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 marduk191/qwen3_mcp --skill comfyui-workflowgit clone --depth 1 https://github.com/marduk191/qwen3_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/marduk191/qwen3_mcp/comfyui-workflow)<a href="https://agentmods.dev/skills/marduk191/qwen3_mcp/comfyui-workflow"><img src="https://agentmods.dev/badge/skills/marduk191/qwen3_mcp/comfyui-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/marduk191/qwen3_mcp/comfyui-workflow.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 | $0.00099 | $0.05219 |
| Opus 5 | $0.00049 | $0.02610 |
| Sonnet 5 | $0.00020 | $0.01044 |
| Haiku 4.5 | $0.00010 | $0.00522 |
Grade A, and why
comfyui-workflow 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 — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Workflow Guide
Comprehensive guide to building image generation workflows in ComfyUI. Covers SD1.5, SDXL, SD3.5, and Flux model families with all common pipeline patterns.
When to Use This Skill
- Creating text-to-image, image-to-image, or inpainting workflows
- Setting up Flux, SDXL, or SD3.5 pipelines
- Adding ControlNet, LoRA, IPAdapter, or other conditioning
- Optimizing sampler/scheduler settings
- Building complex multi-stage generation pipelines
Model Families & Loading
Different models require different loader nodes. This is the most common source of errors.
SD1.5 / SDXL
Uses a single checkpoint file containing UNet + CLIP + VAE.
Node: CheckpointLoaderSimple
ckpt_name: "sd_xl_base_1.0.safetensors"
Outputs: MODEL, CLIP, VAE
File location: ComfyUI/models/checkpoints/
SD3.5
Uses a checkpoint with triple CLIP (clip_g + clip_l + t5xxl).
Node: CheckpointLoaderSimple
ckpt_name: "sd3.5_large.safetensors"
Outputs: MODEL, CLIP, VAE
Or load components separately:
Node: UNETLoader
unet_name: "sd3.5_large.safetensors"
weight_dtype: "default"
Outputs: MODEL
Node: TripleCLIPLoader
clip_name1: "clip_g.safetensors"
clip_name2: "clip_l.safetensors"
clip_name3: "t5xxl_fp16.safetensors"
Outputs: CLIP
Node: VAELoader
vae_name: "sd3.5_vae.safetensors"
Outputs: VAE
SD3.5 Variants:
| Model | Params | Speed | Quality |
|---|---|---|---|
| SD3.5 Large | 8B | Slow | Best |
| SD3.5 Large Turbo | 8B distilled | Fast | Good |
| SD3.5 Medium | 2.5B | Medium | Good |
Flux
Flux does NOT use a single checkpoint. Load components separately:
Node: UNETLoader (or "Load Diffusion Model")
unet_name: "flux1-dev.safetensors"
weight_dtype: "default"
Outputs: MODEL
Node: DualCLIPLoader
clip_name1: "t5xxl_fp16.safetensors" (or fp8)
clip_name2: "clip_l.safetensors"
type: "flux"
Outputs: CLIP
Node: VAELoader
vae_name: "ae.safetensors"
Outputs: VAE
Exception: FP8 checkpoint versions can use CheckpointLoaderSimple with CFG=1.0.
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 · 641 lines · 99 tokens per session scan A 8c56668712cd
comfyui-workflow is a skill published in the GitHub repository marduk191/qwen3_mcp (13 stars, last pushed 7mo ago), licensed MIT. It adds 99 tokens to every session and 5,219 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.