qwen-mm-plugins-api

qwen-mm-plugins-api is a skill for Claude Code, Codex from ShuiHan268/dsh-qwen-mm-plugins. It costs 110 tokens per session (1,611 once invoked), scanned A, a copy of qwen-mm-plugins-api, Apache-2.0.

A set of cloud tools for understanding images, video, and audio with Qwen models, including text extraction, object location, captions, and speech transcription.

In plain words
What is it for?
Captioning images and audiovisual content, extracting text with OCR, locating objects, transcribing speech with timestamps or speaker labels, counting events, and describing music.
Why use it?
It lets an agent analyze media directly instead of requiring separate manual processing for frames, audio, and text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Captioning images and audiovisual content, extracting text with OCR, locating objects, transcribing speech with timestamps or speaker labels, counting events, and describing music.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api
Install

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.

Any agent
npx skills add ShuiHan268/dsh-qwen-mm-plugins --skill qwen-mm-plugins-api
Clone the repo
git clone --depth 1 https://github.com/ShuiHan268/dsh-qwen-mm-plugins

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for qwen-mm-plugins-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api/github.svg)](https://agentmods.dev/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api)
Your own site
<a href="https://agentmods.dev/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api"><img src="https://agentmods.dev/badge/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api/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.

agentmods 80×15 button for qwen-mm-plugins-api

Your own site · 80×15
<a href="https://agentmods.dev/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api"><img src="https://agentmods.dev/badge/skills/shuihan268/dsh-qwen-mm-plugins/qwen-mm-plugins-api.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00110 $0.01611
Opus 5 $0.00055 $0.00805
Sonnet 5 $0.00022 $0.00322
Haiku 4.5 $0.00011 $0.00161

Measured 11d ago against content hash 27f8910080d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/launch_sam3_server.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

This is a copy

100% identical to qwen-mm-plugins-api — 34 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/qwen-mm-plugins-api/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Qwen-MM-Plugins API

You have qwen-mm-plugins-api MCP tools available. They call external models/services to understand media, grouped by model family:

  • VL model (Qwen-VL, OpenAI-compatible endpoint): vision_chat, ocr, grounding.
  • Omni model (Qwen-Omni — reads video frames and the embedded audio track together, so one call reasons over both): 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).

Prefer these over manual ffmpeg/ffprobe scripting. Check the qwen-mm-plugins-api tools in your tool list for full schemas and parameters.

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

Omni model (audio + video together, temporal reasoning; clips up to a few minutes):

  • Transcribe speech, plain textomni_asr (one continuous string, no timestamps)
  • Transcribe with timestampsomni_asr_timestamped (granularity = sentence or word; also returns SRT)
  • Who said whatomni_multi_speaker_asr (diarization: speaker labels + timestamps + SRT; pass num_speakers if known)
  • Describe the content over timeomni_av_caption (splits into spans, one description + start/end per span)
  • Find WHEN something happensomni_av_grounding (natural-language query → matching time segments; temporal localization)
  • Count how many times an event/object/action occurs → omni_av_counting (target → total + per-occurrence timestamps)
  • Analyze / caption a music trackomni_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)

Read the full file on GitHub · 65 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 65 lines · 110 tokens per session scan A 27f8910080d3

Subscribe to this mod's changes

qwen-mm-plugins-api is a skill published in the GitHub repository ShuiHan268/dsh-qwen-mm-plugins (3 stars, last pushed 25d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,611 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to qwen-mm-plugins-api, differing in 34 lines, and is treated as a copy.

Related

Other skills, from other repositories

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

synthetic-sciences/openscience · 67 tokens

whisper

OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual…

ihatesea69/HieuNghi-AI-Skills · 67 tokens

llama-factory

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support.

davila7/claude-code-templates · 51 tokens

seedance-2.0-prompter

Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.

pexoai/pexo-skills · 48 tokens

multimodal-llm

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via gen4turbo), or building multimodal AI pipelines.

yonatangross/orchestkit · 82 tokens

stable-diffusion-image-generation

State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

davila7/claude-code-templates · 50 tokens