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.
git clone --depth 1 https://github.com/sandyup/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/commands/sandyup/comfyui-mcp/viz)<a href="https://agentmods.dev/commands/sandyup/comfyui-mcp/viz"><img src="https://agentmods.dev/badge/commands/sandyup/comfyui-mcp/viz/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/commands/sandyup/comfyui-mcp/viz"><img src="https://agentmods.dev/badge/commands/sandyup/comfyui-mcp/viz.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 | $0.00012 | $0.00445 |
| Opus 5.5 | $0.00005 | $0.00178 |
| Sonnet 5.5 | $0.00002 | $0.00089 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
viz 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 2mo 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.
This is a copy
91% identical to viz — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
/comfy-viz — Visualize a Workflow
The user wants to visualize a ComfyUI workflow as a mermaid flowchart diagram.
Instructions
-
Get the workflow JSON. The argument may be: $ARGUMENTS
- A file path to a workflow JSON file — read it with the Read tool
- Inline JSON pasted directly as the argument
- Nothing — ask the user to provide a workflow file path or paste the JSON
-
Validate the input. The workflow must be in ComfyUI's API format: an object where keys are node IDs and values have
class_typeandinputs. If it looks like the web UI format (hasnodesandlinksarrays), tell the user it needs to be in API format and suggest they export it via "Save (API Format)" in ComfyUI. -
Visualize. Use the
visualize_workflowtool with:workflow: the parsed workflow JSONshow_values:true(to include parameter values in node labels)direction:"LR"(left-to-right, easiest to read)
-
Present the diagram. Show the mermaid output to the user. The mermaid code block will render as a flowchart showing nodes grouped by category with labeled connections.
Example
User: /comfy-viz ~/workflows/my-workflow.json
Steps:
- Read the file at
~/workflows/my-workflow.json - Pass contents to
visualize_workflow - Display the mermaid diagram
Notes
- If the workflow is very large (50+ nodes), suggest using
direction: "TB"(top-to-bottom) for better readability - The diagram groups nodes into subgraphs by category: loading, conditioning, sampling, image, output
- Connection edges are labeled with data types (MODEL, CLIP, CONDITIONING, LATENT, IMAGE, VAE, etc.)
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.
- 2mo ago First seen · 40 lines · 12 tokens per session scan A c88dfc4917c0
viz is a command published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 445 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to viz, differing in 6 lines, and is treated as a copy.
viz compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vizsandyup/comfyui-mcp | Command | 1 | 4mo ago | MIT | A | 12 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |