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 HUANGcvs/MeiGen-AI-Design-MCP --skill setupgit 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/skills/huangcvs/meigen-ai-design-mcp/setup)<a href="https://agentmods.dev/skills/huangcvs/meigen-ai-design-mcp/setup"><img src="https://agentmods.dev/badge/skills/huangcvs/meigen-ai-design-mcp/setup/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/huangcvs/meigen-ai-design-mcp/setup"><img src="https://agentmods.dev/badge/skills/huangcvs/meigen-ai-design-mcp/setup.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 | $0.00048 | $0.02600 |
| Opus 5 | $0.00024 | $0.01300 |
| Sonnet 5 | $0.00010 | $0.00520 |
| Haiku 4.5 | $0.00005 | $0.00260 |
Grade D, and why
setup scanned grade D with 3 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- We'll automatically extract the API key, base URL, and model name Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 ~/.config/meigen/config.json Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
### Option D: Import from curl Example How it starts
The opening of the file, as written. The whole thing — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MeiGen Plugin Setup
You are guiding the user through configuring the MeiGen plugin for image generation. Follow this flow step by step.
Step 1: Welcome
First, check if a config file already exists:
cat ~/.config/meigen/config.json 2>/dev/null
Also check for existing ComfyUI workflows:
ls ~/.config/meigen/workflows/*.json 2>/dev/null
If config exists, show the current configuration (mask API keys: show first 10 chars + "...") and any saved workflows. Ask if they want to reconfigure.
If no config exists, present this introduction:
MeiGen Plugin Configuration
This is optional. Without configuration, you can still use free features:
- Search gallery for inspiration and prompts
- Enhance simple ideas into professional prompts
- Browse available AI models
Configuring a provider unlocks image generation.
Then proceed to Step 2.
Step 2: Choose Provider
Present these options to the user:
Option A: MeiGen Platform (Recommended)
- Supports Nanobanana Pro, GPT image 1.5, Seedream 4.5 and more
- Reference image support for style transfer
- No additional accounts needed — just get a token from meigen.ai
Option B: ComfyUI (Local)
- Use your local ComfyUI installation for image generation
- Full control over models, samplers, and workflow settings
- No cloud API needed — runs entirely on your machine
- Import your own workflow from ComfyUI
Option C: Custom OpenAI-Compatible API
- Use your own OpenAI, Together AI, Fireworks AI, or any OpenAI-compatible service
- Bring your own API key and billing
- Supports any model that uses the OpenAI
/v1/images/generationsendpoint
Option D: Import from curl Example
- Already have a working curl command from your API provider's docs? Paste it directly!
- We'll automatically extract the API key, base URL, and model name
Option E: Skip image generation for now
- Free features still available (inspiration search, prompt enhancement, model listing)
- You can run
/meigen:setupanytime later to enable image generation
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 · 324 lines · 48 tokens per session scan D db23c29ec2d8
setup is a skill published in the GitHub repository HUANGcvs/MeiGen-AI-Design-MCP (8 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 2,600 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 3 findings (harvests environment variables, asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes…
MeiGen Visual Creative Expert
This skill should be used when the user asks to "generate an image", "create artwork", "design a logo", "make a poster", "draw something", "find inspiration", "search for reference images", "enhance my prompt", "improve prompt", "brand design", "product mockup", "batch generate images", "multiple variations"…
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
Social Thumbnail Workflow
A workflow for creating vertical images for short-video platforms and mobile social feeds, where content is usually viewed in a 9:16 portrait layout.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
comfyui-frontend-extensions
Authoring ComfyUI v2 frontend extensions with @comfyorg/extension-api, covering defineNode/defineExtension/defineWidget, shell UI (sidebar tabs, commands, hotkeys), typed events, and handles. Use when writing or editing ComfyUI web-UI extension code (custom node JS, sidebar panels, widgets).