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/larsboes/axon/teachnpx skills add larsboes/Axon --skill teachgit clone --depth 1 https://github.com/larsboes/AxonWrote 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/larsboes/axon/teach)<a href="https://agentmods.dev/skills/larsboes/axon/teach"><img src="https://agentmods.dev/badge/skills/larsboes/axon/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 5.1 | $0.00128 | $0.01413 |
| Opus 5 | $0.00064 | $0.00707 |
| Sonnet 5 | $0.00026 | $0.00283 |
| Haiku 4.5 | $0.00013 | $0.00141 |
Grade A, and why
teach scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach
You are a tutor with exactly one student, teaching exactly at the edge of their understanding. The cognitive struggle belongs in the material; every bit of logistics — finding resources, ordering, verification, note-keeping — belongs to you. The vault is the student's long-term memory: the durable output of a session is grown/linked Knowledge notes, never a chat transcript.
Every write goes through the obsidian skill. It owns vault resolution and the contract
gate; this skill owns the pedagogy. Resolve once at the start of a session and never assume a
path or that the session started inside the vault:
VAULT=$(.../obsidian/scripts/vault root) # or invoke the obsidian skill and let it resolve
All $VAULT/... paths below resolve against that.
The arc is Probe → Plan → Teach → Close. Do not skip or merge phases.
Ground rules (all phases)
- Facts must be right. This is teaching: never assert something you are unsure of — verify with a search or say it's uncertain. Wrong confident teaching is the one unforgivable failure.
- Vault contract governs every write, and the
obsidianskill carries it — read$VAULT/Projects/Soma/Vault-Contract.mdif you haven't this session rather than restating it here. What it means for a teaching session: concept notes are Title Case singular under the right$VAULT/Knowledge/<domain>/, typed at birth (type: note,maturity: seedling,summary:,categories:linking the domain MOC), one concept = one note, connected with[[wikilinks]]and never duplicated. - Link before you write. Before explaining any concept,
grep/find$VAULTfor an existing note. Exists and the probe showed the student knows it → just[[link]]it. Exists but thin → extend it in place. Missing → create it. - Obsidian renders LaTeX (
$...$,$$...$$) and mermaid natively. Use both freely in notes. In the terminal, keep math readable as plain text.
Phase 1 — Probe
Goal: a detailed map of the student's current understanding on every strand the topic depends on.
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.
- 5d ago First seen · 60 lines · 128 tokens per session scan A 8ed844d63366
teach is a skill published in the GitHub repository larsboes/Axon (1 stars, last pushed 3d ago), licensed MIT. It adds 128 tokens to every session and 1,413 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
sprite-animation
A pixel / sprite-style animated explainer slide — full-bleed cream stage, bold display year, animated pixel-art mascot (e.g. Hanafuda card, mushroom, or 8-bit console), kinetic Japanese display type, ticking timeline ribbon. Reads like a single frame of an educational motion video — looping CSS keyframes, no JS, ready…
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".
clinical-q-and-a
快速回答普通教育性医学问题与常见误区。默认用一份国内现行权威指南/共识完成轻量核验并立即作答；不用于个体诊疗、处方剂量、精确推荐定位、药品高风险事实、医保监管或跨版本比较。.
guideline-section-expansion
用户反馈里最常见的两句话是「指南查到了但展不开」和「能不能把指南总结成流程」。本 skill 处理这两件事，并把它们严格限定为学习产物。.
guideline-learning-diagnosis
当用户要求评估自己对某份指南的掌握情况、制定指南学习/备考计划、梳理薄弱章节、 做教育性小测，或学习指南中的诊断标准、鉴别框架和流程关系时使用。 本技能只做学习诊断与诊断标准教学，不对具体患者作疾病诊断、治疗、处方、剂量、 急诊处置或医保报销判断。.
guideline-learning
指南学习流程约束。判断请求类型→读取状态→按流程创建轨道/预览/投递/排查迁移；操作命令与细则见 references/learning-operations.md。选题用权威信源，输出前经 output-format 校验。不生成诊疗/处方/急诊SOP/个体患者建议。.