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 music-to-mvgit 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/music-to-mv)<a href="https://agentmods.dev/skills/qwenlm/qwen-mm-plugins/music-to-mv"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-mm-plugins/music-to-mv/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/music-to-mv"><img src="https://agentmods.dev/badge/skills/qwenlm/qwen-mm-plugins/music-to-mv.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00068 | $0.01393 |
| Opus 5 | $0.00034 | $0.00696 |
| Sonnet 5 | $0.00014 | $0.00279 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
qwen-mm-plugins-omni-chatcut-music-to-mv 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Music-to-MV
Own the project state and route work through three internal workflows. The workflow order is flexible, but their artifact dependencies are not:
music/audio → completed caption or music map → validated storyboard → generated assets/final MV
Python runtime
Before running local Python scripts, call get_music2mv_runtime with {}. Replace python3
in this skill and its references with the returned python_executable unchanged (do not resolve
its symlink). For run_mv_pipeline.py, also pass --expected-python-prefix with the returned
python_prefix; a mismatch stops execution before dependency imports. Query again after an MCP
restart/reinstall; if the tool is unavailable, restore the MCP connection before running scripts.
Route by state
Determine the requested target: analysis_only, storyboard_only, final_mv, or resume. Inventory
the project before choosing a workflow:
python3 <skill-root>/scripts/inspect_music2mv_state.py <project-dir>
Use the first applicable route:
- A final MV exists: validate/report it; do not regenerate it merely to normalize paths.
- Resumable execution state exists: continue the video-generation workflow.
- A validated storyboard exists: deliver it or execute it according to the target.
- A completed caption/music map exists: author or revise the storyboard.
- An incomplete project-backed caption run exists: resume the music-caption workflow from its last durable phase when its source audio is still readable.
- Readable source audio exists: run music captioning, then continue only as far as requested.
- Otherwise request the missing audio, caption, storyboard, or project directory.
Read pipeline-contract.md when deciding artifact validity or invalidation. Read gates.md before changing stages or using a remote provider. Before any remote call, read model-configuration.md and use the same unified model-connection file for Omni, image, and video calls.
What ships with it
47 files 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.
- assets/manifest-template.json 1.4 KB
- assets/model-config.example.json 886 B
- assets/profiles.json 347 B
- assets/seedance-characters.jsonl 723 KB
- references/gates.md 875 B
- references/model-configuration.md 4.2 KB
- references/pipeline-contract.md 1.8 KB
- references/profiles.md 816 B
- references/seedance-character-search.md 6.6 KB
- scripts/inspect_music2mv_state.py 11 KB runs code
- scripts/search_local_characters.py 4.2 KB runs code
- workflows/music-caption/references/final_caption_synthesis.md 8.3 KB
- workflows/music-caption/references/global_music_caption_prompt.md 9.1 KB
- workflows/music-caption/references/music_caption_evidence_contract.md 4.6 KB
- workflows/music-caption/references/music_structure_asr_prompt.md 3.2 KB
- workflows/music-caption/references/segment_vocal_instrument_prompt.md 4.1 KB
- workflows/music-caption/references/sentence_lyrics_srt_prompt.md 3.6 KB
- workflows/music-caption/WORKFLOW.md 14 KB
- workflows/storyboard/assets/creative-blueprint-template.md 4.2 KB
- workflows/storyboard/references/aesthetic-direction.md 1.6 KB
- workflows/storyboard/references/authoring-contract.md 5.1 KB
- workflows/storyboard/references/blocking-camera-design.md 1.1 KB
- workflows/storyboard/references/continuity-editing.md 1021 B
- workflows/storyboard/references/dance-choreography.md 1.2 KB
- workflows/storyboard/references/input-contract.md 1.8 KB
- workflows/storyboard/references/music-to-edit-map.md 4.7 KB
- workflows/storyboard/references/shot-type-grammar.md 1.6 KB
- workflows/storyboard/references/top-level-design.md 1.4 KB
- workflows/storyboard/scripts/normalize_music_analysis.py 4.1 KB runs code
- workflows/storyboard/scripts/split_provider_segments.py 2.4 KB runs code
- workflows/storyboard/scripts/validate_storyboard.py 42 KB runs code
- workflows/storyboard/WORKFLOW.md 19 KB
- workflows/video-generation/assets/api-config.example.json 2.8 KB
- workflows/video-generation/assets/fonts/NotoSansCJKsc-Bold.otf 16604 KB
- workflows/video-generation/assets/fonts/OFL.txt 4.3 KB
- workflows/video-generation/references/api-and-rate-limits.md 6.5 KB
- workflows/video-generation/references/execution-contract.md 7.2 KB
- workflows/video-generation/references/qwen-image30.md 2.2 KB
- workflows/video-generation/references/seedance.md 4.7 KB
- workflows/video-generation/references/seedream.md 1.8 KB
- workflows/video-generation/references/shot-quality-control.md 3.9 KB
- workflows/video-generation/references/subtitles.md 1.8 KB
- workflows/video-generation/references/wan30.md 2.1 KB
- workflows/video-generation/scripts/burn_lyrics_subtitles.py 9.8 KB runs code
- workflows/video-generation/scripts/run_mv_pipeline.py 3.1 KB runs code
- workflows/video-generation/scripts/validate_execution_storyboard.py 14 KB runs code
- workflows/video-generation/WORKFLOW.md 15 KB
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.
- 2d ago First seen · 124 lines · 68 tokens per session scan A 4929bb0f6cf8
qwen-mm-plugins-omni-chatcut-music-to-mv is a skill published in the GitHub repository QwenLM/Qwen-MM-Plugins (2,814 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 1,393 once invoked, about $0.0003 per session on Opus 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 2026-09-10.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…