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 colindickson/unifi --skill unifi-network-managergit clone --depth 1 https://github.com/colindickson/unifiWrote 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/colindickson/unifi/unifi-network-manager)<a href="https://agentmods.dev/skills/colindickson/unifi/unifi-network-manager"><img src="https://agentmods.dev/badge/skills/colindickson/unifi/unifi-network-manager/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/colindickson/unifi/unifi-network-manager"><img src="https://agentmods.dev/badge/skills/colindickson/unifi/unifi-network-manager.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 | $0.00173 | $0.01545 |
| Opus 5.5 | $0.00069 | $0.00618 |
| Sonnet 5.5 | $0.00035 | $0.00309 |
| Haiku 4.5 | $0.00017 | $0.00154 |
Grade A, and why
unifi-network-manager 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 2mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi Network Manager (CLI)
Overview
unifi is a CLI wrapping the UniFi Network Integration API
(https://{host}/proxy/network/integration/v1, X-API-KEY auth). Use it to
inspect and manage a local UniFi console. JSON is the default output — parse it
to answer.
Safety (read first)
- READ before WRITE — inspect with list/get/stats before any mutation.
- Every mutation requires
--yes. First state exactly what will happen and get the user's explicit confirmation in conversation (e.g. "This reboots AP (id ...) — proceed?"), THEN run the command with--yes. - You operate the user's real network. Never run a mutation the user did not approve, and keep actions scoped to the network they asked about. If a request is ambiguous or risky, stop and ask.
Setup Check
- Verify the tool:
command -v unifi. If missing, tell the user to install it (repo hasmake install). Do NOT install it yourself without asking. - Test connectivity:
unifi info.
If you see host is required or auth errors, config is missing. Precedence:
flags > env (UNIFI_HOST, UNIFI_API_KEY, UNIFI_SITE, UNIFI_INSECURE) >
file (~/.config/unifi/config.json). Have the user configure it themselves —
never ask for the API key in chat:
unifi configure --host <ip> --insecure # set UNIFI_API_KEY in their env
Local consoles use self-signed certs, so --insecure is normally required.
Workflow
- Discover the site first if unknown:
unifi sites list→ use the siteidas--site. One site → use it (often named "default"). - Use
--allfor the complete list (handles pagination); else--limit N.
Read commands
unifi info # connectivity check
unifi sites list # get site id
unifi devices list --site <id> # APs/switches/gateways
unifi devices get <deviceId> --site <id>
unifi devices stats <deviceId> --site <id> # health telemetry
unifi clients list --site <id> --all # connected devices
unifi clients get <clientId> --site <id>
unifi vouchers list --site <id> # guest WiFi vouchers
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 127 lines · 173 tokens per session scan A 69fe6e47a67d
unifi-network-manager is a skill published in the GitHub repository colindickson/unifi (3 stars, last pushed 4mo ago), licensed MIT. It adds 173 tokens to every session and 1,545 once invoked, about $0.0007 per session on Opus 5.5. 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.
unifi-network-manager compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| unifi-network-managercolindickson/unifi | Skill | 3 | 4mo ago | MIT | A | 173 | Claude Code, Codex |
| lab-hardware-cadK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 108 | Claude Code |
| opentrons-integrationK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| pylabrobotK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 49 | Claude Code |
| pybammK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 70 | Claude Code, Codex |
| offensive-wifiSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 183 | Claude Code, Codex |
| offensive-wifi-reconSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 130 | Claude Code, Codex |