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 skills add aivrar/portable-hermes-agent --skill portable-comfyuigit clone --depth 1 https://github.com/aivrar/portable-hermes-agentWrote 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/skills/aivrar/portable-hermes-agent/portable-comfyui)<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.
<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>- NVIDIA SkillSpector warn
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.
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 5.1 | $0.00015 | $0.01635 |
| Opus 5 | $0.00008 | $0.00817 |
| Sonnet 5 | $0.00003 | $0.00327 |
| Haiku 4.5 | $0.00002 | $0.00163 |
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 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:
- Installer/Manager API (port 5000) — manages instances, models, nodes
- 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")
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.
- 6d ago First seen · 164 lines · 15 tokens per session scan B 679dae717073
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.
Other skills, from other repositories
summer-warm-color
A bright, hand-painted summer illustration style built from sky blue, grass green, sunshine yellow, and small warm accents. It uses watercolor-like textures, playful scenes, and relaxed handwritten headings.
olive-elegant
A classic editorial style based on deep olive green, cream tones, serif headings, plant motifs, and fine gold details.
oriental-poetic-illustration
A quiet illustration style inspired by East Asian ink paintings, with bamboo, moonlight, fine lines, and generous empty space.
splash-abstract
A bold abstract style that splashes orange-red, magenta, violet, teal, and bright blue across a light background. It uses oversized type, irregular shapes, liquid color areas, and energetic motion.
mint-fresh
A presentation design guide for a fresh, natural look built around pale green colors, generous space, plant drawings, and gentle motion.
vaporwave
A vaporwave-inspired visual design style using deep purple backgrounds, pink and cyan gradients, translucent cards, and retro-futurist details. Vaporwave is an internet art style associated with nostalgia for imagined versions of late-20th-century digital culture.