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/andamio-platform/coach/classify-lesson-typesnpx skills add Andamio-Platform/coach --skill classify-lesson-typesgit clone --depth 1 https://github.com/Andamio-Platform/coachWrote 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/andamio-platform/coach/classify-lesson-types)<a href="https://agentmods.dev/skills/andamio-platform/coach/classify-lesson-types"><img src="https://agentmods.dev/badge/skills/andamio-platform/coach/classify-lesson-types.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 | $0.00025 | $0.01516 |
| Opus 5 | $0.00013 | $0.00758 |
| Sonnet 5 | $0.00005 | $0.00303 |
| Haiku 4.5 | $0.00003 | $0.00152 |
Grade A, and why
classify-lesson-types 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Classify Lesson Types
Description
Walks through each SLT in a set and interviews the user to determine the appropriate lesson type. Builds a classification document and refines heuristics about when each lesson type applies.
Lesson Types
| # | Type | Inputs | Best For |
|---|---|---|---|
| 1 | Product Demo | SLT + screenshots | UI walkthroughs, platform features, "click here then here" sequences |
| 2 | Developer Documentation | SLT + code + docs link | API usage, library integration, code-heavy technical skills |
| 3 | How To Guide | SLT + optional materials | Step-by-step procedures, workflows, processes without heavy UI or code |
| 4 | Organization Onboarding | SLT + org context | Org-specific setup, policies, team conventions |
| 5 | Exploration | SLT + framing questions | Big ideas, thought leadership, worldview challenges, conceptual territory |
Instructions
Path Resolution
Resolve file paths based on your execution context:
- Plugin context (
${CLAUDE_PLUGIN_ROOT}is set): Read knowledge from${CLAUDE_PLUGIN_DATA}/knowledge/(user data), falling back to${CLAUDE_PLUGIN_ROOT}/knowledge/(seed data). Read research from${CLAUDE_PLUGIN_ROOT}/knowledge/research/. - Clone/symlink context (default): Read knowledge from
knowledge/relative to the project root (research is atknowledge/research/).
Pre-Execution Knowledge Check
Before classifying SLTs, read the knowledge base for heuristics that should improve your initial guesses. If any knowledge file does not exist, skip it and proceed without prior heuristics — rely on the lesson type definitions below.
-
Read
knowledge/lesson-types/heuristics.yaml- Use verb_patterns to inform initial classification
- Use subject_patterns to refine based on topic
- Note confidence levels — high confidence patterns can be stated more firmly
-
Read
knowledge/lesson-types/edge-cases.yaml- Check if this SLT matches a known ambiguous pattern
- If so, skip to the discriminating_question that resolved it before
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 · 173 lines · 25 tokens per session scan A dd3a09d2e7d5
classify-lesson-types is a skill published in the GitHub repository Andamio-Platform/coach (6 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 1,516 once invoked, about $0.0001 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
paper-explainer
科研论文解读：解析 arXiv/PDF 的公式与图表，提炼问题、贡献、方法、关键图和结论，再产出 B站/视频号解读视频或知乎/公众号图文。 当用户说“论文解读、讲论文、论文转视频/图文、科研科普、arXiv、学术视频”时使用。 本 SKILL 从论文做内容；video-to-article 从视频做图文，doc-convert 只转换文档格式。.
bq-skill
行为面试 skill。帮求职者挖掘真实经历、用 STAR/CAR 结构化、映射能力标签、构建可复用的中英双语故事库（Story Bank）；并能接入 JD + 简历，针对具体岗位生成 Top 20 BQ 选题 + 基于真实经历的 STAR 准备模板（HTML 报告）。不是背答案，而是建立可复用的职业叙事体系，让任何行为面试题都能自然作答。关键词：behavioral question, BQ, 行为面试, STAR, 故事库, Amazon LP, 职业故事, tell me about a time, 面试准备, JD 面试题预测, top 20 题。.
exam-study-guide
将已经讲完但尚未完成阶段门禁的一个章节整理成强类型教材清单，并在视觉模式下编译为公式可读、图片可见、知识点与全部对应例题逐项精讲的自包含 HTML/PDF。结构化工作区准备阶段完成证据、用户说 Markdown 公式仍是 raw LaTeX、图片缺失、要含课件/作业/Quiz/模拟考试题及答案的零基础讲义，或要求打印版时使用。.
exam-ingest
从学生上传的课件/大纲/老师勾的重点/真题，一键初始化并验证备考工作区：解析 PDF、DOCX、PPTX、 XLSX、常见独立图片与 txt/md，建立分章节 LLM Wiki、标准题库、结构化接管队列与进度状态；仅在 Python 确实无法运行时 明确降级为手动写盘。当工作区尚未建立、资料发生变化、或建库 readiness 被阻断时使用。.
exam-cram
临考前的极速备考总教练。把课件、大纲、重点与真题建成分章 wiki 和标准题库，再组织惰性授课、 题库判分、错题与疑难复盘及可选考前小抄，并持久化进度。用于期末、备考、突击、刷题、划重点、 错题与考前复习；不用于长期规划或与考试无关的写作/编程。.
exam-tutor
按章节惰性加载授课：每次只读当前阶段的一个 wiki 章节，用生活隐喻讲概念、解剖公式；重点题固定走 题面图→问题→读图量→公式→演算→答案详解→溯源七步，画图题先运行算法。用于讲懂当前章或老师勾出的重点题。.