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 yutianxiao6/comfyui-mcp --skill comfyui-workflowgit clone --depth 1 https://github.com/yutianxiao6/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/yutianxiao6/comfyui-mcp/comfyui-workflow)<a href="https://agentmods.dev/skills/yutianxiao6/comfyui-mcp/comfyui-workflow"><img src="https://agentmods.dev/badge/skills/yutianxiao6/comfyui-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/yutianxiao6/comfyui-mcp/comfyui-workflow"><img src="https://agentmods.dev/badge/skills/yutianxiao6/comfyui-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 | $0.00084 | $0.01255 |
| Opus 5 | $0.00042 | $0.00628 |
| Sonnet 5 | $0.00017 | $0.00251 |
| Haiku 4.5 | $0.00008 | $0.00126 |
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ComfyUI Workflow
Operate the user's live ComfyUI installation through the comfyui_* MCP tools. Treat the live node schema and model inventory as authoritative; installations differ because custom nodes, models, and ComfyUI versions differ.
Establish the task
- Determine whether the user wants inspection, graph construction, graph editing, canvas display, execution, or troubleshooting.
- Call
comfyui_healthbefore work that depends on a live ComfyUI instance. - Inspect managed workflows with
comfyui_list_workflowsandcomfyui_get_workflowbefore assuming a workflow is absent or current. - Preserve the user's existing workflow unless they explicitly request replacement. Prefer a new managed workflow for experiments.
If the host prefixes MCP names, select tools by their comfyui_* suffix.
Discover before building
Never invent node class names, input names, output indices, enum values, or model filenames.
- Search with
comfyui_list_node_typesusing a functional term such ascheckpoint,sampler,controlnet, orsave image. - Call
comfyui_get_node_typefor every class whose inputs or outputs affect the graph. - Call
comfyui_list_modelsbefore choosing checkpoints, VAEs, LoRAs, ControlNets, upscale models, or other installed assets. - Use
comfyui_list_templateswhen an installed node pack may already provide a suitable workflow.
Read graph-contract.md before creating or modifying a graph.
Build or edit incrementally
- Create an empty graph with
comfyui_create_workflow, or import an API-format graph withcomfyui_import_workflow. - Add one node at a time with
comfyui_add_node. Keepverify_node_type=trueunless the user is deliberately preparing a graph for a node that is not installed locally. - Set literals with
comfyui_set_inputand links withcomfyui_connect_nodes. - After every mutation, carry the returned revision into the next mutation as
expected_revision. If a revision conflict occurs, read the workflow again and reconcile instead of blindly retrying. - Use
comfyui_disconnect_inputbefore replacing a connection when that makes the intent clearer. Usecomfyui_remove_nodewithforce=trueonly when dangling connections should also be removed. - Keep stable node IDs and useful
_meta.titlevalues so later edits and run overrides are unambiguous.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 77 lines · 84 tokens per session scan A f1cb4858732a
comfyui-workflow is a skill published in the GitHub repository yutianxiao6/comfyui-mcp (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,255 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
ernie-image
Build Baidu ERNIE-Image / ERNIE-Image-Turbo workflows, primarily TEXT-TO-IMAGE. Pick ERNIE when you need precise multilingual text rendering, posters/signage, manga/anime multi-panel layouts, or strong instruction following for complex multi-object scenes. Also supports denoise-based image-to-image refine (NOT…
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
qwen-image-edit
Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing.
video-upscale
Upscale and restore video in ComfyUI. Both the quick local path (per-frame ESRGAN like 4xfoolhardyRemacri via ImageUpscaleWithModel + 4x→2x supersample, with its temporal-flicker tradeoff) and temporal-aware super-resolution (SeedVR2, the newer FlashVSR) with the downscale-first restore pipeline; RIFE/FILM frame…
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.