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-network-mapgit 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-network-map)<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-network-map"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-network-map/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-network-map"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-network-map.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 | $0.00050 | $0.00645 |
| Opus 5 | $0.00025 | $0.00322 |
| Sonnet 5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
unifi-network-map 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 11d 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 Network Map
Build a persistent, labeled topology file from live controller data plus owner interviews. This becomes shared context that makes every other skill smarter (zone IDs are opaque; names live only here).
Output artifact
Write to $ARGUMENTS path if provided, else ./unifi-network-map.md.
Structure:
# Network Map — [site] (generated [date], Network [version])
## Zones (id → human name → networks/subnets)
| Zone ID | Name | Contains | Purpose |
|---|---|---|---|
| 6a2f…791a | HOME | Default 192.168.1.0/24 | family + NAS + AD |
…
## Hardware
| Name | Model | Role | Uplink | Location (if known) |
## Dependencies ("who breaks if this dies")
- [host] provides [service] to [zones/clients] — e.g. "ns1 = internal DNS for ALL zones"
## Firewall philosophy summary
[2-4 sentences: what's default-blocked, notable exceptions and WHY]
## Open questions
- [unidentified zone/host/purpose → owner]
Workflow
- Harvest everything automatic:
get_networks(subnets, VLANs, domain names)get_firewall_policies(zone ids + custom rule names — rule names often reveal purpose, e.g. "Allow Mike to DNS ALL")list_devices+ per-deviceget_device_details(uplink chains)get_wlans(SSIDs → which network they serve)list_all_clients: cluster clients by subnet/OUI/naming into roles.
- Infer candidate names for opaque zone ids using rule-name anchors (e.g., the source zone of "Allow Mike to…" rules = the home/people zone).
- Interview the owner — ask ONLY what data can't answer, in batches:
- Confirm/correct each inferred zone name + purpose
- What is [unidentified zone/host]? (e.g., TMX_NET, Microtik, INFRA_SPECIAL)
- Critical services & their hosts (DNS, AD, NVR, hypervisors)
- Any known "do not touch" constraints.
- Write the map with an Open Questions section for anything unanswered.
- Maintain: when re-run later, diff against the existing file and update changed sections rather than overwriting blindly.
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.
- 11d ago First seen · 65 lines · 50 tokens per session scan A 9978391742ca
unifi-network-map is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 50 tokens to every session and 645 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.