Comfyui Inventory

Before you generate any ComfyUI workflow, run this to scan what's actually installed on your system. It checks via API if ComfyUI is running, or falls back to directory scanning if offline, then caches everything to inventory.json: models, custom nodes, VRAM specs, the works. The real value is workflow validation. It'll tell you exactly which model files are missing and where to download them, or which custom node package you need to install via ComfyUI Manager. Saves you from that annoying cycle of generating a workflow, hitting errors, realizing you don't have the LoRA or InstantID node, then starting over. Cache stays fresh for an hour.

skills.sh installs: 601
GitHub stars: 94
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add mckruz/comfyui-expert --skill comfyui-inventory --agent claude-code

Installs into .claude/skills of the current project.

Files

ComfyUI Inventory Skill

Discovers what's installed in the user's ComfyUI instance and caches results for workflow validation.

Purpose

Every workflow generation MUST be preceded by an inventory check. This prevents:

Referencing models that aren't downloaded
Using nodes that aren't installed
Exceeding VRAM limits

Two Discovery Modes

Online Mode (ComfyUI API Running)

Query the live server for authoritative information.

1. System info:

curl http://127.0.0.1:8188/system_stats

Extracts: GPU name, total VRAM, free VRAM, ComfyUI version.

2. Installed nodes:

curl http://127.0.0.1:8188/object_info

Returns all registered node classes with their input/output specifications.

3. Installed models (per type):

curl http://127.0.0.1:8188/models/checkpoints
curl http://127.0.0.1:8188/models/loras
curl http://127.0.0.1:8188/models/vae
curl http://127.0.0.1:8188/models/controlnet
curl http://127.0.0.1:8188/models/clip
curl http://127.0.0.1:8188/models/clip_vision
curl http://127.0.0.1:8188/models/upscale_models
curl http://127.0.0.1:8188/models/diffusion_models