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.
npx skills add artokun/comfyui-mcp --skill model-registrygit clone --depth 1 https://github.com/artokun/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/skills/artokun/comfyui-mcp/model-registry)<a href="https://agentmods.dev/skills/artokun/comfyui-mcp/model-registry"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/model-registry/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/artokun/comfyui-mcp/model-registry"><img src="https://agentmods.dev/badge/skills/artokun/comfyui-mcp/model-registry.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.02800 |
| Opus 5 | $0.00050 | $0.01400 |
| Sonnet 5 | $0.00020 | $0.00560 |
| Haiku 4.5 | $0.00010 | $0.00280 |
Grade A, and why
model-registry 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 10d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Registry
One table per family: filename → source URL → target subdir under
<COMFYUI>/models/. Use with download_model({ action: "download", url, target_subfolder, filename }).
This registry grows with every release. If a model you need is missing, use
action:"search" (HuggingFace) or action:"download_civitai" and consider
contributing the row.
Quant column (kitchen). Filenames in this registry are mostly bf16 / fp8. NVFP4 and MXFP8 siblings, when a vendor publishes them, are the same stem with nvfp4 / mxfp8 in the name and belong in diffusion_models/ too. kitchen action:"assess" only offers an NVFP4 swap when that sibling is already listed locally — it does not guess a URL from the filename. Blackwell (SM ≥ 10.0) is the GPU that can run NVFP4 / MXFP8 compute.
Conventions
- HF "resolve" URLs download directly:
https://huggingface.co/<repo>/resolve/main/<path> - 🔒 = gated repo, needs
HUGGINGFACE_TOKEN(accept the license on the HF page first) - CivitAI model-page URLs need
download_modelaction:"download_civitai"(resolves version → file); rawcivitai.com/api/download/...URLs work withaction:"download"+CIVITAI_API_TOKEN - Always verify the exact filename a workflow's loader expects. The
model-compatibilityskill covers which VAE/CLIP pairs with which architecture
Shared VAEs & text encoders (download these once)
| File | Source | Target |
|---|---|---|
ae.safetensors (Flux/Z-Image VAE) |
huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors (Apache, not gated) |
vae/ |
vae-ft-mse-840000-ema-pruned.safetensors (SD1.5 VAE) |
huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.safetensors |
vae/ |
clip_l.safetensors |
huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors |
text_encoders/ |
t5xxl_fp8_e4m3fn.safetensors |
huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors |
text_encoders/ |
umt5_xxl_fp8_e4m3fn_scaled.safetensors (WAN) |
huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors |
text_encoders/ |
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.
- 10d ago First seen · 125 lines · 100 tokens per session scan A 594bc882238f
model-registry is a skill published in the GitHub repository artokun/comfyui-mcp (735 stars, last pushed yesterday), licensed MIT. It adds 100 tokens to every session and 2,800 once invoked, about $0.0005 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.
Other skills, from other repositories
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberish speech, drifts off…
seedance
Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated video drifts off the reference face, grows unwanted subtitles or watermarks, duplicates a character, jumps at an extension…
Prompt craft for ComfyUI generation
Use when writing prompts for ComfyUI image or video models: choosing tags vs literary format, fixing composition and anatomy artifacts, picking samplers per LoRA, and writing short movement prompts for video. Neutral examples only.
emotion-to-camera-language
A guide for turning vague visual feelings—such as cinematic, atmospheric, elegant, or healing—into concrete image or video prompt details. It uses lighting direction, depth of field, camera position, and the subject’s state.
comfyui-lora-training
Prepare datasets and configure LoRA training for character consistency. Covers FLUX (AI-Toolkit, SimpleTuner, FluxGym) and SDXL (Kohyass) training with step-by-step guidance. Use when training custom character LoRAs.
comfyui-prompt-engineer
Craft model-specific prompts optimized for the target checkpoint and identity method. Handles FLUX, SDXL, SD1.5, and Wan video models with proper syntax, quality tags, and negative prompts. Use when generating or refining prompts for ComfyUI workflows.