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 mikeholownych/unifi-mcp --skill unifi-whos-homegit clone --depth 1 https://github.com/mikeholownych/unifi-mcpWrote 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/mikeholownych/unifi-mcp/unifi-whos-home)<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-whos-home"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-whos-home/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/mikeholownych/unifi-mcp/unifi-whos-home"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-whos-home.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00073 | $0.00746 |
| Opus 5 | $0.00036 | $0.00373 |
| Sonnet 5 | $0.00015 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
unifi-whos-home 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi Who's Home
Friendly inventory of everything connected to the network, translated into everyday language — plus careful handling of genuinely unknown devices.
Key knowledge
- Randomized MACs are normal: modern phones/laptops use a different fake MAC per WiFi network and often lack hostnames. A phone can appear as "Unknown (Apple)" — that is not an intruder.
- OUI tells you the maker: the start of a MAC identifies the manufacturer
(the client
ouifield). Translate: Apple→iPhone/Mac, Samsung→TV/phone, Sonos→speaker, Raspberry-Pi/Proxmox→homelab box, etc. - Infra devices must never be blocked: APs, switches, NAS, DNS servers.
Cross-check candidates against
list_devices(your actual hardware) before proposing any block.
Workflow
- Inventory —
list_clients(connected now); group as:- Your equipment (matches
list_devices) - Recognizable family stuff (named or obvious OUI: phones, TVs, printers)
- Unknown — list separately with every clue: maker (oui), name/hostname, connection type, first/last seen.
- Your equipment (matches
- Translate each unknown: "Unknown 'bc:24:11…' = a virtual machine on your Proxmox server", "Unknown 'Apple' = someone's iPhone using private-address mode".
- Suspicion checklist (only flag if several hold):
- wireless + unknown maker + active right now + nobody recognizes it
- appeared between dates the user can place
- NOT seen on wired ports
- For each unknown, ask the owner-in-the-house: "do you own a [maker] device?"
- Yes → suggest naming it in the UniFi app so future audits are clean.
- No / unsure → offer
block_clientAFTER stating plainly what blocking does ("it will be kicked off and unable to rejoin until we allow it back") and get explicit confirmation.
- Reassure with facts: WPA2/WPA3 means strangers can't join without the password; unknown entries are usually family gadgets with privacy features.
Output format
Who's home right now: [N devices]
🏠 Your gear: [count] · 👪 Recognized: [count] · ❓ Unknown: [count]
❓ Unknown devices:
1. [maker/OS guess] — [name] — [where seen] — [first seen date]
Likely is: [best plain-English guess]
Want me to [action] on #X?
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.
- 12d ago First seen · 65 lines · 0 tokens per session scan A cb9c7f7b5882
unifi-whos-home is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 73 tokens to every session and 746 once invoked, about $0.0004 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 2026-08-31.
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.