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.
npx skills add QwenLM/Qwen-MM-Plugins --skill skillgit 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/skills/qwenlm/qwen-mm-plugins/skill)<a href="https://agentmods.dev/skills/qwenlm/qwen-mm-plugins/skill"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-mm-plugins/skill/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/skills/qwenlm/qwen-mm-plugins/skill"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-mm-plugins/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00087 | $0.02214 |
| Opus 5.5 | $0.00035 | $0.00886 |
| Sonnet 5.5 | $0.00017 | $0.00443 |
| Haiku 4.5 | $0.00009 | $0.00221 |
Grade A, and why
qwen-mm-plugins-api 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 17d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- qwen-mm-plugins-api — 100% identical, 48 lines differ
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Media Understanding
Use qwen-mm-plugins-api to understand media through configured model services. The tools are grouped by model family:
- VL model (Qwen-VL, OpenAI-compatible endpoint):
vision_chat,ocr,grounding. - Omni model (Qwen-Omni — combines video frames and audio):
perceive_media,omni_asr,omni_asr_timestamped,omni_multi_speaker_asr,omni_av_caption,omni_av_grounding,omni_av_counting,omni_music_caption. - Other services:
transcribe_audio(Qwen3-ASR),segmentation(a SAM3 server).
Check the qwen-mm-plugins-api tools in your tool list for full schemas and parameters. For file reading, rendering, or metadata inspection, use core.
When to Use Which Tool
VL model (single images/videos, spatial reasoning):
- Ask a VLM about images/videos (caption, VQA, free-form) →
vision_chat - Extract text from an image →
ocr - Detect/locate objects in an image (bounding boxes, spatial WHERE) →
grounding. It sends EXIF-corrected pixels, so returned 0–1000 boxes address the displayed image and can be passed directly to corecrop/draw_bboxor searchimage_search.
Omni model (audio + video together, temporal reasoning):
- Prefer general-purpose chat →
perceive_media. Pass the actual objective inprompt; useaudio,video, orautoaccording to the evidence needed. - Treat the atomic tools below as references. Use one when its fixed structured output is explicitly needed rather than merely because its name resembles the task.
- Transcribe speech, plain text →
omni_asr(one continuous string, no timestamps) - Transcribe with timestamps →
omni_asr_timestamped(utterance-level timestamps; returns JSON and SRT) - Who said what →
omni_multi_speaker_asr(diarization: speaker labels + timestamps + SRT; passnum_speakersif known) - Describe the content over time →
omni_av_caption(format=sectionsby default;narrativefor timestamped prose,jsonfor scenes/events) - Find WHEN something happens →
omni_av_grounding(query→ matching time segments;mode=audio_eventfor an exact sound label such asdog_barking) - Count how many times an event/object/action occurs →
omni_av_counting(target→ total + per-occurrence timestamps) - Analyze / caption a music track →
omni_music_caption(whole-track tags — genre / moods / instruments / key / time signature / vocal profile — plus a dense English caption for music generation; audio-only, no timestamps)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 17d ago Changed 558860f6c41b
- 23d ago Changed · +2 lines 1644aca3338a
- 1mo ago Changed 1d6cd2dc5b3f
- 1mo ago Changed · +4 lines · +5 tokens per session 544f8b55821a
- 1mo ago Changed · +6 lines 5829a3bd66ee
- 1mo ago Changed · +2 lines · -28 tokens per session 320e99422724
- 1mo ago First seen · 65 lines · 110 tokens per session scan A 27f8910080d3
qwen-mm-plugins-api is a skill published in the GitHub repository QwenLM/Qwen-MM-Plugins (3,152 stars, last pushed 2d ago), licensed Apache-2.0. It adds 87 tokens to every session and 2,214 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.