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/aethrox/doctrine/teachnpx skills add aethrox/doctrine --skill teachgit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/teach)<a href="https://agentmods.dev/skills/aethrox/doctrine/teach"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/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 | $0.00057 | $0.01004 |
| Opus 5 | $0.00028 | $0.00502 |
| Sonnet 5 | $0.00011 | $0.00201 |
| Haiku 4.5 | $0.00006 | $0.00100 |
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 4d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach
Telling someone an answer and teaching them a skill are different jobs, and mixing them up produces an illusion of understanding that evaporates the moment the topic changes shape. This skill's defining constraint combines two grounded findings: Bloom's Taxonomy (what's being taught has a cognitive level (Remember, Understand, Apply, Analyze, Evaluate, Create), and the level determines the method, not just the content) and the worked-example effect from cognitive load theory. A novice learns faster from a fully worked solution than from solving the same problem cold, but that advantage fades and reverses as competence grows (the expertise-reversal effect), so support has to be removed as skill builds, not held constant.
Phase 1: Place the target level and the learner's current level
Before teaching anything, decide which Bloom level the goal actually requires; "understand why X happens" is a different job from "be able to do X unaided" or "be able to judge whether X is the right call here." Teaching a Create-level goal with only Remember-level content (definitions and facts, no practice) leaves the learner unable to do the thing; teaching a Remember-level goal with elaborate open-ended practice wastes effort neither the goal nor the learner's current level needs.
Gauge where the learner already stands (what they can already do without help) so the first example lands in their zone of proximal development: challenging enough to be worth teaching, not so far ahead it's unintelligible.
Phase 2: Start from a fully worked example
For anything above pure recall, open with a complete, worked-through instance of the skill, not a partially-blanked problem, not "try it and I'll correct you." Narrate the reasoning at each step, not just the mechanical moves, since the reasoning is what transfers to the next problem and the mechanical steps alone don't. A novice's working memory is the bottleneck here; a worked example spends that budget on understanding the solution, where an unaided attempt spends it on the search for one. Write the explanation without em dashes, using a comma, colon, period, or a reworded sentence instead.
What ships with it
1 file 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.
- 4d ago First seen · 47 lines · 57 tokens per session scan A dd81c6ee84aa
teach is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 23d ago), licensed MIT. It adds 57 tokens to every session and 1,004 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
openspec-onboard
Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
ce-explain
Create a durable visual teaching artifact for something worth learning. Use when the user wants to be taught, wants a deep explainer, wants to understand a substantial change, or wants a work recap built for retention. Not for ordinary Q&A, operational diagnosis, or a concise trade-off that belongs in chat. For…
create-skill
Create instruction-only skills that package knowledge and workflow guides for AI clients.
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
learn-from-math-agent-trajectories
Review completed or paused mathematical agent transcripts, visible reasoning, code, searches, tool calls, corrections, and final claims to extract evidence-backed lessons for Jacobian operations, discovery, contracts, skills, evaluations, and documentation. Use for mathematical workflow retrospectives and "what should…