Every DeepSeek Harness plugin

What it is — This plugin translates images into structured coordinate-based text descriptions to enable text LLMs image understanding.

Who it is for — When using DeepSeek Harness text models to analyze images in conversations, this plugin provides pixel-level image understanding via the mm_vision tool. If your model does not support visual tool calls or you do not intend to use the mm_vision tool, you can skip installing it.

Watch out — Sandbox test passed: installed in a new profile and registered by harness. Scan found it will execute shell commands. No obvious pitfalls detected.

The verdict — I would install it because it uses a zero-dependency core to implement the mm_vision tool, but under the premise of using an OpenAI-compatible vision model.

What it is — One-click batch installation and configuration of curated DeepSeek Harness plugins.

Who it is for — New users of DeepSeek Harness facing community plugin selection issues. Users who rely only on npm prebuilt plugins can skip it.

Watch out — Sandbox test passed: installed in a new profile and registered into the profile. It will execute shell commands. No obvious issues found.

The verdict — I would not install it because it will execute shell commands.

What it is — dsh-chat-tidy plugin adjusts DeepSeek Harness conversation page layout to Codex-measured metrics.

Who it is for — If you need tighter reading rhythm for coding-agent tasks in DeepSeek Harness, you can install this plugin. If you prefer the default loose spacing or have installed dsh-ux, skip it because of override conflicts.

Watch out — Sandbox test passed on a new profile and registered successfully. No obvious issues found. Use one layout plugin at a time with dsh-ux to avoid conflicts.

The verdict — I would install it because it offers measured before-and-after comparisons to optimize conversation density.

What it is — Quality-aware in-agent plugin discovery tool for DeepSeek Harness.

Who it is for — In DeepSeek Harness when using the Agent to search for plugins, this tool is suitable to use. Users who do not use natural language interaction with the Agent do not need to install it.

Watch out — Installing from GitHub source code. Sandbox test passed: installed in a new profile and registered into the profile. No obvious issues found.

The verdict — I would install it because it merges a daily quality-scored index with live GitHub search.

What it is — This plugin provides reusable Markdown prompt profiles for DeepSeek Harness that support per-turn model selection, argument substitution, and state restoration.

Who it is for — When you need to repeat model selection and prompt instructions in DeepSeek Harness, this plugin supports single-turn invocation and state restoration. If your workflow does not involve replacing arguments from the command line, you do not need this plugin.

Watch out — Sandbox test shows that installation from source requires manual permission for the build script before harness can complete registration. No other issues found, but the plugin will execute shell commands.

The verdict — If I were you, I would install it because DeepSeek Harness supports per-turn model selection and this plugin provides state restoration support, but you must manually allow the build script.

What it is — Syncs DeepSeek Harness plugin manifest to GitHub Gist.

Who it is for — When managing multiple DeepSeek Harness profiles and needing to sync plugin manifests to GitHub Gist, this plugin is suitable to install. If your workflow does not involve GitHub Gist for syncing DeepSeek Harness plugins, you can skip this plugin.

Watch out — The plugin executes shell commands during profile installation. Sandbox test passed, successfully installed in a new profile and registered by harness.

The verdict — I would install it because it supports syncing of plugin manifests to GitHub Gist, but the premise is accepting execution of shell commands.

What it is — dsh-speak plugin for DeepSeek Harness, announces final reply via voice.

Who it is for — When using DeepSeek Harness for long coding tasks and wanting voice prompt on completion. Users who prefer text-only logs without voice features do not need it.

Watch out — Sandbox test passed: installed in fresh profile and registered by harness. No obvious pitfalls found. The project stresses best-effort execution that will not interrupt sessions.

The verdict — I would install it because it offers a verified solution for voice announcements on long tasks.

What it is — This plugin bridges messages from WeChat, QQ and Feishu to DeepSeek Harness agent sessions and supports proactive push to wake bots from scheduled tasks and deliver AI replies to your phone.

Who it is for — If you need to wake channel bots from scheduled tasks and deliver AI replies to your phone, install this plugin. If you mainly use DeepSeek Harness built-in chat interfaces and do not need external IM channel integration, you do not need to install it.

Watch out — Sandbox testing shows it can be installed but protobufjs@7.6.5 is blocked by pnpm, preventing full harness registration; manual build approval is required for source installation. No obvious pitfalls were found.

The verdict — I would install it because it provides proactive IM push and remote monitoring, but I must manually allow the build script to install it.

What it is — Enables image recognition for pasted pictures in DeepSeek Harness.

Who it is for — When you use DeepSeek Harness to handle code screenshots or UI prototypes, it fits. If your work does not require structured evidence or cross-session memory reuse, you can skip it.

Watch out — Sandbox test passed in a fresh profile and registered by harness. It will execute shell commands. No obvious issues found.

The verdict — I would install it because it supports cross-session visual evidence memory and content-hash caching.

What it is — This plugin creates independent sidebar containers for open-mcp-apps applications in DeepSeek Harness web profile.

Who it is for — If you are managing multiple open-mcp-apps applications in DeepSeek Harness web profile and need each to have its own workspace and session, then this plugin suits you. If you are using a non-web profile, then this plugin is not suitable.

Watch out — Sandbox testing passed, no obvious issues found. The plugin executes shell commands to manage app containers. You need to ensure that the open-mcp-apps engine is running.

The verdict — If I were you, I would install it because it supports independent containers for open-mcp-apps applications in DeepSeek Harness web profile, but only if the open-mcp-apps version is 0.5.1 or newer.

What it is — Perlica-themed DeepSeek Harness plugin delivering tiered terminal notification sounds for task states.

Who it is for — Users performing agent tasks with DeepSeek Harness are suitable for installing this plugin. Those who prefer complete silence can skip it because they may focus more on text-based interactions.

Watch out — Sandbox test passed: installed into a new profile and registered by Harness. It executes shell commands to play sounds. No obvious issues found.

The verdict — I would install it for agent workflows needing state feedback, because it offers targeted audio cues, yet only if background playback is allowed on my platform.