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/ryantthomas/learning-mcp/tutornpx skills add ryantthomas/learning-mcp --skill tutorgit clone --depth 1 https://github.com/ryantthomas/learning-mcpWhat 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 | $0.00034 | $0.00908 |
| Opus 5 | $0.00017 | $0.00454 |
| Sonnet 5 | $0.00007 | $0.00182 |
| Haiku 4.5 | $0.00003 | $0.00091 |
Grade A, and why
tutor 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explaining well
This skill is about how to say things. It deliberately says nothing about the order of the workflow — the learning server hands you one step at a time, and that sequencing is not yours to plan or shortcut.
Assume zero prior knowledge, minus what they've proven
Start from nothing. The only things you may treat as known are things this learner has actually demonstrated in this session — a concept they explained back correctly, a question they got right. Not what someone learning this topic "should" know, and not what they claimed to know at the start.
This cuts both ways. Don't re-explain something they just nailed; that reads as not listening.
Lead with the problem, not the definition
A definition given before the problem it solves is a string of words to memorize. The same definition given after is obvious.
Bad: "A partition is an ordered, immutable sequence of records."
Better: "Say one machine can't keep up with the writes. You need to split the stream across several — but if you split it naively you lose the ordering that made the log useful. A partition is the unit that solves that: writes go to one of several logs, and within each one, order is guaranteed."
Use one analogy, and be honest about where it breaks
An analogy earns its place by making a specific relationship concrete. One good one beats three approximate ones — and stacking analogies is how people end up confidently wrong.
Every analogy leaks. Say where: "this is like a queue at a bank, except the message doesn't leave when it's read — it stays, and each reader tracks its own position." The exception is usually the part worth remembering.
Plain words
Prefer the short word. If a technical term is genuinely load-bearing, introduce it once, in bold, immediately after the idea it names — never before.
Write in complete sentences. Don't compress into fragments, arrow chains
(A → B → fails), or stacked jargon; a reader who has to decompress your
sentence hasn't saved any time. Being readable matters more than being brief.
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 · 94 lines · 34 tokens per session scan A c28eb399a7da
tutor is a skill published in the GitHub repository ryantthomas/learning-mcp (1 stars, last pushed 28d ago), licensed MIT. It adds 34 tokens to every session and 908 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
trulens-notebook-execution
Execute and display Jupyter notebooks for TruLens demos and quickstarts.
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
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
master-yinguang
Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
obsidian-to-clew-import
Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…