portable-comfyui

portable-comfyui is a skill for Claude Code, Codex from aivrar/portable-hermes-agent. It costs 15 tokens per session (1,635 once invoked), scanned B, original, MIT.

A local image-generation setup built around ComfyUI, a visual tool for connecting AI image-processing steps. It can manage the setup, its models and nodes, and generate images with Stable Diffusion and other models.

In plain words
What is it for?
Use it to install or manage portable ComfyUI, inspect its status and GPU information, manage models and nodes, and generate images.
Why use it?
It lets you run image generation on the local machine and provides commands for installing and managing the required servers and models.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to install or manage portable ComfyUI, inspect its status and GPU information, manage models and nodes, and generate images.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aivrar/portable-hermes-agent/portable-comfyui
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.

Any agent
npx skills add aivrar/portable-hermes-agent --skill portable-comfyui
Clone the repo
git clone --depth 1 https://github.com/aivrar/portable-hermes-agent

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for portable-comfyui

README.md
[![agentmods](https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/portable-comfyui/github.svg)](https://agentmods.dev/skills/aivrar/portable-hermes-agent/portable-comfyui)
Your own site
<a href="https://agentmods.dev/skills/aivrar/portable-hermes-agent/portable-comfyui"><img src="https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/portable-comfyui/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for portable-comfyui

Your own site · 80×15
<a href="https://agentmods.dev/skills/aivrar/portable-hermes-agent/portable-comfyui"><img src="https://agentmods.dev/badge/skills/aivrar/portable-hermes-agent/portable-comfyui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,635 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 47 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Server-Side Request Forgery · line 48
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 49
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 50
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 63
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 82
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 83
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 84
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 87
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 98
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 101
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 114
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 121
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 122
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 123
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Server-Side Request Forgery · line 142
    Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.
    Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
  • medium Data Exfiltration · line 55
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 56
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 57
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 66
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 73
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 5.1 $0.00015 $0.01635
Opus 5 $0.00008 $0.00817
Sonnet 5 $0.00003 $0.00327
Haiku 4.5 $0.00002 $0.00163

Measured 6d ago against content hash 679dae717073, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

portable-comfyui scanned grade B with 1 finding 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 6d 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

r = httpx.post("http://127.0.0.1:5000/api/install") # Full install
skills/extensions/portable-comfyui/SKILL.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ComfyUI Image Generator - Hermes Skill

You have access to a portable ComfyUI installation for AI image generation with Stable Diffusion and other models.

When to Use

Use this skill when the user wants to install or manage the portable ComfyUI extension, work with its models or nodes, or generate images through a local ComfyUI instance.

Server Info

  • Installer API: http://127.0.0.1:5000 (management)
  • ComfyUI Web UI: http://127.0.0.1:8188 (when instance is running)
  • Location: extensions/comfyui/

Quick Start

If not running, start the management server:

cd extensions/comfyui && launcher.bat

If not installed yet:

cd extensions/comfyui && install.bat

Architecture

ComfyUI has two layers:

  1. Installer/Manager API (port 5000) — manages instances, models, nodes
  2. ComfyUI instances (port 8188+) — the actual image generation servers

Management API Endpoints (use via terminal with python httpx)

System Status

import httpx
r = httpx.get("http://127.0.0.1:5000/api/status")   # Overall status
r = httpx.get("http://127.0.0.1:5000/api/gpus")      # GPU info
r = httpx.get("http://127.0.0.1:5000/api/settings")  # Current settings

Install ComfyUI

r = httpx.post("http://127.0.0.1:5000/api/install")        # Full install
r = httpx.post("http://127.0.0.1:5000/api/update")         # Update ComfyUI
r = httpx.post("http://127.0.0.1:5000/api/install/sage-attention")  # Install SageAttention

Instance Management (multi-GPU)

# List all instances
r = httpx.get("http://127.0.0.1:5000/api/instances")

# Create new instance
r = httpx.post("http://127.0.0.1:5000/api/instances", json={
    "gpu": 0,       # GPU index
    "port": 8189,   # Port for this instance
    "vram": "normal" # normal, low, cpu
})

# Start/Stop instances
httpx.post("http://127.0.0.1:5000/api/instances/{id}/start")
httpx.post("http://127.0.0.1:5000/api/instances/{id}/stop")
httpx.post("http://127.0.0.1:5000/api/instances/start-all")
httpx.post("http://127.0.0.1:5000/api/instances/stop-all")

Read the full file on GitHub · 164 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. 6d ago First seen · 164 lines · 15 tokens per session scan B 679dae717073

Subscribe to this mod's changes

portable-comfyui is a skill published in the GitHub repository aivrar/portable-hermes-agent (217 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,635 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.