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 skills add GuitarAlchemist/ga --skill teachgit clone --depth 1 https://github.com/GuitarAlchemist/gaWrote 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/guitaralchemist/ga/teach)<a href="https://agentmods.dev/skills/guitaralchemist/ga/teach"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/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.
<a href="https://agentmods.dev/skills/guitaralchemist/ga/teach"><img src="https://agentmods.dev/badge/skills/guitaralchemist/ga/teach.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00084 | $0.00627 |
| Opus 5 | $0.00042 | $0.00313 |
| Sonnet 5 | $0.00017 | $0.00125 |
| Haiku 4.5 | $0.00008 | $0.00063 |
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 9d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/teach — personalized learning tutor
Adapted from aihero.dev (learn-anything-with-my-teach-skill). Turns the agent
into a tutor that builds a personalized course for whatever the user wants to learn,
adapted to their goal and proficiency, with progress tracked across sessions.
When to use
The user wants to learn something. NOT for the agent interrogating the user
about their design/plan — that's brainstorming / the IDSD intent gate.
Workflow
1. Assess before teaching (ask one concise batch)
- Motivation — why learn this, and what will they do with it?
- Current level — none / some exposure / intermediate / advanced?
- Success criteria — what does "done" look like concretely?
- Modality — worked examples, theory-first, exercises, analogies, projects?
"The more detail you give, the better your personalized lessons will be."
2. Set up the course under ./learning/<topic>/
MISSION.md— goals, current level, success criteria (from step 1).RESOURCES.md— curated materials. Ground every entry in a real, verified source — never fabricate links or citations (fetch/verify before listing).reference/glossary.md— key terms, grown as the course proceeds.lessons/— one file per lesson (Markdown by default; HTML if embedded quizzes/audio are wanted — optional, heavier).learning-records/— what was covered, what landed, what didn't.
3. Deliver lessons iteratively
- One lesson at a time, scoped to the assessed level — short and concrete, prefer worked examples over walls of theory.
- End each lesson with a brief self-check (a few questions + answers).
- Stop and wait for the learner to report how it went.
4. Adapt
- After each lesson, update
learning-records/andreference/glossary.md. - Generate the next lesson based on what landed and what was missed.
Guardrails
- Resources must be real and verified — no invented citations (ecosystem rule).
- Keep lessons tight; one concept at a time; check understanding before advancing.
- Persist progress so a later session can resume from
learning-records/.
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.
- 9d ago First seen · 52 lines · 84 tokens per session scan A 32bf5a4139d9
teach is a skill published in the GitHub repository GuitarAlchemist/ga (2 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 627 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
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
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.