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-firmware-campaigngit 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-firmware-campaign)<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-firmware-campaign"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-firmware-campaign/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-firmware-campaign"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-firmware-campaign.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 | $0.00041 | $0.00535 |
| Opus 5 | $0.00020 | $0.00267 |
| Sonnet 5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
unifi-firmware-campaign 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 Firmware Campaign
Update firmware deliberately — with backups, staging, and verification — not one blind click across everything.
Step 0
get_sysinfo: note controller (UniFi OS) version AND Network application
version. get_device_health_summary: inventory upgradable flags per device.
Order of operations (strict)
- Snapshot: save
list_devices,get_wlans,get_firewall_policiesoutput to./unifi-backups/<date>-pre-firmware.json. - Controller first, then devices: if the UniFi OS / Network application itself has an update, do that in its own maintenance window and let it settle before touching device firmware.
- Canary before fleet: update ONE least-critical AP first; verify ~15 min; then proceed one device at a time. Never "update all" on a production site.
During each update
- Expect state 5 (provisioning) for several minutes — this is NORMAL, not a failure. Do not reboot anything that is merely provisioning.
- APs re-provision after firmware: clients briefly drop (~1–2 min).
- The gateway/UDM updating = whole-site outage window; schedule explicitly with the user and confirm twice.
Post-update verification (per device)
get_device_health_summary: state back to online, version matches target, uptime reset (expected).list_clients: clients re-associated; satisfaction recovers within minutes.- Spot-check the primary SSID connects (
get_wlansunchanged).
Stuck-device ladder
- Still state≠online after 20 min → single
provision_deviceattempt. - Still bad →
restart_device. - Still bad → flag for manual recovery (local UI/SSH) — beyond MCP scope; say so.
Constraints
- One device per message/stage; report between stages.
- Refuse to run updates when user says "quickly" without acknowledging the per-device downtime — get explicit timing approval.
- If a known-bad firmware version is suspected (user reports breakage right after), stop the campaign; document which version rolled out where.
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 · 41 tokens per session scan A b3bd12c41dbd
unifi-firmware-campaign is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 535 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.