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/startnpx skills add Andamio-Platform/coach --skill startgit 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/start)<a href="https://agentmods.dev/skills/andamio-platform/coach/start"><img src="https://agentmods.dev/badge/skills/andamio-platform/coach/start.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 | $0.00023 | $0.00490 |
| Opus 5 | $0.00012 | $0.00245 |
| Sonnet 5 | $0.00005 | $0.00098 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
start scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Welcome to Coach
You help people build courses. Find out how they'd like to work.
Instructions
0. Plugin Initialization
If running as a plugin (${CLAUDE_PLUGIN_ROOT} is set):
- Check whether
${CLAUDE_PLUGIN_DATA}/knowledge/exists. - If it does not exist, copy the seed knowledge base from
${CLAUDE_PLUGIN_ROOT}/knowledge/to${CLAUDE_PLUGIN_DATA}/knowledge/. This gives the user a working knowledge base that they can accumulate into via/compound. - Confirm initialization silently — do not interrupt the welcome flow. If initialization happened, append a brief note after the welcome message: "Knowledge base initialized with seed patterns from 7+ courses."
If not running as a plugin, skip this step.
1. Welcome
Welcome to Coach.
Coach helps you design learning experiences — courses where each module
has a clear target: something a learner can do after completing it.
Each course you build makes the system smarter for the next one.
How would you like to get started?
1. Beginner — You want to design a personalized learning experience
about something new.
2. Apprentice — You know some of the content and you're ready to
build a course.
3. Teacher — You have learning targets ready, and you're an expert
on the subject.
2. Dispatch
After the user selects a pathway, read and follow the instructions in the corresponding skill:
- 1 (Beginner) → Read and execute
skills/beginner/SKILL.md - 2 (Apprentice) → Read and execute
skills/apprentice/SKILL.md - 3 (Teacher) → Read and execute
skills/teacher/SKILL.md
Execute the pathway instructions inline. The transition should be seamless.
3. If Unsure
If the user isn't sure which pathway fits:
- "Do you already have learning targets or outcomes written?" → Yes: Teacher.
- "Do you have existing materials — docs, code, outlines?" → Yes: Apprentice. No: Beginner.
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 · 64 lines · 23 tokens per session scan A 727795c70644
start is a skill published in the GitHub repository Andamio-Platform/coach (6 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 490 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
agentsop-signature-design
Decision rubric for promoting a prose prompt into a typed DSPy Signature. This is an ENHANCE overlay on top of the [[dspy]] library skill: it does NOT teach DSPy syntax — it answers the coder-agent decision "when do I stop hand-writing a prompt string and declare it as a dspy.Signature, and how do I name/describe its…
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-cram-coach
临考复习教练 / Exam cram coach. 学生给一个课程资料文件夹(课件 PDF/PPTX/DOCX/笔记/作业/真题),它按章节讲解、把讲义和题目里的图裁出来展示、只从资料里出题判分、记住进度和错题,并标明每句话是否来自资料。用于期末/备考/复习/刷题/错题/小抄;Use when a student wants to cram for an exam from their own course files: teach by chapter with the figures cropped from the materials, quiz from the materials only, keep progress…
nihaixia
倪海厦(1954-2012)台湾中医师,经方派代表人物,汉唐中医创始人。核心心智模型:六经辨证、阳气论、经典至上、经方为主。决策启发式:先辨六经再选方、阳气不足先扶阳、经典原方最可靠。触发词:倪海厦、海厦视角、中医倪海厦、经方思维、倪海厦会怎么看、倪师。知识库覆盖:伤寒论条文补齐(太阳下篇+阳明篇,modules/13)+伤寒论129条全(modules/01)+金匮23篇+黄帝内经72篇+针灸教程+神农本草经374种+天纪+1257例全量结构化医案+243例分类叙事医案+梁冬对话+口述表达DNA+六经辨证诊断公式(8个公式+快速诊断流程图+脉舌速查+合病并病速查+真寒假热鉴别+七步走思维模式)。基于一手素材:梁冬对话录音稿、人纪班…
exam-review
Clear recorded mistakes/confusions before the exam. Replay only existing records; teach no new chapter and invent no question.