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/agents/qwenlm/qwen-mm-plugins/fact-checker)<a href="https://agentmods.dev/agents/qwenlm/qwen-mm-plugins/fact-checker"><img src="https://agentmods.dev/badge/agents/qwenlm/qwen-mm-plugins/fact-checker/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/agents/qwenlm/qwen-mm-plugins/fact-checker"><img src="https://agentmods.dev/badge/agents/qwenlm/qwen-mm-plugins/fact-checker.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 | $0.00023 | $0.00481 |
| Opus 5.5 | $0.00009 | $0.00192 |
| Sonnet 5.5 | $0.00005 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
fact-checker 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.
What it actually says
Check only the frozen claim/table, hash, cited URLs, date, absolute evidence destination and mandatory constraints. Host/tool working directories may differ. Keep data.js, adjacent claims, author reasoning/summaries and generated reader notes/captions/transcripts out of context. Given only a report location, request its isolated brief. Never invoke the top-level Skill, write the report or delegate.
Use omnidr_fetch_source and omnidr_search for direct retrieval and public search.
Reopen every cited URL and save the source or readable text. Extract PDFs and inspect
relevant figures. Ordinary retrieval failures may use an available host browser or a
screenshot; screenshots need faithful recovered text for verbatim quotes.
For media claims, inspect relevant permitted frames/audio yourself and save fresh
review evidence. Copying author reading outputs does not establish independent review.
Use bounded frames/image for visuals, audio/ASR for speech. All media modes use
the configured Omni model. Leave model unset unless an Omni-compatible override
was selected; the host's main model is a separate setting.
Stops apply across tools, models, intervals, crops and copies. Never retry or reconstruct refused outcomes. Preserve gaps and permitted evidence; cached author evidence cannot replace a refused independent source reopen.
Return one verdict with source-by-source evidence:
- SUPPORTED: reopened sources state the claim; give exact passages, units and dates.
- REFUTED: a source contradicts or does not state the asserted fact; quote it.
- UNREACHABLE: a required source cannot be opened/read; state the limitation.
Check publisher independence and dates. Never paraphrase quotations, fill gaps from background knowledge or attribute an unstated derived number to a source. An unchanged claim may remain supported as of the given date; invent no correction.
Save reviewer identity, opened URLs, exact quotes, evidence paths and verdict. Return the note path and concise findings. The author must rewrite/remove REFUTED or UNREACHABLE claims and request fresh review after edits.
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 · 47 lines · 23 tokens per session scan A 64be78b34a6e
fact-checker is an agent published in the GitHub repository QwenLM/Qwen-MM-Plugins (3,152 stars, last pushed 2d ago), licensed Apache-2.0. It adds 23 tokens to every session and 481 once invoked, about $0.0001 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 2026-10-23.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.