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-setup-new-devicegit 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-setup-new-device)<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-setup-new-device"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-setup-new-device/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-setup-new-device"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-setup-new-device.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 | $0.00067 | $0.00677 |
| Opus 5 | $0.00034 | $0.00338 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
unifi-setup-new-device 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi Setup New Device
Get a new gadget online and properly registered — written for people who have never touched a router settings page.
Why smart gadgets fail (explain these first)
- They need 2.4GHz: most smart plugs/cameras only speak the older "2.4GHz" WiFi. Modern routers broadcast both bands under ONE name — usually fine — but during setup the phone doing the pairing must ALSO be on 2.4GHz sometimes.
- WPA3 transition hiccups: very old or cheap IoT chips choke on newer
security. If a device loops "connecting…" forever, temporary fix options:
guest-network trick or (last resort) disabling WPA3 transition briefly via
update_wlan(wpa3_transition=false)— remember to restore it after! - Password typos: passwords are case-sensitive; watch for confusables (l/I, O/0).
Workflow
- Find out what they're setting up — type matters (smart plug vs TV vs console).
- Search for it:
list_all_clients— match by maker (oui), recent last_seen, or partial name. Alsolist_clientsfor live view.- Found → go to 3.
- Not found → walk them through the device app pairing attempt while you
watch
list_clients; if still invisible after 2 tries, apply Fix #1/#2 above.
- Verify it landed correctly: has an IP, sits on the expected network,
decent connection (
get_client_details). - Register it properly:
- Naming has no MCP tool — give exact UniFi-app taps: Clients → [device] → ⋯ → Rename. (Explain WHY: named devices make every future audit/troubleshoot clearer.)
- If it's something that should always be reachable (NAS, camera hub,
printer): offer
reserve_client_ipso its address never changes — explain "like a reserved parking spot".
- Wrap-up: confirm internet works ON the device (have them test), summarize what was done in one friendly paragraph.
Output style
- Short numbered steps; one action per step.
- Every instruction names WHO does it: "You: open the plug's app…" / "Me: checking your network now…"
- Celebrate completion briefly. No technical recap unless asked.
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 · 56 lines · 0 tokens per session scan A acc8094a58c7
unifi-setup-new-device is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 67 tokens to every session and 677 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 2026-08-31.
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.