Plugins

精准 Token 洞察，实时追踪，智能优化提示和用量归因 Sharp token insights, real‑time tracking, smart optimization signals & attribution

DeepSeek Harness (DSH) 会话内图片渲染插件：全局 show_image 工具 + 点击放大 lightbox。 | Inline image rendering plugin for DSH: global show_image tool + click-to-enlarge lightbox.

Context-window attribution for DSH Web: a Mini Utility Dock panel that ranks the user messages, assistant turns, reasoning blocks and tool results of a session by the tokens each one occupies, so it is clear which entries hold the window. It also shows the share by entry type, the heaviest entries across the live sessions of the host, and, where the host provides them, provider usage and the estimated system/tools/messages composition. The panel is read-only: it does not estimate cost, modify a session, or trigger compaction.

DeepSeek Harness plugin: a model-facing show_image tool that presents a local image to the human viewer in the conversation.

DeepSeek Harness 插件：语音 + 通知出口——agent 通过云端 TTS（火山 seed-tts / 小米 MiMo V2.5，失败自动回退 SAPI）/ 桌面通知 / 提示音主动联系用户。融合 dsh-plugin-notify 的 DSH 原生深度集成与 agent-voice-mcp-minus 的云端 TTS 调优，零 Python 依赖，Windows 原生。

Per-workspace custom system prompts for DeepSeek Harness (DSH): set one active prompt per workspace, captured into a session at creation time, editable from a session-header dialog. 给 DeepSeek Harness 的「工作区自定义提示词」插件：每个工作区一条生效提示词，新建会话时固化注入，会话头部弹窗增删改查。

Bridges WeChat private messages to DSH with two-way text, image, file, and media transfer, aiming to restore the native DSH experience in WeChat.

Standalone mobile surface for dsh: scan-to-pair device trust, realtime SSE sync, three-channel completion notifications (in-app / Web Push / Server酱·Bark·Telegram), offline outbox, approval & question panels, per-provider usage meters, PWA; a native narrow-screen phone UI.

Runtime security guard for DSH: loader import confinement, HTTP Host header validation, and source patch for VM sandbox escapes (4 CVEs). AI-assisted.

Tiered task queue as the single source of truth for DSH↔Hermes work (reset > approve > review): enqueue tools for all submission paths, lease/claim model with concurrency 1, priority aging against starvation, atomic busy mutex, and a Hermes-side consumer (cron */1 + monitor gating) that drains tasks, writes review-handoff requests with single-slot checks, and invokes the reset agent.

Local-first control plane for managing multiple DSH runtimes, profiles, presets, sessions, plans, and knowledge references.

Evidence-first frontend release checks: real-browser content, accessibility, runtime, network, and baseline regression reports with screenshots.

Plays a chime when the AI asks a clarifying question (a `?` / `？` in the message, or an `ask_user_question` tool call). Synthesized via Web Audio API, no audio file, works on every OS.

Task-complete and question notification sounds for the DeepSeek Harness Web UI: a soft chime when the agent finishes a turn, a ding-dong when it asks you something (questions, plan reviews, approvals). Synthesized Web Audio, zero assets, mute toggle and volume slider in the session header and settings.

Jimu (积木): domain-based orchestration plugin for DeepSeek Harness — domain_plan confirmation, per-domain sub-agents with hand-off, and automatic LLM audit.

Turns a product or UI request into an implementation-ready design spec with /ui-workflow and /ui-rerun. Analysts run through a read-only ui_analyst tool, and the lead agent writes docs/ui-workflow reports.

Intercepts turn-stopping to force one critique-and-improve round after each completed turn before the agent stops.

Claude Code style /init command and tool that writes a minimal CLAUDE.md and symlinks AGENTS.md to it.

Scheduled tasks and message push manager: cron scheduling with auto push to Feishu and multi-channel, dual-env (OpenClaw/DSH).

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Model-facing image-generation tool with a configurable channel and normalized image parameters.

Adds image input and recognition through configured DSH providers or an OpenAI-compatible endpoint.

Control, organize, diagnose, design, personalize, and answer product knowledge questions for a Yeelight smart home, powered by the local yeelight-home runtime.