unifi-mcp: Skill for Claude Code

.agents/skills/unifi-client-data-correctness/SKILL.md

myco:unifi-client-data-correctness is a skill for Claude Code from sirkirby/unifi-mcp. It costs 222 tokens per session (3,407 once invoked), scanned A, original, MIT.

A coding guide for retrieving client-device data from UniFi network controllers. UniFi is a networking product family, and a monorepo is one repository containing multiple related applications and packages.

In plain words
What is it for?
Changing, debugging, or extending UniFi client retrieval in Python models, manager code, and GraphQL types.
Why use it?
It helps prevent incorrect device status or details caused by using the wrong controller endpoint, mismatching data models, or skipping fallback and merge rules.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is sirkirby/unifi-mcp's own configuration. It tells Claude Code how to work on unifi-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unifi-mcp configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/live_smoke.py --server network --phase readonly --tool unifi_list_clients.

Reuse

Borrowing it

Nothing to install: this file belongs to sirkirby/unifi-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sirkirby/unifi-mcp/main/.agents/skills/unifi-client-data-correctness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sirkirby/unifi-mcp

Made for: Claude Code.

Wrote 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.

agentmods badge for myco:unifi-client-data-correctness

README.md
[![agentmods](https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/unifi-client-data-correctness/github.svg)](https://agentmods.dev/skills/sirkirby/unifi-mcp/unifi-client-data-correctness)
Your own site
<a href="https://agentmods.dev/skills/sirkirby/unifi-mcp/unifi-client-data-correctness"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/unifi-client-data-correctness/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.

agentmods 80×15 button for myco:unifi-client-data-correctness

Your own site · 80×15
<a href="https://agentmods.dev/skills/sirkirby/unifi-mcp/unifi-client-data-correctness"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/unifi-client-data-correctness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 222 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,407 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00222 $0.03407
Opus 5 $0.00111 $0.01703
Sonnet 5 $0.00044 $0.00681
Haiku 4.5 $0.00022 $0.00341

Measured 11d ago against content hash 34a6b40f132f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

myco:unifi-client-data-correctness 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/unifi-client-data-correctness/SKILL.md · 327 lines

How it starts

The opening of the file, as written. The whole thing — 327 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UniFi Client Data Retrieval Correctness

This skill covers the five correctness patterns required when reading, mapping, or extending UniFi client data in the unifi-mcp monorepo. The patterns were validated against a live UDM SE controller and surfaced four production bugs (Issues #297–#298, PRs #299–#300) in a single release cycle. Each pattern is a permanent fixture — violating any one of them silently corrupts client data for a measurable fraction of real devices.

Primary files:

  • packages/unifi-core/src/unifi_core/network/models/clients.py — model factories (client_from_controller, blocked_client_from_controller, client_lookup_from_controller) and the _is_online() helper
  • packages/unifi-core/src/unifi_core/network/managers/client_manager.pyget_client_details() with dual-endpoint fallback and merge logic
  • apps/api/src/unifi_api/graphql/types/network/client.py — Strawberry GraphQL types (Client, BlockedClient, ClientLookup) that mirror the Pydantic models

Prerequisites

Before working on any client retrieval code, confirm:

  1. You know which endpoint is the data source for the code path you are changing (/stat/sta vs /rest/user). The two have radically different field coverage; a change that is correct for one may be wrong for the other.
  2. You have access to raw controller payloads (via scripts/live_smoke.py --server network --phase readonly --tool unifi_list_clients) to verify field presence. Do not assume field presence based on documentation or past experience — firmware variance is real.
  3. Any bug report must include: controller hardware, UniFi OS version, Network Application version, and the raw API payload showing the unexpected value. Implement fixes only after the root cause is confirmed in the raw payload (not inferred from shaped output).

Procedure 1: Choose the Right Endpoint

Use /stat/sta (active connections) as the primary source for client details. Fall back to /rest/user (historical snapshots) only for offline clients or transient failures. Never invert this order.

Read the full file on GitHub · 327 lines

Changes

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.

  1. 11d ago First seen · 327 lines · 222 tokens per session scan A 34a6b40f132f

Subscribe to this mod's changes

myco:unifi-client-data-correctness is a skill published in the GitHub repository sirkirby/unifi-mcp (803 stars, last pushed today), licensed MIT. It adds 222 tokens to every session and 3,407 once invoked, about $0.0011 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.

Related

Other skills, from other repositories

streamdeck-designer

Design, theme, and author complete Stream Deck layouts for the user's hardware using the streamdeck-mcp tools. Use whenever the user wants a custom Stream Deck setup, asks for a themed deck (e.g. "hello-kitty Twitch deck", "retrowave music controls", "a dev deck for this repo"), wants buttons or dials configured for…

verygoodplugins/streamdeck-mcp · 167 tokens

streamdeck-profile

Use this skill when you need to configure Elgato Stream Deck desktop profiles without taking USB control of the hardware.

verygoodplugins/streamdeck-mcp · 0 tokens

unifi-udm-pro-mcp

UniFi UDM Pro MCP Server for managing networks, connected clients, Wi-Fi settings, and device health via Model Context Protocol.

rodolfoconcepcion/unifi-udm-pro-mcp · 35 tokens

aurora

Aurora Smart Home orchestrator — routing layer for all smart home skills. Use this skill when the user asks ANY smart home question and you need to decide which skill to invoke, or when a task spans multiple skills (e.g., "build a sensor that shows on a dashboard and triggers automations"). Invoke aurora FIRST before…

tonylofgren/aurora-smart-home · 133 tokens

HA Integration Dev

Home Assistant custom integration development in Python. Covers customcomponents, DataUpdateCoordinator, configflow, OAuth2, conversation agent, HACS publishing, device registry, entity platforms, services, repair issues, diagnostics, Bluetooth integrations, and multi-coordinator patterns.

tonylofgren/aurora-smart-home · 55 tokens

Node-RED

Node-RED visual automation flows for Home Assistant. Covers visual automation, flow JSON, trigger-state, api-call-service, function nodes, context storage, timer patterns, error handling, and node-red-contrib-home-assistant-websocket nodes. Use when user mentions "Node-RED", "flow", "visual automation", or…

tonylofgren/aurora-smart-home · 76 tokens