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 t3chnaztea/unifi-skills --skill templategit clone --depth 1 https://github.com/t3chnaztea/unifi-skillsWrote 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/t3chnaztea/unifi-skills/template)<a href="https://agentmods.dev/skills/t3chnaztea/unifi-skills/template"><img src="https://agentmods.dev/badge/skills/t3chnaztea/unifi-skills/template/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/t3chnaztea/unifi-skills/template"><img src="https://agentmods.dev/badge/skills/t3chnaztea/unifi-skills/template.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00104 | $0.00822 |
| Opus 5 | $0.00052 | $0.00411 |
| Sonnet 5 | $0.00021 | $0.00164 |
| Haiku 4.5 | $0.00010 | $0.00082 |
Grade A, and why
unifi-yourskill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi Yourskill
One or two sentences: what this covers, and that it assumes the auth lanes and
endpoint map from unifi-connect. Cross-reference siblings by name
(unifi-firewall, unifi-wifi, unifi-clients, unifi-context-map) instead
of repeating their content.
Guidelines for a good UniFi skill
Delete this section in your real skill; it is authoring guidance.
- Name:
unifi-<area>, lowercase and hyphens. The directory name MUST equal the frontmattername. - Description: starts with "Use when", lists concrete triggers and symptom phrasings, ends with a "not for X, use Y" pointer. No workflow summary: an agent will follow the description instead of reading the body.
- Parameterize everything site-specific.
<UDM_HOST>never a real address,$UNIFI_API_KEYfrom env never a literal,<DEVICE_ID>/<ZONE_ID>/<MAC>placeholders. Where an example address is unavoidable use the documentation ranges:192.0.2.x(RFC 5737) andaa:bb:cc:dd:ee:ff. - Never include a real inventory. No MAC lists, no camera names or
placements, no WAN address, no SSID names, no household or company names. See
unifi-context-mapfor why this matters more here than in most repos. - Original prose only. Do not paste from Ubiquiti docs or help-centre articles. Write the lesson the docs do not teach, and link the docs as the canonical manual.
- Say which version you verified against, in
compatibilityand in the body for any version-sensitive claim. UniFi moves endpoints between releases with no deprecation notice. A claim stated as universal that was observed once on one controller is the most likely thing in a skill to be wrong. - Distinguish config from operational state. This API will echo back settings it has not applied. If a claim rests on a read-back, say which field and which endpoint proves it.
- Verify against ground truth. Every write ends with a fresh read and a before/after. Show the reader how to confirm, not just how to change.
- Keep
SKILL.mdunder ~500 lines; push heavy detail intoreferences/*.md. - Scripts are allowed here (this repo ships one) but keep them standard-library only, dependency-free, and readable in one sitting. An agent operating someone's gateway should be running code they can audit in five minutes.
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.
- 10d ago First seen · 69 lines · 104 tokens per session scan A 04e393b60cc5
unifi-yourskill is a skill published in the GitHub repository t3chnaztea/unifi-skills (38 stars, last pushed 18d ago), licensed MIT. It adds 104 tokens to every session and 822 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
unifi-cli
Use when asked about UniFi network gear or the local network — access points, gateway, switches, WiFi, or which clients/devices are connected. Queries the local UniFi gateway via the unifi CLI.
lab-hardware-cad
Design custom laboratory hardware as parametric build123d models and export fabrication-ready STEP, STL, and DXF files - microfluidic chips and molds, optomechanical mounts and breadboard adapters, cuvette and microplate holders, tube racks, animal-behavior rigs, and 3D-printed instrument fixtures. Use when a research…
opentrons-integration
Author, review, migrate, simulate, and troubleshoot official Opentrons Python Protocol API v2 protocols for Flex and OT-2 robots. Use for robot-specific liquid handling, deck and labware setup, pipettes, modules, runtime parameters, liquid classes, and Opentrons App analysis. Use pylabrobot instead when one workflow…
pylabrobot
Develop and review PyLabRobot lab-automation resources, liquid-handling plans, offline simulations, and supported-device integrations. Use for PyLabRobot protocols or API questions; keep physical execution behind an explicit operator safety gate.
offensive-wifi
Wireless / 802.11 attack methodology for red team engagements and wireless security assessments. Covers monitor-mode setup, WPA/WPA2-PSK handshake capture and PMKID attacks, WPA3 SAE downgrade and Dragonblood, WPA-Enterprise (EAP) attacks (MSCHAPv2 cracking, EAP-TLS cert theft, evil-twin RADIUS), Karma / Known Beacons…
offensive-wifi-recon
Wi-Fi reconnaissance methodology — adapter selection, monitor mode and packet injection setup, regulatory domain handling, multi-band airspace mapping, hidden SSID discovery, BSSID/ESSID/channel/PMF/encryption fingerprinting, client probe analysis, vendor OUI lookup, war-driving with Kismet/airodump-ng/Wigle, and…