Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 1668 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-image-routerdsh-image-routerCatalog AnalyzedDigests the images in a prompt with a vision model before admission, so any model — a text-only one included — can read them without the session ever switching models, and adds a describe_image tool for image paths.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.4dsh-plugin-image-inputdsh-plugin-image-inputCatalog AnalyzedImage-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1dsh-deepseek-visiondsh-deepseek-visionCatalog AnalyzedA vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.7screenshot-feedback-hook-mcp#dsh-screenshot-feedback-hook-mcpdsh-screenshot-feedback-hook-mcpCatalog AnalyzedAdds a take screenshot tool plus two optional automatic capture points, putting the screen into the conversation as an image block; requires an image-capable model.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.1dsh-llm-vision-bridgedsh-llm-vision-bridgeCatalog AnalyzedNative LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2SpecWorkflowspecworkflowCatalog AnalyzedRegisters a SpecWorkflow skill pack for requirement clarification, implementation specs, execution, delivery review, repair planning, bug diagnosis, and source-backed research.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-tool-generate-imagedsh-tool-generate-imageCatalog AnalyzedModel-facing `generate_image` tool for text-only models: the model asks for a picture in natural language, Gemini draws it via the Antigravity CLI, the image is saved to a configurable output directory, and the tool returns the file paths for the model to use in its work.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.1dsh-cinematic-workflowdsh-cinematic-workflowCatalog AnalyzedA local-first, human-gated authorial film workflow for DeepSeek HarnessWorkflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0agent-vision-toolkitAnionex/agent-vision-toolkitCatalog Analyzed为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCodeVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-pathifydsh-image-pathifyCatalog AnalyzedLets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.9dsh-vision-toolsdsh-vision-toolsCatalog AnalyzedFull vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2deepseek-vision#plugins/dsh-plugin-deepseek-visiondsh-plugin-deepseek-visionCatalog AnalyzedVision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.2dsh-vision-proxydsh-vision-proxyCatalog AnalyzedDeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit2 reported in bounded auditArtifact0.4.1dsh-automation@michengai/dsh-automationCatalog AnalyzedRuns scheduled coding tasks in isolated DeepSeek Harness sessions, managed from Settings or the agent.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.45@gelomen/glm-vision-plugin@gelomen/glm-vision-pluginCatalog AnalyzedDSH Web Plugin：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + Plugin设置卡片）。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.0dsh-glm-visiondsh-glm-visionCatalog AnalyzedGLM 视觉模型Plugin：注册 glm-vision 供应商路由（glm-4.6v 系列，image+text 输入声明）并提供 glm_vision 工具，让 DeepSeek 等文本主模型直接调用智谱视觉模型看图。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.3dsh-vision-guarddsh-vision-guardCatalog AnalyzedTransparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.3@lijian-ui/dsh-vision-toggle@lijian-ui/dsh-vision-toggleCatalog AnalyzedPer-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.1Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation