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 hybridindie/comfyui_mcp --skill workflowsgit clone --depth 1 https://github.com/hybridindie/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/hybridindie/comfyui_mcp/workflows)<a href="https://agentmods.dev/skills/hybridindie/comfyui_mcp/workflows"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/workflows/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/hybridindie/comfyui_mcp/workflows"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/workflows.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 | $0.00031 | $0.01438 |
| Opus 5.5 | $0.00012 | $0.00575 |
| Sonnet 5.5 | $0.00006 | $0.00288 |
| Haiku 4.5 | $0.00003 | $0.00144 |
Grade A, and why
workflows 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Workflow Building Guide
API Format
ComfyUI workflows use a JSON format where each node is a key-value pair:
{
"1": {
"class_type": "KSampler",
"inputs": {
"seed": 42,
"steps": 20,
"cfg": 7.0,
"sampler_name": "euler",
"scheduler": "normal",
"denoise": 1.0,
"model": ["2", 0],
"positive": ["3", 0],
"negative": ["4", 0],
"latent_image": ["5", 0]
}
}
}
- Keys are string node IDs (e.g.,
"1","2") class_typeis the ComfyUI node type nameinputscontains parameters and connections- Connections use the format
["source_node_id", output_index]
Common Node Chains
txt2img (text to image)
CheckpointLoaderSimple -> CLIPTextEncode (positive) -> KSampler -> VAEDecode -> SaveImage
img2img (image to image)
LoadImage -> VAEEncode -> KSampler (with denoise < 1.0) -> VAEDecode -> SaveImage
ControlNet
LoadImage -> ControlNetLoader + ControlNetApply -> feed into KSampler positive conditioning
LoRA Stacking
CheckpointLoaderSimple -> LoraLoader (chain multiple) -> KSampler
Key Nodes Reference
| Node | Purpose | Key Inputs |
|---|---|---|
CheckpointLoaderSimple |
Load a model checkpoint | ckpt_name |
CLIPTextEncode |
Encode text prompt | text, clip |
KSampler |
Run diffusion sampling | model, positive, negative, latent_image, steps, cfg, seed |
VAEDecode |
Decode latent to image | samples, vae |
VAEEncode |
Encode image to latent | pixels, vae |
SaveImage |
Save output image | images, filename_prefix |
LoadImage |
Load input image | image (filename) |
LoraLoader |
Apply LoRA weights | model, clip, lora_name, strength_model, strength_clip |
ControlNetLoader |
Load ControlNet model | control_net_name |
ControlNetApply |
Apply ControlNet | conditioning, control_net, image, strength |
Using the Workflow Tools
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 · 93 lines · 31 tokens per session scan A 8820ef893441
workflows is a skill published in the GitHub repository hybridindie/comfyui_mcp (3 stars, last pushed 12d ago), licensed MIT. It adds 31 tokens to every session and 1,438 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
local-gpu-imagegen
Use when a user asks to create, generate, draw, render, transform, restyle, or revise a visual asset on the local GPU.
b123d-modeling
Use this skill when asked to model, build, or modify a 3D part or assembly with build123d — from a text description, a technical drawing (image or PDF), dimensions in a spec, or an existing STEP/STL file.
b123d-edit
Use this skill when the task is to change an existing build123d model or script: "make this bracket 5 mm taller", "move the holes inward", "add a counterbore", "remove this rib", "make it fit this mating part", or "repair the code so the intended edit remains parametric".
browser-forms
Fill a whole web form, post a comment or reply, or read a long thread in Safari or Chrome with the fewest Mac MCP browser calls.
video-to-skill
Author an ordinary host skill from retained video or demonstration observations, then validate its source provenance, timestamped evidence, assets, rights declarations and retained task-run bindings before producing a local deterministic .skill archive. Use when deriving reusable instructions from a recording; task…
gemini-visualize
Generates interactive HTML visualizations (concept maps, evidence networks, knowledge graphs) from Gemini analysis results. Use when the user requests a concept map, evidence network, or knowledge graph from completed analysis.