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/melodic-software/claude-code-plugins/teachnpx skills add melodic-software/claude-code-plugins --skill teachgit clone --depth 1 https://github.com/melodic-software/claude-code-pluginsWrote 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/melodic-software/claude-code-plugins/teach)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/teach"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/teach.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 | $0.00079 | $0.06190 |
| Opus 5 | $0.00039 | $0.03095 |
| Sonnet 5 | $0.00016 | $0.01238 |
| Haiku 4.5 | $0.00008 | $0.00619 |
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 yesterday.
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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Teach a user interactively across multiple sessions. Not by lecturing, but by coaching through the Knowledge-Skills-Wisdom progression grounded in the user's real goals. Maintains persistent learning state so each session builds on prior understanding.
Use when: user asks to learn across sessions (teach me, study session, help me learn, onboard me to). Skip when: one-off inline question (answer directly); task-context codebase investigation (use the project's own code-exploration tooling); extracting book knowledge to a reference file (/knowledge:book-distill when installed).
Two modes share pedagogy but differ in source material:
topic. General subject learning. Resources come from external high-trust sources (books, courses, docs, communities).codebase. Repo-grounded learning. Resources come from the consuming repo's own code, docs, ADRs, conventions, discovered at teach-time (see "Codebase mode").
Workspace layout (where persistent learning state lives): see "Workspace layout" below. The single source of truth every action resolves paths against. Informed by ZPD/K-S-W pedagogy research.
Workspace layout
Learning state is the user's own study material. User documents, not machine internals. Every workspace lives at <workspace-root>/<project-slug>/<mode>/<topic>/, where <workspace-root> resolves per "Workspace root resolution" below (topic mode defaults to the OS Documents folder's Claude Learning/ home where one is eligible; codebase mode defaults to ${CLAUDE_PLUGIN_DATA}); no root ever pollutes the consuming repo unless the project itself declares one:
<workspace-root>/<project-slug>/<mode>/<topic>/
├── MISSION.md WHY the user is learning this — goal, success criteria, constraints (workspace-global)
├── GLOSSARY.md durable terminology SSOT — add only when the user demonstrates understanding (global)
├── RESOURCES.md curated high-trust sources (knowledge + wisdom communities) (global)
├── NOTES.md teaching preferences + working notes — how the user wants to be taught (global)
├── assets/ shared lesson components — lesson.css + answer-shuffling quiz.js, spliced into HTML lessons (context/lessons.md "Assets library")
├── learning-records/ cross-cutting ZPD log — ADR-style insight records (append-only)
│ ├── 0001-<slug>.md
│ └── 0002-<slug>.md
└── concepts/ per-concept slices
└── <concept-slug>/ ONE tightly-scoped thing — things that change together, together
├── lesson.html the teaching unit — pedagogically ephemeral (rarely revisited, regenerable), NOT the topic-docs ephemeral tier; `lesson.md` where the host can't render HTML (ONE lesson file per concept — format decision + replacement rules: context/lessons.md)
├── reference.md durable compressed cheat-sheet (revisited; the rot-relevant artifact)
└── exercise.md colocated practice (optional)
What ships with it
10 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.
- context/assessment.md 3.3 KB
- context/exercises.md 3.3 KB
- context/glossary.md 2.4 KB
- context/lessons.md 13 KB
- context/mission.md 2.2 KB
- context/pedagogy.md 7.2 KB
- context/resources.md 2.6 KB
- evals/evals.json 13 KB
- scripts/list-workspaces.sh 7.0 KB runs code
- scripts/list-workspaces.test.sh 8.3 KB runs code
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.
- yesterday First seen · 211 lines · 79 tokens per session scan A db0afb1cd3bf
teach is a skill published in the GitHub repository melodic-software/claude-code-plugins (14 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 6,190 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 2026-09-03.
Other skills, from other repositories
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
count-combinations
For probability and counting: permutations, combinations, sample spaces, Monte Carlo simulation, brute-force enumeration, card/dice problems.
complete
複数の媒体(レポート・コード等)にまたがる大学の課題を,出題文・採点基準に照らして過不足なく仕上げる.要求を媒体へ割り当て,assignment プラグインの対応スキルへ委譲し,媒体間の継ぎ目を走査して一つの提出物として確定する.「この課題をやって」「課題を完璧に仕上げて」など,課題まるごとを任されたときに使う(単一媒体なら /assignment:report ・ /assignment:program を直接使う)..
report
課題のレポート・小論文部分を,出題文・採点基準の要求を過不足なく満たす形で執筆する.「レポートを書いて」「この設問に答えて」など,課題文書の執筆を求められたときに使う(既存文書の推敲だけなら /refine:docs を使う)..
career-junior-onboarding
신입·주니어가 첫 90일을 스스로 설계하도록 돕는 온보딩 코칭 스킬입니다. "신입인데 뭘 해야 할지 모르겠어", "첫 출근 준비", "질문하는 법 알려줘", "사수가 없어", "일 빨리 배우고 싶어"처럼 요청할 때 사용하세요. 입사 전 준비 → 첫 90일 정보 비대칭 해소 → 질문 3요소 프레임 → 보고 기술 → 사수 없이 성장하기 → 생산성 로드맵까지 단계별 워크플로우와 90일 온보딩 플랜, 질문 템플릿, 셀프 온보딩 체크리스트를 제공합니다.
phpunit-migration-test-reviewing
Internal sub-skill. Do not auto-activate. Use only when explicitly invoked by name by another skill or agent.