home-network

home-network is a skill for Claude Code from xiaolai/mac-it-guy-pro. It costs 70 tokens per session (1,481 once invoked), scanned A, original, MIT.

A troubleshooting guide for home networks that helps identify whether a problem is in a device, Wi-Fi, the router, or the internet provider. It also covers free fixes, hardware choices, connecting machines, and basic security.

In plain words
What is it for?
Use it to diagnose home-network issues, tune Wi-Fi, decide whether hardware is needed, connect computers and printers, and apply basic network security.
Why use it?
It prevents buying a new router or mesh system when the real cause is a device fault, interference, poor placement, or an ISP problem.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mac-it-guy-pro plugin — 8 skills, 12 commands, 4 agents, 2 hooks shipped together

Install

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.

agentmods
npx agentmods add skills/xiaolai/mac-it-guy-pro/home-network
Any agent
npx skills add xiaolai/mac-it-guy-pro --skill home-network
Clone the repo
git clone --depth 1 https://github.com/xiaolai/mac-it-guy-pro

Made for: Claude Code.

Or install mac-it-guy-pro, the plugin that ships this one along with the rest of its 8 skills, 12 commands, 4 agents, 2 hooks.

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 home-network

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/home-network.svg)](https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/home-network)
Your own site
<a href="https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/home-network"><img src="https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/home-network.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,481 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00070 $0.01481
Opus 5 $0.00035 $0.00740
Sonnet 5 $0.00014 $0.00296
Haiku 4.5 $0.00007 $0.00148

Measured 6d ago against content hash 14fe50b79caa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

home-network 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 6d 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.

skills/home-network/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Home Network — find the layer before spending money

The defining mistake in home networking is buying hardware to fix a problem that was never in the hardware. A new router does nothing for a congested channel, a badly placed access point, a saturated uplink, or an ISP fault — and the user has spent real money and still has the problem. Your job is to locate the layer first. Everything else in this skill follows from that.

Detail lives in five references, each loaded at the step that needs it: diagnostics.md (the measurements and what the numbers mean), wifi-tuning.md (the free fixes, in order), router-buying.md (what to buy, and when not to), connecting-machines.md (sharing files, screens, printers between machines), and network-security.md (the hardening baseline).

The four layers, and how to tell them apart

Layer Symptom pattern The isolating test
Device One machine is slow; everything else on the same Wi-Fi is fine Test a second device in the same spot. If it's fine, stop looking at the network
Wi-Fi Slow or dropping the further you get from the router, fine beside it; worse in the evening Compare a wired test to a Wi-Fi test at the router, then Wi-Fi at the problem spot
Router / LAN All devices affected, everywhere, including wired; internal transfers slow too Wired test at the router is also bad
ISP / uplink All devices affected, wired included; the router's own status page shows the fault; often time-of-day Wired speed test at the router is bad and the router reports a healthy LAN

The single most useful measurement is a wired test at the router. If wired is fine and Wi-Fi is bad, the ISP is innocent and the fix is free. If wired is bad too, no amount of Wi-Fi tuning will help and no new router will either. Do this before any other diagnosis; it eliminates half the possibilities in ninety seconds.

The fix ladder — never skip a rung

Work strictly in order. Each rung is cheaper than the one after it, and roughly half of real complaints are solved by the first three.

Read the full file on GitHub · 55 lines

Files

What ships with it

5 files 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.

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. 6d ago First seen · 55 lines · 70 tokens per session scan A 14fe50b79caa

Subscribe to this mod's changes

home-network is a skill published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,481 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.

Related

Other skills, from other repositories

c-bluetooth

Manage Bluetooth devices on macOS using the blucli (blu) CLI. List paired and available devices, connect to headphones/speakers/keyboards, and disconnect devices by name or MAC address.

daxaur/openpaw · 44 tokens

oura-setup

Connect an Oura Ring via OAuth2 — app registration, token exchange, and credential storage.

vellum-ai/vellum-assistant · 22 tokens

oura

Pull sleep, activity, readiness, heart rate, and other health data from a connected Oura Ring via the Oura Cloud API V2.

vellum-ai/vellum-assistant · 30 tokens

solidworks-vibecad

SolidWorks VibeCAD 参数化设计规划子技能。用于把自然语言机械设计需求转成结构化设计计划、制造规则检查、SolidWorks API 执行摘要和审查门禁;当任务涉及 text-to-CAD、vibecoding 固化、行业知识库、提示词模板、参数化建模计划、CNC 安装座/连接块/支架批量生成时使用。.

wzyn20051216/solidworks-automation-skill · 96 tokens

eide

EIDE (Embedded IDE) 工程构建工具,用于扫描 .eide/eide.yml 工程、枚举构建 配置 (ConfigName)、执行 build/rebuild/clean 并解析构建日志,返回可供 jlink/openocd 复用的产物路径。当用户提到 EIDE、Embedded IDE、eide.yml、 unifybuilder、VS Code EIDE 扩展、Cl.eide 时自动触发,也兼容 /eide 显式调用。 即使用户只是说"用 EIDE 编译一下"或"EIDE 烧录到板子上",只要上下文涉及 EIDE 嵌入式工程就应触发此 skill。.

zhinkgit/embeddedskills · 151 tokens

telephony-and-conferencing

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet…

cbrock84/headcount · 85 tokens