tutoring

tutoring is a skill for Claude Code from xiaolai/mac-it-guy-pro. It costs 73 tokens per session (1,684 once invoked), scanned A, original, MIT.

Teaching guidance for an IT assistant that explains the reasons behind computer fixes. It uses either brief explanations during a task or deeper lessons based on the user's own computer measurements.

In plain words
What is it for?
Use it when explaining a Mac, network, or internet-related fix, building a learning plan, or deciding how much technical detail to provide.
Why use it?
It helps people understand what happened and how to make future decisions, instead of giving them commands they may not understand.

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/tutoring
Any agent
npx skills add xiaolai/mac-it-guy-pro --skill tutoring
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 tutoring

README.md
[![agentmods](https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/tutoring.svg)](https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/tutoring)
Your own site
<a href="https://agentmods.dev/skills/xiaolai/mac-it-guy-pro/tutoring"><img src="https://agentmods.dev/badge/skills/xiaolai/mac-it-guy-pro/tutoring.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,684 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 $0.00073 $0.01684
Opus 5 $0.00036 $0.00842
Sonnet 5 $0.00015 $0.00337
Haiku 4.5 $0.00007 $0.00168

Measured 5d ago against content hash 92041077b933, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

tutoring 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 5d 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/tutoring/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tutoring — build the model, not the procedure

Scope note

This skill governs how to teach — the modes, the grounding rule, the ten-section structure, depth scaling, and the pull-not-push discipline. It holds no domain facts of its own.

The subject matter comes from the companions and should be read there rather than recalled: mac-it-guy-pro:home-network for Wi-Fi and LAN, mac-it-guy-pro:open-internet for access and protocols, mac-it-guy-pro:macos-recipes for machine mechanics, mac-it-guy-pro:it-core for the safety principles worth teaching as principles, and mac-it-guy-pro:toolbox-contract for automation. Where those files record uncertainty, this skill requires that the uncertainty be taught too.

Assume the operational work is done for the user. They do not need to memorise commands, menus, or syntax. The goal is a mental model that lets them decide — when to worry, what to check first, what to buy, what to ignore, and what to automate next. That last one is the only part no assistant can do for them.

The asset no generic course has

The IT guy just did the thing, on this machine, with these numbers. A user who has just watched their loaded responsiveness measured at 180 RPM while a download runs is ready to understand bufferbloat in a way no textbook opening can match — they have the symptom, the measurement, and the fix in hand at the same moment.

So every lesson is grounded in the user's own evidence: values from ~/ITGuy/machine.md, events from ledger.jsonl, and what actually happened in visits.log. Quote their real numbers. Reach for a generic example only when their machine has no instance of the thing, and say that you are doing so.

Two modes, and they are not equal

Just-in-time is the one that matters for a non-technical user. Something just happened; explain why, in a paragraph, right then. No diagrams, no sections, no reading assignment. This mode is triggered by the user asking "why?", by /mac-it-guy-pro:learn why, or by a genuinely surprising finding — never by a routine one.

Read the full file on GitHub · 82 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. 5d ago First seen · 82 lines · 73 tokens per session scan A 92041077b933

Subscribe to this mod's changes

tutoring is a skill published in the GitHub repository xiaolai/mac-it-guy-pro (5 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,684 once invoked, about $0.0004 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

learning-and-development

Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.

cbrock84/headcount · 64 tokens

diagnose

Диагностика ступени мастерства (Диагност R28, FORM.089 §6.1 v5.0) прямо в VS Code / claude.ai. До 6 вопросов, 3 мин. Сохраняет cp-профиль в канонический журнал learning.cpassessments — через MCP-инструмент (browser) или напрямую в Neon (VS Code). Запускай когда: пилот говорит «пройди диагностику», «какая моя ступень»…

TserenTserenov/FMT-exocortex-template · 130 tokens

lesson-close

Закрыть текущее занятие. Финализирует lesson/YYYY-MM-DD.md (frontmatter status, метаданные времени, длительность), делает commit + push в репо DS-personal-guide. Триггерит замкнутый контур доставки — после push → GitHub webhook → bot oauthserver.py:/webhook/github/workbook → synconeusertodt → ЦД обновляется в Neon.…

TserenTserenov/FMT-exocortex-template · 129 tokens

personal-guide-render

Персональное руководство пилота собирается автоматически на сервере платформы по расписанию. Используй когда пилот просит «пересобери руководство», «обнови мой план», «собери руководство на сегодня» — скилл объясняет текущее состояние и проверяет, что руководство доехало.

TserenTserenov/FMT-exocortex-template · 71 tokens

app-it

Turn a local project or a hosted web app (including a published Claude Artifact URL) into a macOS Dock-launchable .app. Use when the user wants a clickable Dock app, local app package, icon, App It install, hosted-URL or Artifact wrapper, or repeatable desktop launcher. Defaults to native Swift WebKit, shipped…

Christian-Katzmann/app-it · 91 tokens

app-it-static

Turn a finished or buildable web app into a macOS Dock-launchable .app that serves built output instead of a dev server. Use when the user asks for app-it-static, a finished site/app launcher, a lightweight Dock app, or a dist/build/out bundle clickable from the Dock. Builds once, serves a snapshot via…

Christian-Katzmann/app-it · 89 tokens