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/HUANGcvs/MeiGen-AI-Design-MCPWrote 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/commands/huangcvs/meigen-ai-design-mcp/ref)<a href="https://agentmods.dev/commands/huangcvs/meigen-ai-design-mcp/ref"><img src="https://agentmods.dev/badge/commands/huangcvs/meigen-ai-design-mcp/ref/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/commands/huangcvs/meigen-ai-design-mcp/ref"><img src="https://agentmods.dev/badge/commands/huangcvs/meigen-ai-design-mcp/ref.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 | $0.00016 | $0.00166 |
| Opus 5 | $0.00008 | $0.00083 |
| Sonnet 5 | $0.00003 | $0.00033 |
| Haiku 4.5 | $0.00002 | $0.00017 |
Grade A, and why
ref 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 9d 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
Upload Reference Image
Upload a local image for use as a reference in image generation.
Instructions
- The user provides a file path:
$ARGUMENTS - If no path provided, ask: "Please provide the path to your image file."
- Call
upload_reference_imagewith the file path - Show the returned URL and compression details
- Confirm: "Reference ready. You can now use
/meigen:gen— I'll apply this reference automatically."
Remember the uploaded URL in context so subsequent /meigen:gen calls can use it as referenceImages.
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.
- 9d ago First seen · 22 lines · 16 tokens per session scan A ebd2f2bebf1a
ref is a command published in the GitHub repository HUANGcvs/MeiGen-AI-Design-MCP (8 stars, last pushed today), licensed MIT. It adds 16 tokens to every session and 166 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
gen
Quick image generation. Use when user runs /meigen:gen with a prompt. Skips intent assessment, generates directly.
director
Direct a short film from a story. Generates scenes, frames, and video clips.
compare
Diff two ComfyUI workflows to see what changed.
gallery
Browse and inspect generated ComfyUI outputs.
viz
Visualize a ComfyUI workflow as a mermaid diagram.
combine-people
Composite multiple people into one image with Comfy Cloud.