teach

teach is a skill for Codex from owainlewis/agent-skills. It costs 65 tokens per session (1,066 once invoked), scanned A, original, MIT.

A teaching and tutorial-writing guide for explaining technical or AI topics to beginners. It helps structure lessons around how something works or how to use it.

In plain words
What is it for?
Writing course lessons, technical articles, video scripts, workshops, newsletters, and course outlines, with plain-language explanations and worked examples.
Why use it?
It reduces the risk of skipping prerequisites, unfamiliar terms, or the concrete outcome a learner needs.

Skill for Codex

Written for Codex: agents/openai.yaml present.

Good fit Writing course lessons, technical articles, video scripts, workshops, newsletters, and course outlines, with plain-language explanations and worked examples.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/owainlewis/agent-skills/teach
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.

Any agent
npx skills add owainlewis/agent-skills --skill teach
Clone the repo
git clone --depth 1 https://github.com/owainlewis/agent-skills

Made for: Codex.

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 teach

README.md
[![agentmods](https://agentmods.dev/badge/skills/owainlewis/agent-skills/teach.svg)](https://agentmods.dev/skills/owainlewis/agent-skills/teach)
Your own site
<a href="https://agentmods.dev/skills/owainlewis/agent-skills/teach"><img src="https://agentmods.dev/badge/skills/owainlewis/agent-skills/teach.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,066 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 $0.00065 $0.01066
Opus 5 $0.00032 $0.00533
Sonnet 5 $0.00013 $0.00213
Haiku 4.5 $0.00006 $0.00107

Measured 8d ago against content hash 6c8b74f63987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

teach 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 8d 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/teach/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Teach

Turn a topic into a tutorial that explains how something works or teaches the reader how to do it.

Treat every output as a tutorial. Apply the same teaching rules to course lessons, technical articles, workshops, video scripts, and newsletters.

Write for an intelligent beginner unless the user defines another audience. Do not talk down to them. Explain assumed steps and unfamiliar terms.

Frame the tutorial

  1. Infer the learner, what they already know, and why they need this.
  2. Choose one thing they should understand, decide, build, or troubleshoot after the tutorial.
  3. Narrow a broad topic until it fits the requested format and length.
  4. Decide what the learner must know first. Teach or state that prerequisite before relying on it.
  5. Exclude interesting material that does not support the outcome.

If the audience or outcome is missing and different choices would produce different tutorials, ask one question. Otherwise use a sensible assumption and proceed.

Use a concrete title

Name the question, mechanism, decision, or result. Prefer a concrete noun and verb.

  • Weak: "Understanding AI agents"
  • Better: "How an AI agent decides which tool to call"
  • Weak: "A deep dive into RAG"
  • Better: "How RAG finds context before the model answers"
  • Weak: "The future of prompting"
  • Better: "When a prompt needs an example"

Reject titles that merely name a field or promise depth.

Build the lesson

  1. Open with a problem, decision, or result the learner can recognise.
  2. Give the smallest complete explanation of what the thing is and when it is useful.
  3. Explain the mechanism in the order it happens. Name the actor, action, input, output, and limit.
  4. Define each new term in plain English before depending on it. Use one name for the same thing throughout.
  5. Walk through one realistic example completely.
  6. State the general rule after the learner has seen it work.
  7. Close the most likely wrong conclusion, edge case, or limitation.
  8. Give the learner a useful next action. For applied lessons, include a small exercise and a way to check the result.

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file 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. 8d ago First seen · 99 lines · 65 tokens per session scan A 6c8b74f63987

Subscribe to this mod's changes

teach is a skill published in the GitHub repository owainlewis/agent-skills (44 stars, last pushed 17d ago), licensed MIT. It adds 65 tokens to every session and 1,066 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 2026-08-30.