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 agentmods add skills/baileywickham/unifi-cli/unifi-clinpx skills add baileywickham/unifi-cli --skill unifi-cligit clone --depth 1 https://github.com/baileywickham/unifi-cliWhat 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 | $0.00049 | $0.00493 |
| Opus 5 | $0.00024 | $0.00246 |
| Sonnet 5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
unifi-cli 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 yesterday.
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.
What it actually says
unifi-cli
CLI for the UniFi Network Integrations API on a local UniFi gateway (Cloud Gateway Ultra, UDM, UDR, etc.).
Prerequisites
-
unifiis on PATH.bun linkinstalls it to~/.bun/bin, which may not be on PATH in every shell — try~/.bun/bin/unifibefore assuming it's missing. If it isn't installed, install it (requires Bun):git clone https://github.com/baileywickham/unifi-cli cd unifi-cli && bun install && bun link -
API key in
UNIFI_API_KEYor~/.config/unifi-cli/config.json. If missing, the CLI prints setup instructions — relay them to the user instead of guessing. (Keys must be created in the gateway's local web UI, not unifi.ui.com — the CLI's error output and the repo README explain this.)
Commands
Prefer --json when you need to parse the output.
unifi devices --json # all UniFi hardware: model, IP, state
unifi device <name|id> # one device: detail + uptime/cpu/memory
unifi clients [--wired|--wireless] # connected clients
unifi sites # sites (usually just "default")
unifi info # network application version
Typical questions this answers: "what APs do I have?" → unifi devices;
"is the living room AP up?" → unifi device living-room;
"what's on my network?" → unifi clients.
Write actions — ask the user first
unifi device restart <name> and unifi device power-cycle <name> <port>
disrupt the network. NEVER run them unless the user explicitly asked for that
action in this conversation. These commands prompt interactively, so when
running them from Claude pass --yes — but only after the user has explicitly
confirmed the action in the conversation.
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.
- yesterday First seen · 46 lines · 49 tokens per session scan A 440184a066c8
unifi-cli is a skill published in the GitHub repository baileywickham/unifi-cli (1 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 493 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
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
implementation-strategy
Decide how to implement runtime and API changes before editing code. Use when a task changes exported APIs, MCP tool definitions, runtime behavior, or configuration, and you need to choose the compatibility boundary and implementation shape.
docs-sync
Audit documentation coverage by comparing implementation against docs/. Use when asked to check doc coverage, sync docs with code, or after significant API surface changes. Produce a report and ask for approval before editing.
pr-draft-summary
Generate a PR-ready summary block with branch suggestion, title, and description. Use in the final handoff after moderate-or-larger code changes; skip for trivial or conversation-only tasks.
code-change-verification
Run the verification stack (format, lint, typecheck, test) when changes affect runtime code, tests, or build config.
typescript
This skill should be used when the user asks to "optimize TypeScript performance", "speed up tsc compilation", "configure tsconfig.json", "fix type errors", "improve async patterns", or encounters TS errors (TS2322, TS2339, "is not assignable to"). Also triggers on .ts, .tsx, .d.ts file work involving type…