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 agentmods add commands/artokun/comfyui-mcp/installgit clone --depth 1 https://github.com/artokun/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/artokun/comfyui-mcp/install)<a href="https://agentmods.dev/commands/artokun/comfyui-mcp/install"><img src="https://agentmods.dev/badge/commands/artokun/comfyui-mcp/install.svg" alt="Measured on agentmods" 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 | $0.00008 | $0.00830 |
| Opus 5 | $0.00004 | $0.00415 |
| Sonnet 5 | $0.00002 | $0.00166 |
| Haiku 4.5 | $0.00001 | $0.00083 |
Grade A, and why
install 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 5d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comfy-install — Install a Custom Node Pack
The user wants to install a ComfyUI custom node pack from the registry or a GitHub repository.
Instructions
-
Parse the argument. The argument is: $ARGUMENTS
If no argument was provided, ask the user what node pack they want to install.
Determine the source type:
- GitHub URL: starts with
https://github.com/; use it directly - Registry ID: a slug like
comfyui-impact-pack; search for it - Descriptive name: like "Impact Pack" or "ControlNet"; search for it
- GitHub URL: starts with
-
Find the pack. If not a direct GitHub URL:
- Call
search_custom_nodes(action: "search") with the argument asquery - Present the top results: name, description, author, star count
- If multiple matches, ask the user to confirm which one they want
- Call
search_custom_nodes(action: "details") with the selected pack ID for full info including the repository URL
- Call
-
Confirm with the user. Before installing, show:
- Pack name and description
- Author and repository URL
- Number of nodes included (if available)
- Ask for explicit confirmation to proceed
-
Determine the custom_nodes directory. The custom nodes directory is typically at the ComfyUI base path under
custom_nodes/. Checkget_system_statsif needed to find the ComfyUI installation path. Verify the directory exists. -
Clone the repository. Use the Bash tool to:
git clone {repo_url} {custom_nodes_dir}/{pack_name}If the directory already exists, inform the user and ask if they want to update it (
git pull) instead. -
Install dependencies. Check for dependency files in the cloned directory:
- If
requirements.txtexists: runpip install -r requirements.txtusing ComfyUI's Python venv - If
install.pyexists: run it with ComfyUI's Python interpreter - Use the venv Python path (e.g.,
.venv/Scripts/python.exeon Windows or.venv/bin/pythonon Linux/macOS)
- If
-
Restart ComfyUI. Tell the user that new nodes require a restart to be loaded. Offer to call
restart_comfyuito restart automatically.
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.
- 5d ago First seen · 69 lines · 8 tokens per session scan A d885b2278daa
install is a command published in the GitHub repository artokun/comfyui-mcp (716 stars, last pushed yesterday), licensed MIT. It adds 8 tokens to every session and 830 once invoked, about $0.0000 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 commands, from other repositories
qa-compare
You are the QA expert in the Video Recreation Agent Team.
NUKE_COMP
You are a senior VFX compositor with deep Nuke pipeline experience who has transitioned into pipeline TD work. You think about tool integration the way a compositor thinks about a comp tree — everything must connect cleanly, data must flow predictably, and the artist should never have to think about the plumbing.
analyze-video
You are the ANALYST expert in the Video Recreation Agent Team.
assemble-montage
You are the EDITOR expert in the Video Recreation Agent Team.
COMFY_LEAD
You are the ComfyUI technical lead. You know ComfyUI's API, node system, workflow JSON format, and the MCP protocol deeply. You're hardening an AI co-pilot that helps VFX artists work with ComfyUI through natural language.
VFX_SUPER
You are a VFX supervisor with 15+ years in commercial VFX (lighting, compositing, look-dev). You're the quality gate for anything artist-facing in this AI co-pilot. Your job: ensure every interaction, error message, and documentation choice makes sense to a Lighting TD or compositor who has ZERO developer background.