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 magnus919/agent-skills --skill teach-megit clone --depth 1 https://github.com/magnus919/agent-skillsWrote 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/magnus919/agent-skills/teach-me)<a href="https://agentmods.dev/skills/magnus919/agent-skills/teach-me"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/teach-me/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/magnus919/agent-skills/teach-me"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/teach-me.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 | $0.00074 | $0.01711 |
| Opus 5.5 | $0.00030 | $0.00684 |
| Sonnet 5.5 | $0.00015 | $0.00342 |
| Haiku 4.5 | $0.00007 | $0.00171 |
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 2d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach Me
Help the learner do something they could not do independently before. Adapt to observed work, their goals, and their constraints; do not promise rapid expertise or claim this skill has demonstrated learning efficacy.
Establish the next useful goal
Use what the learner already supplied. Ask only what materially changes the next step: what they want to be able to do and how much time they have now. Offer a concrete, revisable goal if the topic is broad. Invite relevant prior experience, accessibility needs, preferred language, or format without demanding a profile. Do not assign fixed learning-style labels or infer ability from identity.
Once the subject is known, begin bounded source retrieval. After verifying its subject basis and answer criteria, use a brief task or sample of existing work to provisionally locate prerequisites; self-report alone is not mastery evidence. Source diagnostic tasks before presenting or judging them. Let learners decline diagnosis; then begin with a clearly provisional starting point. Do not make intake a barrier to help.
Research before teaching
Read subject research before the first substantive explanation or final lesson plan, and whenever the subject or version changes. Retrieve and inspect authoritative subject material for the next useful segment. Training memory can suggest search terms, never substitute for retrieved evidence. The pedagogy references bundled here do not establish subject facts.
Verify the segment's key facts, procedures, worked examples, and answer criteria against inspected sources or reproducible checks derived from those sources. Keep citations close to claims; label your own synthesis, derivations, and fictional practice scenarios. Record source date/version and material disagreement. Do not invent citations, imply unread material was checked, or turn analogies into facts.
Stop researching once the next segment and its checks are supported. If retrieval fails, try a suitable accessible alternative within the available time. If no adequate source is accessible, explain the specific limitation and request a readable excerpt, document, or source. Offer goal-setting or study organization; do not quietly teach from memory or manufacture a completed lesson plan. If only part is supported, offer that narrower scope and identify the gap.
What ships with it
8 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.
- 2d ago First seen · 142 lines · 74 tokens per session scan A 8be477617b07
teach-me is a skill published in the GitHub repository magnus919/agent-skills (133 stars, last pushed 2d ago), licensed MIT. It adds 74 tokens to every session and 1,711 once invoked, about $0.0003 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 2026-10-16.
Other skills, from other repositories
teach-me
Companion learning skill that makes a codebase legible fast. Surveys a repository, builds a cited map, runs a guided tour in dependency order, and finishes with a validated first change so the learner has actually moved the code. Use when the user runs /teach-me, or asks to learn, understand, onboard onto, get up to…
quiz-me
Companion assessment skill that grills a user on a codebase until their understanding is proven rather than assumed. Asks one question at a time, grades every answer against the real code with citations, scores 0-100 by difficulty tier, and drills the weak areas it finds. Use when the user runs /quiz-me, or asks to be…
canvas
Fetch Canvas LMS courses and assignments via API token.
playwright
Use when the task requires capturing or automating a real browser from the terminal.
ace-rsi-toolkit
Run ACE (Agentic Context Engineering, Zhang et al. 2025) on an agent the sequential offline way - a Reflector reads each training Trace, a Curator adds the lessons to a playbook of rules the agent reads before every task, and the final playbook is measured on a published Benchmark.
cocoplus-config
CocoPlus configuration SSOT — $cocoplus sync propagates cocoplus.toml into downstream artifacts; $cocoplus migrate-config converts legacy safety-config.json. Invoked via $cocoplus sync and $cocoplus migrate-config.