network

network is a command for Claude Code from xiaolai/mac-it-guy-pro. It costs 28 tokens per session (1,846 once invoked), scanned A, original, MIT.

A Mac command for diagnosing and fixing home-network problems, including slow Wi-Fi and connections between devices. A home network is the router and devices sharing one internet connection.

In plain words
What is it for?
Inspecting a network, finding connected devices, improving Wi-Fi, connecting machines, and reviewing basic network security.
Why use it?
It measures the network before suggesting changes and checks that you control the network before scanning it.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit Inspecting a network, finding connected devices, improving Wi-Fi, connecting machines, and reviewing basic network security.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add xiaolai/mac-it-guy-pro
Claude Code
/plugin install 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 network

README.md
[![agentmods](https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/network/github.svg)](https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/network)
Your own site
<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/network"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/network/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 network

Your own site · 80×15
<a href="https://agentmods.dev/commands/xiaolai/mac-it-guy-pro/network"><img src="https://agentmods.dev/badge/commands/xiaolai/mac-it-guy-pro/network.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,846 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.
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 $0.00028 $0.01846
Opus 5.5 $0.00011 $0.00738
Sonnet 5.5 $0.00006 $0.00369
Haiku 4.5 $0.00003 $0.00185

Measured 1mo ago against content hash e769da1ebfec, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

commands/network.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Network — measure first, spend last

Read ${CLAUDE_PLUGIN_ROOT}/skills/home-network/SKILL.md first — the layer model, the fix ladder, and the boundaries are binding. Read ${CLAUDE_PLUGIN_ROOT}/skills/it-core/SKILL.md for the safety contract and ${CLAUDE_PLUGIN_ROOT}/skills/machine-profile/SKILL.md before writing anything to the profile. Read ~/ITGuy/machine.md if it exists. If uname is not Darwin, say this version supports Mac only and stop.

Confirm this is the user's own network before scanning anything — ask explicitly with AskUserQuestion, do not infer it from context. The question is whether this is their home network or one they administer. If it is a coffee shop, an office, a campus, or shared accommodation they do not control, do the parts that only inspect this Mac and decline the rest — see the boundaries in the skill. Ask once per run, before the first discovery command, and never in place of it.

Network data is sensitive. Device names, addresses, MAC addresses, and the SSID together describe a household. Follow the privacy rule in the skill: keep them out of ~/ITGuy/machine.md, redact them from anything saved or shared, and warn the user before they paste a network report into a support chat or a forum.

Resolve the subcommand from $ARGUMENTS; empty means check. If $ARGUMENTS is non-empty but matches none of the six, treat it as a problem description — name the six subcommands, say which one you think fits, and confirm before running it.

check — the health report

  1. Run the measurements in ${CLAUDE_PLUGIN_ROOT}/skills/home-network/references/diagnostics.md: Wi-Fi signal and SNR here, networkQuality idle, ping to the router and beyond, DNS in use, device count.
  2. Report in the it-core report format, one row per area (Wi-Fi signal · Speed · Responsiveness · Router link · Internet link · Devices), each with its own 🟢/🟡/🔴 so a single bad area is visible rather than averaged away.
  3. Lead the top line with the layer, not the number: "Your Wi-Fi is the bottleneck, not your internet plan" is the sentence the user needs.
  4. End with exactly one recommended next step: read the profile's network notes and Watch List first to see which rungs have already been applied, then recommend the lowest rung of the fix ladder not yet tried. Without that check, a second visit repeats the advice of the first.

Read the full file on GitHub · 68 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. 1mo ago First seen · 68 lines · 28 tokens per session scan A e769da1ebfec

Subscribe to this mod's changes

network is a command published in the GitHub repository xiaolai/mac-it-guy-pro (6 stars, last pushed 16d ago), licensed MIT. It adds 28 tokens to every session and 1,846 once invoked, about $0.0001 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.