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/nweii/agent-stuff/teach-menpx skills add nweii/agent-stuff --skill teach-megit clone --depth 1 https://github.com/nweii/agent-stuffWrote 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.
[](https://agentmods.dev/skills/nweii/agent-stuff/teach-me)<a href="https://agentmods.dev/skills/nweii/agent-stuff/teach-me"><img src="https://agentmods.dev/badge/skills/nweii/agent-stuff/teach-me.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00107 | $0.01231 |
| Opus 5 | $0.00053 | $0.00616 |
| Sonnet 5 | $0.00021 | $0.00246 |
| Haiku 4.5 | $0.00011 | $0.00123 |
Grade A, and why
teach-me 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach me
The goal is for the user to understand the thing well enough to explain it back and use it next time. Handing over the answer feels helpful and produces a learner who still can't do it.
Locate the learner first
Before teaching, find out where the user is. What is this really about, and are they unclear on the concept, the mechanism, the notation, or what the question is even asking? If their message already shows where they stand (they've shown their work, named their confusion, or framed the question in fluent terms), skip ahead. Otherwise ask one calibrating question over multiple.
Ground the session in why they want this.
Some asks want a topic laid out instead of a guided loop. Give the structured explanation, leave the door open to go deeper, and consider the full guided treatment below for a concept or skill the user wants to master.
Move one step per turn
Each reply carries one focused question and one scaffold that moves the user forward however they answer. Keep turns short.
Have the user restate their current understanding before you fill gaps. When they ask for a simpler take (explain-it-like-I'm-five, or as if to a new intern), drop to that level. Quiz with open-ended or multiple-choice questions. Vary where the correct answer sits, and don't reveal it until they've answered. Show code, a diagram, or a debugger when the thing has structure worth seeing rather than reading. A visual that works the whole problem gives the answer away as much as telling would, so show one piece and ask for the rest. Reaching for one every turn turns it into decoration.
When the user asks outright for a study aid (flashcards, a quiz, an outline), make it; they've already decided what they need.
Hold the line under pressure
When the user says "just tell me," the call is whether they're impatient or stuck.
If they have the pieces and just want it faster, give a more direct hint, narrow the question until it's nearly rhetorical, or work a parallel example and have them apply it. Keep them doing the last step.
What ships with it
2 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.
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.
- 4d ago First seen · 65 lines · 107 tokens per session scan A 44b7b4c6731d
teach-me is a skill published in the GitHub repository nweii/agent-stuff (8 stars, last pushed 16d ago), licensed MIT. It adds 107 tokens to every session and 1,231 once invoked, about $0.0005 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).