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 workflowgit 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/workflow)<a href="https://agentmods.dev/skills/hybridindie/comfyui_mcp/workflow"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/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/hybridindie/comfyui_mcp/workflow"><img src="https://agentmods.dev/badge/skills/hybridindie/comfyui_mcp/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 | $0.00011 | $0.00610 |
| Opus 5.5 | $0.00004 | $0.00244 |
| Sonnet 5.5 | $0.00002 | $0.00122 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
workflow scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Workflow
Create and optionally run a ComfyUI workflow. Template or description provided by the user as input: "$ARGUMENTS".
Steps
-
Pick a template. If no specific template was requested, choose from the built-in template names accepted by
comfyui_create_workflow:txt2img,img2img,upscale,inpaint,txt2vid_animatediff,txt2vid_wan,controlnet_canny,controlnet_depth,controlnet_openpose,ip_adapter,lora_stack,face_restore,flux_txt2img,sdxl_txt2img. The full list is also incomfyui_create_workflow's docstring. (Note:comfyui_list_workflowsreturns server-side/workflow_templatesfrom front-end packages — not these MCP-built-in templates.) If the user provides a template name that is not in this list, respond with an error message and list the valid options above. -
Create the workflow.
- If the user did not specify any parameter overrides, call
comfyui_create_workflowwith only the template name (omitparams; it defaults to"", which applies the predefined settings for the selected template). - If the user specified overrides (e.g., prompt, dimensions), pass them as a JSON string in the
paramsargument:create_workflow(template="txt2img", params='{"prompt": "a sunset", "width": 768}')
- If the user did not specify any parameter overrides, call
-
Validate the workflow. Call
comfyui_validate_workflowwith the workflow JSON returned from step 2. The response is a dict{valid, errors, warnings, node_count, pipeline}. Report any entries inerrors(blocking) andwarnings(non-blocking). -
Present the workflow. Show a summary of what the workflow does (nodes, connections, key parameters). Offer the user two options:
- Run it — call
comfyui_run_workflowwithwait=True. The response is a dict envelope:{status, prompt_id, outputs, elapsed_seconds, warnings?}. Readstatusto confirm completion. - Modify it — use
comfyui_modify_workflowto add/remove nodes or change parameters, then re-validate
- Run it — call
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 · 32 lines · 11 tokens per session scan A 01228e26e785
workflow is a skill published in the GitHub repository hybridindie/comfyui_mcp (3 stars, last pushed 13d ago), licensed MIT. It adds 11 tokens to every session and 610 once invoked, about $0.0000 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.