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/sandyup/comfyui-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/plugins/sandyup/comfyui-mcp/plugin)<a href="https://agentmods.dev/plugins/sandyup/comfyui-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/sandyup/comfyui-mcp/plugin/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/plugins/sandyup/comfyui-mcp/plugin"><img src="https://agentmods.dev/badge/plugins/sandyup/comfyui-mcp/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
comfy 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 1mo 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.
This is a copy
100% identical to comfy — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "comfy",
"version": "0.1.0",
"description": "Claude Code plugin for ComfyUI — generate images, visualize workflows, manage models, and explore custom nodes",
"author": {
"name": "artokun"
},
"repository": "https://github.com/artokun/comfyui-mcp",
"keywords": ["comfyui", "stable-diffusion", "image-generation", "mcp"]
}
What it installs
The manifest is a name and a version. 32 skills, 11 commands, 4 agents, 2 hooks travel with it, and installing the plugin installs all of them — 2,696 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill director A 32 tokens
- Skill troubleshooting A 28 tokens
- Skill anima-base A 67 tokens
- Skill comfyui-core A 24 tokens
- Skill ai-toolkit-trainer A 93 tokens
- Skill color-correction A 161 tokens
- Skill comfyui-launch-flags A 212 tokens
- Skill report-bug A 135 tokens
- Skill civitai A 107 tokens
- Skill workflow-layout A 79 tokens
- Skill krea2-txt2img A 52 tokens
- Skill model-registry A 91 tokens
- Skill ltxv2-video A 65 tokens
- Skill wan-flf-video A 33 tokens
- Skill ernie-image A 98 tokens
- Skill video-extend A 146 tokens
- Skill comfyui-frontend-extensions A 75 tokens
- Skill flux-txt2img A 44 tokens
- Skill qwen-txt2img A 41 tokens
- Skill z-image-txt2img A 35 tokens
- Skill ideogram-ultra A 67 tokens
- Skill video-upscale A 167 tokens
- Skill qwen-image-edit A 28 tokens
- Skill anima-lora-trainer A 64 tokens
- Skill wan-t2v-video A 38 tokens
- Skill wan-multitalk A 55 tokens
- Skill installer-packs A 56 tokens
- Skill model-compatibility A 47 tokens
- Skill comfyui-node-registry A 37 tokens
- Skill prompt-engineering A 28 tokens
- Skill debug-render A 122 tokens
- Skill triton-sageattention C 170 tokens
- Command compare A 10 tokens
- Command install A 8 tokens
- Command convert A 11 tokens
- Command node-skill A 12 tokens
- Command gen A 11 tokens
- Command batch A 6 tokens
- Command director A 16 tokens
- Command debug A 9 tokens
- Command gallery A 8 tokens
- Command recipe A 18 tokens
- Command viz A 12 tokens
- Agent comfy-debugger A 21 tokens
- Agent comfy-explorer A 17 tokens
- Agent comfy-optimizer A 18 tokens
- Agent comfy-researcher A 22 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
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.
- 1mo ago First seen · 11 lines scan A 21ddf70061b5
comfy is a plugin published in the GitHub repository sandyup/comfyui-mcp (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. It is 100% identical to comfy, differing in 0 lines, and is treated as a copy.
Other plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.