Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/marduk191/qwen3_mcpnpx agentmods add skills/marduk191/qwen3_mcp/comfyui-nodesWrote 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/marduk191/qwen3_mcp/comfyui-nodes)<a href="https://agentmods.dev/skills/marduk191/qwen3_mcp/comfyui-nodes"><img src="https://agentmods.dev/badge/skills/marduk191/qwen3_mcp/comfyui-nodes/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/marduk191/qwen3_mcp/comfyui-nodes"><img src="https://agentmods.dev/badge/skills/marduk191/qwen3_mcp/comfyui-nodes.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 | $0.00100 | $0.07215 |
| Opus 5.5 | $0.00040 | $0.02886 |
| Sonnet 5.5 | $0.00020 | $0.01443 |
| Haiku 4.5 | $0.00010 | $0.00722 |
Grade A, and why
comfyui-nodes 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.
How it starts
The opening of the file, as written. The whole thing — 1,061 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Custom Node Development Skill
Comprehensive guide to creating custom nodes for ComfyUI. Covers both the current V1 API and the new V3 schema API.
Quick Reference
Official Resources:
- Repository: https://github.com/comfyanonymous/ComfyUI
- Documentation: https://docs.comfy.org/custom-nodes
- V3 Migration: https://docs.comfy.org/custom-nodes/v3_migration
- Example Nodes: https://github.com/comfyanonymous/ComfyUI/tree/master/comfy_extras
File Structure
Custom nodes go in ComfyUI/custom_nodes/:
ComfyUI/
└── custom_nodes/
└── my_custom_nodes/
├── __init__.py # REQUIRED: Node registration
├── nodes.py # Node class definitions
├── requirements.txt # Optional: pip dependencies
└── web/ # Optional: Frontend JS extensions
└── js/
└── my_extension.js
Basic Node Template
ALL FOUR class attributes (CATEGORY, RETURN_TYPES, FUNCTION, INPUT_TYPES) are REQUIRED. Missing any one will cause silent failure.
class MyCustomNode:
"""Description of what this node does."""
# ── ALL FOUR REQUIRED ATTRIBUTES ──────────────────────────
CATEGORY = "my_nodes/utilities" # REQUIRED: Menu location
RETURN_TYPES = ("IMAGE",) # REQUIRED: Output types as TUPLE (NOT a method!)
RETURN_NAMES = ("output_image",) # Optional: Display names for outputs
FUNCTION = "process" # REQUIRED: Name of the method ComfyUI will call
OUTPUT_NODE = False # Optional: True for terminal nodes (save, preview)
# ──────────────────────────────────────────────────────────
@classmethod
def INPUT_TYPES(cls): # REQUIRED: Must be a @classmethod
return {
"required": {
"image": ("IMAGE",),
"strength": ("FLOAT", {
"default": 1.0,
"min": 0.0,
"max": 2.0,
"step": 0.1,
"display": "slider",
"tooltip": "Effect strength"
}),
},
"optional": {
"mask": ("MASK",),
},
"hidden": {
"node_id": "UNIQUE_ID",
}
}
# Method name MUST match FUNCTION value. Parameters MUST match INPUT_TYPES keys.
# Do NOT use execute(**kwargs). Use explicit named parameters.
def process(self, image, strength, mask=None, node_id=None):
# Your processing logic here
result = image * strength
return (result,) # MUST return a tuple matching RETURN_TYPES (NOT a dict!)
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 · 1,061 lines · 100 tokens per session scan A 9ac114a55c06
comfyui-nodes is a skill published in the GitHub repository marduk191/qwen3_mcp (15 stars, last pushed 8mo ago), licensed MIT. It adds 100 tokens to every session and 7,215 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…