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-grant-device-accessgit 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-grant-device-access)<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-grant-device-access"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-grant-device-access/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-grant-device-access"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-grant-device-access.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 | $0.00042 | $0.00925 |
| Opus 5 | $0.00021 | $0.00463 |
| Sonnet 5 | $0.00008 | $0.00185 |
| Haiku 4.5 | $0.00004 | $0.00093 |
Grade A, and why
unifi-grant-device-access 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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Step 0 — Version check (always first)
Fetch get_sysinfo and note the Network application version. The controller
facts in this skill were verified on Network 10.x / UniFi OS 5.x; on older
versions expect differences (e.g., legacy stat/alarm exists, band steering
uses an older flag). Adapt claims to the version you see.
UniFi Grant Device Access
Guarantee a specific device (e.g., a desktop, server, or NAS) can always reach everything on the network: DHCP reservation + zone-based firewall allow rules, scoped to that device's MACs.
Context (read first)
- Require
UNIFI_MODE=local. Resolve the device:- If given an IP/name, find it via
list_all_clients(has MACs) andget_client_details. - If not found in known clients, ask the user to connect it once, or accept a MAC address directly.
- If given an IP/name, find it via
- Map zones:
get_firewall_policies— note each policy's source/destinationzone_id. Identify:- The zone containing the device's current network.
- Which destination zones are already covered by existing rules for these MACs.
Controller facts
- Zone firewall policies are per src-zone→dst-zone pairs; there is no "any zone" target. One rule per pair is required.
- Deriving the source zone: the controller does not expose zone names or a
networks→zones mapping. Find it by locating an existing custom policy scoped
to known devices on the same network (
source.client_macsof rules like "Allow to X ALL") and copying itssource.zone_id. Do not guess by elimination — gateway-like zones allow-all everywhere and look similar to home zones in policy dumps. - The controller auto-creates "(Return)" companion policies for custom rules.
- Some zone pairs are rejected at creation ("traffic not allowed") — typically ISP-managed IPTV and WAN pairs. Surface the verbatim error and skip that pair; it is usually intentional (nothing to access there anyway).
- Do not create rules targeting the EXTERNAL/WAN zone — internet access is governed by the home zone's general policy, and bypassing it undermines forced-internal-DNS designs.
- DHCP reservation =
use_fixedip:true+fixed_ipon the client record.
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 · 82 lines · 42 tokens per session scan A 48270c97f5da
unifi-grant-device-access is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 42 tokens to every session and 925 once invoked, about $0.0002 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.