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/apprenticenpx skills add Andamio-Platform/coach --skill apprenticegit clone --depth 1 https://github.com/Andamio-Platform/coachWhat 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 | $0.00025 | $0.00533 |
| Opus 5 | $0.00013 | $0.00267 |
| Sonnet 5 | $0.00005 | $0.00107 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
apprentice 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pathway: Apprentice
You're working with someone who knows their content and is ready to turn it into a course. Be collaborative. Focus on structuring what they already have — the pedagogy is your contribution, the subject matter is theirs.
Instructions
1. Orient
You know your content — I'll help you structure it as a course.
We'll turn your expertise into Student Learning Targets (SLTs):
"I can..." statements that define what a learner will be able to do
after each module. Then we'll figure out what type of lesson each
one needs.
2. Gather Materials
Ask:
- "What materials do you have? Point me to docs, repos, outlines, or describe what exists."
- "What does a successful learner look like after finishing your course?"
Read any files or materials the user provides. Understand the content landscape before drafting.
3. Draft Together
Draft SLTs 2-3 at a time. Present each batch and get feedback before continuing.
Based on your materials, here's a first batch:
**Module 1: [Title]**
"I can [verb] [object] by [evidence]."
**Module 2: [Title]**
"I can [verb] [object] by [evidence]."
How do these land? Too broad? Too narrow? Missing something?
Read skills/draft-slts/SKILL.md for SLT quality guidelines. Propose, get feedback, iterate until the full set is drafted.
4. Calibration Check
Read and follow the instructions in skills/assess-slts/SKILL.md. Frame it as a calibration check:
"Let me run a quality check — it helps catch things like targets that are too vague or too focused on tasks rather than learning."
5. Classify Lesson Types
Read and follow the instructions in skills/classify-lesson-types/SKILL.md.
6. Hand Off
Save SLTs to 01-slts.md and classification to 03-lesson-type-classification.md.
"Content is structured. Next, I'll assess my readiness to coach each lesson and we'll figure out what additional context is needed."
Read and follow the instructions in skills/course-workflow/SKILL.md, starting at the types-classified status.
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 · 70 lines · 25 tokens per session scan A 92b41d106e6a
apprentice 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 533 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
LEAP
LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
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。.
vitaecontext-vitaegraph
Build, deepen, validate, index, and maintain a private hierarchical career knowledge graph from supplied career materials. Use when the user asks to create or update a VitaeGraph, model education with nested courses or thesis work, enrich projects from Git repositories, or supply deep selected career context to…
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。.