models

models is a command for Claude Code from HUANGcvs/MeiGen-AI-Design-MCP. It costs 30 tokens per session (317 once invoked), scanned A, original, MIT.

A command for listing available MeiGen image-generation models and choosing which model should be used by default in the current session. A provider is the service or local system that supplies the model.

In plain words
What is it for?
Use it to review available models or ComfyUI workflows, check which providers are active, and set a session-only default model for later image-generation requests.
Why use it?
It makes provider status and model choices visible without changing permanent configuration, and the selection resets when the session ends.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the meigen plugin — 2 skills, 4 commands, 3 agents shipped together

Good fit Use it to review available models or ComfyUI workflows, check which providers are active, and set a session-only default model for later image-generation requests.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/huangcvs/meigen-ai-design-mcp/models
Install

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.

Clone the repo
git clone --depth 1 https://github.com/HUANGcvs/MeiGen-AI-Design-MCP

Made for: Claude Code.

Or install meigen, the plugin that ships this one along with the rest of its 2 skills, 4 commands, 3 agents.

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.

agentmods badge for models

README.md
[![agentmods](https://agentmods.dev/badge/commands/huangcvs/meigen-ai-design-mcp/models/github.svg)](https://agentmods.dev/commands/huangcvs/meigen-ai-design-mcp/models)
Your own site
<a href="https://agentmods.dev/commands/huangcvs/meigen-ai-design-mcp/models"><img src="https://agentmods.dev/badge/commands/huangcvs/meigen-ai-design-mcp/models/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.

agentmods 80×15 button for models

Your own site · 80×15
<a href="https://agentmods.dev/commands/huangcvs/meigen-ai-design-mcp/models"><img src="https://agentmods.dev/badge/commands/huangcvs/meigen-ai-design-mcp/models.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 317 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00317
Opus 5 $0.00015 $0.00159
Sonnet 5 $0.00006 $0.00063
Haiku 4.5 $0.00003 $0.00032

Measured 9d ago against content hash 525deeb52e93, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

models 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.

plugin/commands/models.md · 32 lines

What it actually says

Models & Provider Status

Show available models and let the user switch the default for this session.

Instructions

  1. Call list_models to get all available models and providers
  2. Present results in a compact numbered list:
    • For MeiGen models: [N] Model Name (ID: xxx) — X credits, ratios: ...
    • For ComfyUI workflows: [N] workflow-name — checkpoint, steps, sampler
    • For OpenAI-compatible: [N] model-name (via custom API)
  3. Show current configuration status (which providers are active)
  4. Ask: "Enter a number to set as default model for this session, or press Enter to keep current."
  5. If user selects a model:
    • Remember the model ID in conversation context
    • Confirm: "Default model set to [name]. All subsequent image generations will use this model."
    • For all future generate_image calls in this session, automatically pass this model ID
  6. If no providers are configured, show a brief message and suggest /meigen:setup

Important

The model switch is session-scoped — it persists in the conversation context, not in config files. When the user starts a new session, the default resets to the provider's default model.

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.

  1. 9d ago First seen · 32 lines · 30 tokens per session scan A 525deeb52e93

Subscribe to this mod's changes

models is a command published in the GitHub repository HUANGcvs/MeiGen-AI-Design-MCP (8 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 317 once invoked, about $0.0002 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.