A teaching workspace for learning a skill or concept over several sessions. It keeps the learner’s goals, sources, lessons, notes, and demonstrated progress together.

It is for researching a subject, creating self-contained lessons and reference pages, and recording what the learner understands.

It gives each lesson context from earlier sessions and uses the learner’s progress to decide what to teach next.

teach — Skill for Kiro by smileynet/teach-me

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 smileynet/teach-me --skill teach

Clone the repo

git clone --depth 1 https://github.com/smileynet/teach-me

Made for: Kiro.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/smileynet/teach-me/teach/github.svg)](https://agentmods.dev/skills/smileynet/teach-me/teach)

Your own site

<a href="https://agentmods.dev/skills/smileynet/teach-me/teach"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/teach/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/smileynet/teach-me/teach"><img src="https://agentmods.dev/badge/skills/smileynet/teach-me/teach.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,050 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.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.04050
Opus 5.5	$0.00018	$0.01620
Sonnet 5.5	$0.00009	$0.00810
Haiku 4.5	$0.00005	$0.00405

Measured 16d ago against content hash 9f086796a63d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 16d 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.

.kiro/skills/teach/SKILL.md · 296 lines

How it starts

The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The user wants to learn something. This is stateful — they intend multiple sessions.

Ownership & Routing

teach is the conversational learning engine. It owns the live relationship with the learner; generate-topic owns the durable artifact assembly line. The two never both drive the same request.

teach owns:

First-contact orientation and mission elicitation (.user/learner-profile.md)
Finding the ZPD and deciding what to teach next
Interactive teaching: re-explanation of existing material, Socratic follow-ups, zoom navigation
Quick single-lesson drafts during a live session (no completeness guarantee)
The map (MAP.md) as the curriculum spine
Learner-state reads/writes (under .user/ only)

teach does NOT own (hand off, don't duplicate):

The durable authoring sequence (research → lesson → reference → SR → quiz → verify). That procedure has a single owner: the generate-topic Phase 2 pipeline. When teach needs a complete, verified, tracked artifact, it invokes generate-topic rather than re-running the steps itself.
SR-question structure — owned by generate-topic/references/sr-question-authoring.md.
Exercise design and the callout/decision hierarchy — owned by visual-teaching.md.
Retention quizzing of already-taught material — owned by quiz-me.

Hand off to generate-topic when: the learner names a topic to learn, asks for a new lesson, or asks to "complete" / fill gaps on an existing topic — anything that must produce a durable, verified artifact. Hand off to quiz-me when the learner wants to be tested on what they already learned.

Keep in teach when: the learner is mid-conversation and needs a concept re-explained ("wait, what?"), wants orientation ("show me the map", "where do I start?"), is setting up their mission/preferences, or explicitly wants a throwaway draft inside the current session.

See the routing table in #routing-table for how specific prompts resolve.

Read the full file on GitHub · 296 lines

Files

What ships with it

7 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.

16d ago Changed · +79 lines 9f086796a63d
1mo ago Changed · +2 lines 2b6ec2156c05
2mo ago Changed cbcd34b09147
2mo ago First seen · 215 lines · 46 tokens per session scan A e85e6bd7cb65

Subscribe to this mod's changes

teach is a skill published in the GitHub repository smileynet/teach-me (3 stars, last pushed 13d ago), licensed MIT. It adds 46 tokens to every session and 4,050 once invoked, about $0.0002 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.

Learning and teaching agent-skills ai learning spaced-repetition

teach next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
teachsmileynet/teach-me	Skill	3	13d ago	MIT	A	46	Kiro
ankibytesagain/ai-skills	Skill	16	6mo ago	none	A	53	Claude Code, Codex
reading-metaskillkangarooking/cangjie-skill	Skill	12k	1mo ago	MIT	A	139	Claude Code, Codex
assisted-masteryathola/claude-night-market	Skill	348	today	MIT	A	32	Claude Code
antivibemohi-devhub/antivibe	Skill	1.1k	3mo ago	MIT	A	50	Claude Code
shikhu-inquiryarjunpatel7/shikhu	Skill	16	today	MIT	A	212	Claude Code
shikhu-studyarjunpatel7/shikhu	Skill	16	today	MIT	A	40	Claude Code