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/convertgit 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/convert)<a href="https://agentmods.dev/commands/artokun/comfyui-mcp/convert"><img src="https://agentmods.dev/badge/commands/artokun/comfyui-mcp/convert.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 | $0.00011 | $0.01011 |
| Opus 5 | $0.00005 | $0.00505 |
| Sonnet 5 | $0.00002 | $0.00202 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
convert 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comfy-convert — Convert Workflow Format
The user wants to convert a ComfyUI workflow between the web UI format and the API format.
Instructions
-
Read the workflow file. The argument is: $ARGUMENTS
- If a file path is provided, read it with the Read tool
- If no argument is provided, ask the user for a file path or to paste the JSON
-
Detect the format. Examine the JSON structure:
- UI format: has top-level
"nodes"array and"links"array (this is what "Save" in the web UI produces) - API format: has string keys (node IDs like
"1","2") where each value has"class_type"and"inputs"(this is what "Save (API Format)" produces)
Tell the user which format was detected and which format it will be converted to.
- UI format: has top-level
-
If converting UI format to API format:
a. Iterate over each node in the
"nodes"array. Each node has:id(integer): becomes the string key in API formattype: becomesclass_typewidgets_values: ordered list of widget valuesinputs: array of input slots withname,type, and optionallinkoutputs: array of output slots
b. For each node, call
create_workflow (action:"node_info")with the node'stypeto get the input schema. This tells you:- The order and names of widget inputs (to map
widgets_valuescorrectly) - Which inputs are required vs optional
- Expected types for each input
c. Build the API node's
inputsobject:- Map
widgets_valuesto named inputs using the order fromcreate_workflow (action:"node_info") - For linked inputs (where
linkis not null), find the connection in the"links"array. Each link is[link_id, source_node_id, source_slot, target_node_id, target_slot, type]. Set the input value to["{source_node_id}", source_slot]
d. Assemble the API workflow:
{ "{node_id}": { "class_type": type, "inputs": {...} }, ... } -
If converting API format to UI format:
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 · 79 lines · 11 tokens per session scan A 48571182f890
convert is a command published in the GitHub repository artokun/comfyui-mcp (721 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 1,011 once invoked, about $0.0001 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
setup
You are setting up the Video Recreation Agent Team inside this comfyui-agent repo. Run every step below automatically. Don't ask permission — just do it, report what happened.
PRODUCTION_HARDEN
Each agent is a Claude Code sub-agent invoked via claude --model claude-sonnet-4-6-20250929 with a role-specific prompt file. Agents operate on branches, submit PRs via conventional commits.
PRODUCER
You are the production manager for this open-source VFX tool. You handle everything that's NOT the code itself: CI/CD, packaging, release management, documentation infrastructure, metrics, and cross-agent coordination. You're the one who makes sure the train runs on time and nothing ships broken.
qa-compare
You are the QA 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.
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.