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/kousen/claude-code-training/onboardnpx skills add kousen/claude-code-training --skill onboardgit clone --depth 1 https://github.com/kousen/claude-code-trainingWrote 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/kousen/claude-code-training/onboard)<a href="https://agentmods.dev/skills/kousen/claude-code-training/onboard"><img src="https://agentmods.dev/badge/skills/kousen/claude-code-training/onboard.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 | $0.00036 | $0.00314 |
| Opus 5 | $0.00018 | $0.00157 |
| Sonnet 5 | $0.00007 | $0.00063 |
| Haiku 4.5 | $0.00004 | $0.00031 |
Grade A, and why
onboard 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
Codebase Onboarding Generator
This skill runs in a forked subagent so the broad discovery work doesn't pollute the parent conversation's context. The parent receives a concise summary; the full analysis lives in the generated files.
Procedure
-
Analyze project structure
- Top-level layout, build tooling, language and framework versions
- Key entry points, primary modules, integration points
- Notable conventions (testing, error handling, configuration, naming)
-
Write
CODEBASE.md- Architecture overview (high-level + per-module)
- Setup and run instructions
- Key patterns to know — what's idiomatic in this repo
- Gotchas — things that surprised you while exploring
- Where to start reading (5-10 file pointers)
-
Generate
PRESENTATION.mdin Slidev format- 12-20 slides covering the same ground
- Use the same conventions as
slides.mdif one exists in the repo
-
Note any TODOs you found that look like onboarding-relevant footguns.
Use a professional, practical tone. Skip marketing fluff — new team members need to do work, not be sold on the project.
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 · 34 lines · 36 tokens per session scan A 2b1e0dffb1e5
onboard is a skill published in the GitHub repository kousen/claude-code-training (335 stars, last pushed 7d ago), licensed MIT. It adds 36 tokens to every session and 314 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
article-writing
Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.
ljg-learn
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
code-documenter
Use when adding docstrings, creating API documentation, or building documentation sites. Invoke for OpenAPI/Swagger specs, JSDoc, doc portals, tutorials, user guides.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
grid-ctf-ops
Operational knowledge for the gridctf scenario including strategy playbook, lessons learned, and resource references. Use when generating, evaluating, coaching, or debugging gridctf strategies.