prompt optimizer: rewrites drafts with 6 strategies × 3 languages plus custom instructions, optional goal/todo/compaction-summary/tool-result and chat context, a confirm dialog, last-5 history and three-tier settings persistence.

Adds an icon button to the composer that optimizes the current draft prompt through the active model.

DSH plugin: mark messages as invalid so an operator annotation digest steers what a compaction checkpoint absorbs. Cache-preserving: appends after the cached prefix, never rewrites history.

Adds an Optimize prompt control next to the composer send button that rewrites the draft into a structured prompt (plain, sections, or role-task-goal) streamed from the session model, with Use, Undo, Copy and Close.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

Browse 90 prompt methods with usage guidance and sources, insert a selected requirement, or compare and edit a full rewrite before applying it in the DSH composer.

Rewrites the composer draft into a tighter prompt in one click and restores the exact original in another, running on Harness's own models by default or any OpenAI-compatible endpoint, with an editable polishing prompt.

Rewrites the composer draft into a precise prompt with a configurable model and a fully editable rewriting instruction; reads the content behind @file, @folder and @session references for context and keeps the reference chips intact; offers a one-click undo that restores the text you wrote yourself, and places the button in either composer toolbar with an adjustable colour and size.