What is Qwen-MM-Plugins CLAUDE.md?

A set of repository instructions for coding agents working on the Qwen-MM-Plugins project. It explains how capabilities, skills, and MCP servers are organized and packaged.

Use it when developing, packaging, testing, or reviewing capabilities and MCP servers in the Qwen-MM-Plugins repository.

It helps contributors place code in the right folders, follow naming and dependency rules, and package capabilities consistently.

How QwenLM/Qwen-MM-Plugins configures Claude Code

About the project

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.

QwenLM/Qwen-MM-Plugins · 2,807 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to QwenLM/Qwen-MM-Plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/QwenLM/Qwen-MM-Plugins/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/QwenLM/Qwen-MM-Plugins

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/qwenlm/qwen-mm-plugins/claude-md/github.svg)](https://agentmods.dev/instructions/qwenlm/qwen-mm-plugins/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/qwenlm/qwen-mm-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/qwenlm/qwen-mm-plugins/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/qwenlm/qwen-mm-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/qwenlm/qwen-mm-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 807 This file is loaded in full into every session.

When invoked 807 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found 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.

Model	Per session	Once invoked
Fable 5.1	$0.00807	$0.00807
Opus 5	$0.00404	$0.00404
Sonnet 5	$0.00161	$0.00161
Haiku 4.5	$0.00081	$0.00081

Measured 10d ago against content hash dd40581a62fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

Qwen-MM-Plugins CLAUDE.md 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 10d 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.

CLAUDE.md · 76 lines

How it starts

The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository instructions for coding agents

Keep this file limited to non-obvious repository rules. User-facing orientation belongs in the README; installation, development, testing, and release details belong in docs/.

Local development

Use bash install.sh local for the complete harness path and a dedicated clone: local mode writes absolute checkout paths into tracked manifests. Restore them with bash install.sh local --restore. For server-only iteration, run Python directly; see Local development.

Architecture and packaging

A capability lives under src/capabilities/<cap>/ and may ship a Skill, an MCP server, or both. edu-agent is Skill-only; example is an unpublished template.
Keep names aligned: folder <cap>, Skill/plugin/entry qwen-mm-plugins-<cap>, extra [<cap>], and import qwen_mm_plugins_<cap-with-underscores>.
Installed capabilities are independent. Put reusable code in src/shared/ or src/mcp_framework.py; never import a sibling capability's server package.
All MCP servers ship in one qwen-mm-plugins distribution. Extras select dependencies, not packaged source files.
Marketplace installs bundle every shipped component: server capabilities carry Skill + MCP; Skill-only capabilities must not advertise an MCP server.
The video-memory builder intentionally copies schema.py and embeddings.py; consistency tests require the builder and server copies to remain byte-identical.

MCP server convention

Each server package:

exports its capability __version__, SPECS, and get_handler from __init__.py;
uses the generic __main__.py shim, mcp_framework.run_main, and build_registry(__name__, [subpackages]) discovery;
declares each tool as a Pydantic-backed TOOL plus handle(arguments) -> list[content-dict];
returns MCP text or image blocks and imports optional heavy dependencies lazily.

Do not duplicate registration or schemas manually. Qwen Code namespaces MCP servers globally, so every manifest server key must use the unique capability name.

Read the full file on GitHub · 76 lines

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.

10d ago First seen · 76 lines · 807 tokens per session scan A dd40581a62fd

Subscribe to this mod's changes

Qwen-MM-Plugins CLAUDE.md is an instructions file published in the GitHub repository QwenLM/Qwen-MM-Plugins (2,807 stars, last pushed today), licensed Apache-2.0. It adds 807 tokens to every session, about $0.0040 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 2026-08-30.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

Qwen-MM-Plugins: Instructions file for Claude Code