node-skill

A command for generating a Claude Code skill for a ComfyUI custom node pack.

In plain words
What is it for?
Use it with a ComfyUI Registry ID or GitHub URL to generate and save a skill describing the pack's nodes and examples.
Why use it?
It packages a node pack's input, output, and usage details into a skill file that Claude Code can follow.

Command

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.

agentmods
npx agentmods add commands/artokun/comfyui-mcp/node-skill
Clone the repo
git clone --depth 1 https://github.com/artokun/comfyui-mcp
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 431 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00012 $0.00431
Opus 5 $0.00006 $0.00216
Sonnet 5 $0.00002 $0.00086
Haiku 4.5 $0.00001 $0.00043

Measured 3d ago against content hash 7354cb31eb34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

node-skill 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 3d 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/node-skill.md · 41 lines

What it actually says

/comfy-skill — Generate a Node Pack Skill

The user wants to generate a Claude Code skill file for a ComfyUI custom node pack.

Instructions

  1. Parse the argument. The argument is: $ARGUMENTS

    • A ComfyUI Registry ID (e.g., comfyui-impact-pack)
    • A GitHub repository URL (e.g., https://github.com/ltdrdata/ComfyUI-Impact-Pack)
    • Nothing, in which case ask the user which node pack they want to generate a skill for
  2. Generate the skill. Use the list_packs tool with:

    • action: "generate_skill"
    • source: the registry ID or GitHub URL
    • install_in: save to skills/<pack-name>/ inside the plugin directory
  3. Report the result. Tell the user:

    • Where the skill file was saved
    • A brief summary of what nodes are covered
    • That they may need to restart Claude Code for the skill to take effect

Example

User: /comfy-skill comfyui-impact-pack

Steps:

  • Call list_packs with action: "generate_skill", source "comfyui-impact-pack" and install_in set to the skills directory
  • Show the user where the file was saved and what it covers

Notes

  • The generated skill includes node class types, input/output specs, usage examples, and a ## Sources section (official repo README vs empirically-tuned composition patterns)
  • Skills are saved as SKILL.md files in subdirectories under the plugin's skills/ folder
  • If the node pack isn't found in the registry, suggest the user provide a GitHub URL instead
  • If nodes from the pack are installed locally, the skill will include live /object_info data
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. 3d ago First seen · 41 lines · 12 tokens per session scan A 7354cb31eb34

Subscribe to this mod's changes

node-skill is a command published in the GitHub repository artokun/comfyui-mcp (701 stars, last pushed 3d ago), licensed MIT. It adds 12 tokens to every session and 431 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 2026-08-30.

Related

Other commands, from other repositories

setup

You are setting up the Video Recreation Agent Team inside this comfyui-agent repo. Run every step below automatically. Don't ask permission — just do it, report what happened.

JosephOIbrahim/Comfy-Cozy · 0 tokens

PRODUCTION_HARDEN

Each agent is a Claude Code sub-agent invoked via claude --model claude-sonnet-4-6-20250929 with a role-specific prompt file. Agents operate on branches, submit PRs via conventional commits.

JosephOIbrahim/Comfy-Cozy · 0 tokens

PRODUCER

You are the production manager for this open-source VFX tool. You handle everything that's NOT the code itself: CI/CD, packaging, release management, documentation infrastructure, metrics, and cross-agent coordination. You're the one who makes sure the train runs on time and nothing ships broken.

JosephOIbrahim/Comfy-Cozy · 0 tokens

qa-compare

You are the QA expert in the Video Recreation Agent Team.

JosephOIbrahim/Comfy-Cozy · 0 tokens

COMFY_LEAD

You are the ComfyUI technical lead. You know ComfyUI's API, node system, workflow JSON format, and the MCP protocol deeply. You're hardening an AI co-pilot that helps VFX artists work with ComfyUI through natural language.

JosephOIbrahim/Comfy-Cozy · 0 tokens

NUKE_COMP

You are a senior VFX compositor with deep Nuke pipeline experience who has transitioned into pipeline TD work. You think about tool integration the way a compositor thinks about a comp tree — everything must connect cleanly, data must flow predictably, and the artist should never have to think about the plumbing.

JosephOIbrahim/Comfy-Cozy · 0 tokens