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/compilenpx skills add Andamio-Platform/coach --skill compilegit 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/compile)<a href="https://agentmods.dev/skills/andamio-platform/coach/compile"><img src="https://agentmods.dev/badge/skills/andamio-platform/coach/compile.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 | $0.00016 | $0.02699 |
| Opus 5 | $0.00008 | $0.01350 |
| Sonnet 5 | $0.00003 | $0.00540 |
| Haiku 4.5 | $0.00002 | $0.00270 |
Grade A, and why
compile 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 — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Compile Module for Import
Description
Takes a completed course module and packages it into the clean directory structure required by Andamio's module import system. Creates a compiled/ directory with outline.md, numbered lesson files, and optional introduction.md and assignment.md.
Import Format Quick Reference
module-folder/
├── outline.md # Required
├── introduction.md # Optional
├── assignment.md # Optional
├── lesson-1.md # Optional (maps to SLT 1)
├── lesson-2.md # Optional (maps to SLT 2)
└── ...
outline.md critical requirements:
| Element | Format | Notes |
|---|---|---|
| Title (YAML) | title: in frontmatter |
Module display name |
| Code | YAML code: |
Unique module identifier — can be a number (101) or slug (intro-cardano) |
| SLT heading | ## SLTs |
Must be exactly this (H2, case-insensitive) — first element after frontmatter |
| SLT list | Numbered or bulleted | Each item becomes one SLT |
Common mistakes:
- Adding
# Titleheading in outline.md → not needed, title comes from YAML frontmatter - Using
# Student Learning Targetsinstead of## SLTs→ parser ignores SLTs
Upsert behavior: If code matches an existing module, content will be updated.
Instructions
1. Select Course and Module
First, list courses in courses-in-progress/:
## Available Courses
| # | Course | Modules |
|---|--------|---------|
| 1 | andamio-for-contributors | 4 |
| 2 | andamio-for-api-developers | 4 |
Which course? (number or slug)
After course selection, list modules:
## Modules in [Course Name]
| # | Module | SLTs | Lessons Written |
|---|--------|------|-----------------|
| 1 | Your On-Chain Identity | 3 | 3/3 |
| 2 | Browsing Courses and Projects | 3 | 3/3 |
| 3 | Earning a Credential | 2 | 2/2 |
| 4 | The Contribution Loop | 4 | 1/4 |
Which module to compile? (number)
Warn if lessons are incomplete:
- If
lessons/module-N/doesn't have files for all SLTs, show warning - Ask if user wants to continue anyway (partial compile)
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 · 374 lines · 16 tokens per session scan A d06bfa363fcd
compile is a skill published in the GitHub repository Andamio-Platform/coach (6 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 2,699 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
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。.
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。.
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。.