AuC is a Python framework for running a single AI agent with an asynchronous, pluggable reasoning loop, language-model adapters, permission levels, and observable events. It is used to build coding and conversational agents with tools, security checks, web interfaces, background jobs, evaluations, and isolated execution. The catalogue entries are skills for extending its agent workflow.
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 ufy2024/AuC --skill homelab-vlan-segmentationgit clone --depth 1 https://github.com/ufy2024/AuCWrote 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/ufy2024/auc/homelab-vlan-segmentation)<a href="https://agentmods.dev/skills/ufy2024/auc/homelab-vlan-segmentation"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/homelab-vlan-segmentation/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/ufy2024/auc/homelab-vlan-segmentation"><img src="https://agentmods.dev/badge/skills/ufy2024/auc/homelab-vlan-segmentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 21 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00056 | $0.03074 |
| Opus 5 | $0.00028 | $0.01537 |
| Sonnet 5 | $0.00011 | $0.00615 |
| Haiku 4.5 | $0.00006 | $0.00307 |
Grade A, and why
homelab-vlan-segmentation 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 7d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- homelab-vlan-segmentation — 86% identical, 28 lines differ
- homelab-vlan-segmentation — 81% identical, 29 lines differ
- homelab-vlan-segmentation — 81% identical, 29 lines differ
How it starts
The opening of the file, as written. The whole thing — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Homelab VLAN Segmentation
How to split a home network into isolated VLANs so IoT devices, guests, and your main PCs cannot talk to each other. The most impactful security upgrade for a home network.
All firewall rules shown here add isolation between segments — they do not remove existing protections. Apply changes in a maintenance window and verify connectivity between segments after each step before moving on.
When to Use
- Setting up VLANs on a home network for the first time
- Isolating IoT devices (smart bulbs, cameras, TVs) from trusted devices
- Creating a guest Wi-Fi network that cannot reach home devices
- Explaining how VLANs work to someone unfamiliar with the concept
- Configuring trunk ports, access ports, and SSID-to-VLAN mapping
- Troubleshooting inter-VLAN routing or firewall rule issues on pfSense/OPNsense/UniFi
How It Works
Without VLANs — flat network:
All devices on 192.168.1.0/24
Smart TV (potential malware) → can reach your NAS, PCs, everything
With VLANs:
VLAN 10 — Trusted 192.168.10.0/24 (PCs, phones, laptops)
VLAN 20 — IoT 192.168.20.0/24 (smart TV, bulbs, cameras)
VLAN 30 — Servers 192.168.30.0/24 (NAS, Pi, VMs)
VLAN 40 — Guest 192.168.40.0/24 (visitor Wi-Fi)
VLAN 99 — Management 192.168.99.0/24 (switch/AP web UIs)
Smart TV → blocked from reaching 192.168.10.0/24 and 192.168.30.0/24
Guests → internet only, cannot see any home devices
VLAN Design Template
VLAN Name Subnet Gateway Purpose
10 trusted 192.168.10.0/24 192.168.10.1 PCs, phones, laptops
20 iot 192.168.20.0/24 192.168.20.1 Smart home devices
30 servers 192.168.30.0/24 192.168.30.1 NAS, Pi, self-hosted
40 guest 192.168.40.0/24 192.168.40.1 Visitor Wi-Fi
99 management 192.168.99.0/24 192.168.99.1 Network gear web UIs
Examples
Typical homelab with UniFi AP and managed switch:
Scenario: 3-bedroom house, UniFi Dream Machine + UniFi 8-port switch + 2 APs
VLAN 10 — Trusted 192.168.10.0/24 MacBook, iPhones, iPad
VLAN 20 — IoT 192.168.20.0/24 Nest thermostat, Philips Hue, Ring doorbell, smart TVs
VLAN 30 — Servers 192.168.30.0/24 Synology NAS (192.168.30.10), Pi-hole (192.168.30.2)
VLAN 40 — Guest 192.168.40.0/24 Visitor Wi-Fi — internet only
SSID → VLAN mapping:
"Home" → VLAN 10 (WPA2, strong password, trusted devices only)
"IoT" → VLAN 20 (WPA2, separate password, printed on router for setup)
"Guest" → VLAN 40 (WPA2, simple password you can share freely)
Switch port behavior:
Port 1 → trunk to router (tagged VLANs 10,20,30,40,99)
Port 2 → trunk to APs (tagged VLANs 10,20,40; AP handles per-SSID tagging)
Port 3 → access VLAN 30 (NAS — untagged, no VLAN awareness needed)
Port 4 → access VLAN 30 (Pi-hole — untagged)
Port 5–8 → access VLAN 10 (wired workstations)
Firewall rules applied (all rules add isolation, none remove existing protections):
IoT → Trusted: BLOCK
IoT → Servers: BLOCK except 192.168.30.2:53 (Pi-hole DNS allowed)
IoT → Internet: ALLOW
Guest → Local networks: BLOCK
Guest → Internet: ALLOW
Trusted → everywhere: ALLOW
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.
- 7d ago First seen · 334 lines · 56 tokens per session scan A d303c131f0f4
homelab-vlan-segmentation is a skill published in the GitHub repository ufy2024/AuC (1,090 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 3,074 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.