comfy-optimizer

An agent that examines ComfyUI workflows, which are visual pipelines for generating images, and reports possible performance problems.

In plain words
What is it for?
Use it to inspect workflow structure, trace how data moves between nodes, check installed models and system resources, and receive concrete optimization suggestions.
Why use it?
It helps identify slow steps, wasted graphics memory, repeated operations, and settings that do not fit the model or computer being used.

Agent

Part of the comfy plugin — 41 skills, 11 commands, 4 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add agents/artokun/comfyui-mcp/optimizer
Clone the repo
git clone --depth 1 https://github.com/artokun/comfyui-mcp

Or install comfy, the plugin that ships this one along with the rest of its 41 skills, 11 commands, 4 agents, 2 hooks.

Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00018 $0.02261
Opus 5 $0.00009 $0.01130
Sonnet 5 $0.00004 $0.00452
Haiku 4.5 $0.00002 $0.00226

Measured 3d ago against content hash a05b0295cc64, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugin/agents/optimizer.md · 197 lines

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 fixes the user can apply.

Optimization Workflow

Step 1: Load and Understand the Workflow

  1. Visualize the workflow: Use visualize_workflow to generate a mermaid diagram and understand the pipeline structure
  2. Identify the model family: Determine if the workflow uses SD 1.5, SDXL, Flux, SD3, or a video model
  3. Count nodes: Catalog all nodes by type to spot redundancies
  4. Trace the data flow: Follow MODEL, CLIP, VAE, CONDITIONING, LATENT, and IMAGE paths

Step 2: Check System Resources

  1. Get system stats: Use get_system_stats() to determine:
    • Total VRAM and current usage
    • GPU model and capabilities
    • PyTorch version and CUDA version
  2. Check installed models: Use list_local_models to see what's available
  3. 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.

Read the full file on GitHub · 197 lines

Changes

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.

  1. 3d ago First seen · 197 lines · 18 tokens per session scan A a05b0295cc64

Subscribe to this mod's changes

comfy-optimizer is an agent published in the GitHub repository artokun/comfyui-mcp (701 stars, last pushed 3d ago), licensed MIT. It adds 18 tokens to every session and 2,261 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.