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/nicograef/handbook/tutornpx skills add nicograef/handbook --skill tutorgit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/tutor)<a href="https://agentmods.dev/skills/nicograef/handbook/tutor"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/tutor.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 | $0.00124 | $0.01774 |
| Opus 5 | $0.00062 | $0.00887 |
| Sonnet 5 | $0.00025 | $0.00355 |
| Haiku 4.5 | $0.00012 | $0.00177 |
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 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tutor
- Named prose exception: output-style.md#named-prose-exceptions.
Workflow
1. Scope the session
- Identify the subject and its source:
- Model knowledge — established topics.
- Local files or code — the user pointed at paths.
- Web research — niche, recent, or version-sensitive topics.
- Fetch authoritative sources for those rather than trusting memory.
- Check for existing state:
ls ~/.claude/tutor/(see session-state.md). - If the topic exists, offer to continue — due review items come first.
- Ask one structured round, a single AskUserQuestion call, no more:
- Familiarity — new / some / refresher.
- Goal — deep understanding / interview prep / working knowledge.
- Length — default ~10 questions.
- Then state the rules of the game once:
- Attempt before help.
- Hints are questions.
- The answer is revealed only after two failed scaffold rounds.
2. Build the question bank
- Spawn one general-purpose subagent to digest the material and write the session files.
- Follow the brief in session-state.md; it lists the inputs to pass.
- Give the subagent
${CLAUDE_SKILL_DIR}/session-state.mdand${CLAUDE_SKILL_DIR}/question-design.mdto read first. - Reason 1 — subagent file writes never render in the main conversation, so the answer key stays off-screen.
- Reason 2 — a pre-committed key makes grading honest: the answer is fixed before the learner answers.
3. Quiz loop
For each item, interleave concepts and mix formats per question-design.md.
- Pick the next item from
bank.jsononly.- Due-queue entries first, each served by a not-yet-asked item on the same concept.
- Then unasked items.
- Never re-ask an item graded in an earlier session.
- Sole exception: it serves a due entry and no fresh same-concept item exists.
- Never open
key.jsonbefore the learner commits an answer.
- Choice items → one AskUserQuestion call.
- Question 1 is the item; options verbatim from the bank, order pre-shuffled.
- Question 2 is confidence: Sure / Likely / Guessing.
- Free-text items → ask in chat; the learner answers in their own words.
- Free-text items add the same confidence call; grade only once both are given.
- After the learner commits, look up only that item's key entry:
jq '.items["<id>"]' key.json. - Grade against the key:
What ships with it
2 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.
- yesterday Changed · -11 lines a6b60df4b40b
- 4d ago First seen · 150 lines · 124 tokens per session scan A 4f41b17dc51b
tutor is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 124 tokens to every session and 1,774 once invoked, about $0.0006 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
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
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).