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/sandyup/comfyui-mcp/recipegit 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/recipe)<a href="https://agentmods.dev/commands/sandyup/comfyui-mcp/recipe"><img src="https://agentmods.dev/badge/commands/sandyup/comfyui-mcp/recipe.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 | $0.00018 | $0.02175 |
| Opus 5 | $0.00009 | $0.01087 |
| Sonnet 5 | $0.00004 | $0.00435 |
| Haiku 4.5 | $0.00002 | $0.00217 |
Grade A, and why
recipe 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 3d 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 recipe — 54 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comfy-recipe — Multi-Step Generation Recipes
The user wants to run a predefined multi-step image generation pipeline. Each recipe chains multiple workflows together, passing the output of one step as input to the next.
Instructions
-
Parse the arguments. The argument is: $ARGUMENTS
If no argument was provided, list the available recipes and ask the user to choose one.
Extract:
- Recipe name: the first word (e.g.,
portrait,hires-fix,product-shot,style-transfer) - Prompt: everything after the recipe name
- Recipe name: the first word (e.g.,
-
Available recipes:
portrait— Generate a portrait and upscale itproduct-shot— Generate a product image with clean backgroundhires-fix— Generate at low resolution, then upscale with img2img for more detailstyle-transfer— Apply a style prompt to an existing image via img2imgmorph— Generate two frames and create a smooth morph video between them
-
Check available models. Call
list_local_modelswithmodel_type: "checkpoints"to find a checkpoint. Also checkmodel_type: "upscale_models"for upscale recipes. If models are missing, download appropriate ones before proceeding. -
Execute the recipe. For each step, create the workflow, run it, and chain the output.
Portrait Recipe
- Step 1 — Generate:
create_workflowwithtxt2img, prompt from user, 1024x1024, 25 steps, cfg 7 - Step 2 — Upscale:
create_workflowwithupscale, using the output image from Step 1, 2x upscale - Final output: 2048x2048 upscaled portrait
Product-Shot Recipe
- Step 1 — Generate:
create_workflowwithtxt2img, prompt from user (append "product photography, clean white background, studio lighting" to the prompt), 1024x1024, 25 steps, cfg 7 - Step 2 — Remove background: If a background removal node is available, create a workflow to remove the background. Otherwise, skip this step and note it for the user.
- Final output: product image (with or without background removal)
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.
- 3d ago First seen · 126 lines · 18 tokens per session scan A dcac63e35093
recipe is a command published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,175 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to recipe, differing in 54 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.