Qwen-MM-Plugins is a collection of plugins that gives agent harnesses native multimodal abilities, including reading images, video, documents, code, and data. It is used to add these capabilities to coding agents across several supported harnesses, either through local models or multimodal APIs. The catalogue entries are its independently installable skills, MCP servers, and setup instructions.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/QwenLM/Qwen-MM-PluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/qwenlm/qwen-mm-plugins/marketplace)<a href="https://agentmods.dev/plugins/qwenlm/qwen-mm-plugins/marketplace"><img src="https://agentmods.dev/badge/plugins/qwenlm/qwen-mm-plugins/marketplace/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/qwenlm/qwen-mm-plugins/marketplace"><img src="https://agentmods.dev/badge/plugins/qwenlm/qwen-mm-plugins/marketplace.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
qwen-mm-plugins marketplace scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"name": "qwen-mm-plugins",
"owner": {
"name": "QwenLM",
"url": "https://github.com/QwenLM/Qwen-MM-Plugins"
},
"metadata": {
"description": "Qwen multimodal understanding plugins — Agent Skills + MCP servers",
"version": "1.0.9"
},
"plugins": [
{
"name": "qwen-mm-plugins-core",
"source": {
"source": "git-subdir",
"url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
"path": "src/capabilities/core",
"ref": "qwen-mm-plugins-core-v1.0.5"
},
"description": "Read and visualize any file (images, video, docs, 3D, and more), plus image tools — crop, annotate, extract frames — as MCP tools."
},
{
"name": "qwen-mm-plugins-api",
"source": {
"source": "git-subdir",
"url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
"path": "src/capabilities/api",
"ref": "qwen-mm-plugins-api-v1.0.5"
},
"description": "Cloud APIs for understanding media, by model family: VL (vision chat, OCR, grounding), Omni A/V (timestamped captioning, ASR / multi-speaker diarization, temporal grounding, event counting), plus ASR and segmentation (SAM3) — as MCP tools; currently supports DashScope."
},
{
"name": "qwen-mm-plugins-search",
"source": {
"source": "git-subdir",
"url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
"path": "src/capabilities/search",
"ref": "qwen-mm-plugins-search-v1.0.4"
},
"description": "Web search and page extraction via Serper, Exa, or Tavily, plus Serper Lens reverse-image search as MCP tools."
},
{
"name": "qwen-mm-plugins-video-memory",
"source": {
"source": "git-subdir",
"url": "https://github.com/QwenLM/Qwen-MM-Plugins.git",
"path": "src/capabilities/video-memory",
"ref": "qwen-mm-plugins-video-memory-v1.0.3"
},
"description": "Hierarchical graph memory for long-video QA (build + query) as The plugins it lists here
This marketplace lists 1 plugin kept in the same repository. Each has its own page, its own measurements and its own install command.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago Changed · +10 lines 2c2878598080
- 9d ago First seen · 94 lines scan A f12afa16a884
qwen-mm-plugins marketplace is a plugin published in the GitHub repository QwenLM/Qwen-MM-Plugins (2,804 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
manim-skills
Manim (math animation) skills for AI coding agents — animate equations, plot functions, and render 3Blue1Brown-style explainers to MP4 with Manim Community Edition.
minli-skill
A collection of Claude Code skills, where Claude Code is an AI programming assistant. It includes a video-explanation workflow and a template for formatting WeChat Official Accounts posts.
motion-design-skills
Motion design fundamentals, engines, and brand elements as installable skills for AI coding agents — timing, typography, color, composition, After Effects, Remotion, logos, and backgrounds.
twelvelabs
TwelveLabs video AI integration. Index, search, and analyze videos using TwelveLabs' multimodal AI platform.
write-a-readme
Turn codebases into accurate, on-brand READMEs with editable SVG banners.
skind-skills
Investment research and educational video creation.