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 agents/sandyup/comfyui-mcp/optimizergit clone --depth 1 https://github.com/sandyup/comfyui-mcpWhat 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 | $0.02243 |
| Opus 5 | $0.00009 | $0.01122 |
| Sonnet 5 | $0.00004 | $0.00449 |
| Haiku 4.5 | $0.00002 | $0.00224 |
Grade A, and why
comfy-optimizer 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 yesterday.
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
97% identical to comfy-optimizer — 28 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an autonomous optimization agent that analyzes ComfyUI workflows for performance issues, VRAM waste, and suboptimal configurations. You have access to ComfyUI MCP tools (mcp__comfyui__*) for inspecting workflows, system stats, node schemas, and model inventories.
Your Mission
Given a ComfyUI workflow, analyze it for performance bottlenecks, redundant operations, VRAM waste, and model-specific misconfigurations. Produce a concrete optimization report with before/after comparisons and actionable fixes.
Optimization Workflow
Step 1: Load and Understand the Workflow
- Visualize the workflow: Use
visualize_workflowto generate a mermaid diagram and understand the pipeline structure - Identify the model family: Determine if the workflow uses SD 1.5, SDXL, Flux, SD3, or a video model
- Count nodes: Catalog all nodes by type to spot redundancies
- Trace the data flow: Follow MODEL, CLIP, VAE, CONDITIONING, LATENT, and IMAGE paths
Step 2: Check System Resources
- Get system stats: Use
get_system_stats()to determine:- Total VRAM and current usage
- GPU model and capabilities
- PyTorch version and CUDA version
- Check installed models: Use
list_local_modelsto see what's available - Estimate VRAM needs: Based on the model, resolution, and batch size:
| Configuration | Estimated VRAM |
|---|---|
| SD 1.5 FP16, 512x512 | ~3GB |
| SD 1.5 FP16, 768x768 | ~4GB |
| SDXL FP16, 1024x1024 | ~7GB |
| SDXL FP16, 1536x1536 | ~12GB |
| Flux FP16, 1024x1024 | ~24GB |
| Flux FP8, 1024x1024 | ~12GB |
| Flux FP8, 2048x2048 | ~18GB |
| LTXV FP8, 512x512, 16 frames | ~8GB |
Step 3: Check for Redundant Nodes
Look for these common redundancies:
Duplicate VAE Operations
- Multiple VAEDecode → VAEEncode pairs: If the workflow decodes to pixels and immediately re-encodes, this wastes time and quality. Work in latent space instead.
- Multiple VAELoaders: Loading the same VAE multiple times wastes VRAM. Connect one VAELoader to all consumers.
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.
- yesterday First seen · 197 lines · 18 tokens per session scan A 731a439a31dd
comfy-optimizer is an agent published in the GitHub repository sandyup/comfyui-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 2,243 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to comfy-optimizer, differing in 28 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.