junie-training CLAUDE.md

junie-training CLAUDE.md is an instructions file for coding agents from kousen/junie-training. It costs 1,112 tokens per session, scanned A, a copy of junie-training AGENTS.md, MIT.

Repository instructions for a training project about JetBrains’ AI coding assistant. They cover project context and guidelines for making Slidev presentations, including keeping each slide focused.

In plain words
What is it for?
Use them when creating or editing training slides, especially Slidev files. They also provide project context for examples about JetBrains’ AI coding assistant.
Why use it?
They help keep training materials readable and consistent across different slides and IDE examples. The rules limit dense text, long code samples, and hard-to-read color combinations.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/kousen/junie-training/claude-md
Clone the repo
git clone --depth 1 https://github.com/kousen/junie-training

Wrote 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.

agentmods badge for junie-training CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kousen/junie-training/claude-md.svg)](https://agentmods.dev/instructions/kousen/junie-training/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/kousen/junie-training/claude-md"><img src="https://agentmods.dev/badge/instructions/kousen/junie-training/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,112 This file is loaded in full into every session.
When invoked 1,112 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin 89% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01112 $0.01112
Opus 5 $0.00556 $0.00556
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 5d ago against content hash 0ebaf110ea21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

junie-training CLAUDE.md 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.

Origin

This is a copy

89% identical to junie-training AGENTS.md — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Guidelines for Claude

Project Context

This is a comprehensive Junie training repository for teaching JetBrains' AI coding assistant across multiple IDEs. The training materials were developed with Claude's assistance and demonstrate best practices for AI-assisted development.

Slide Presentation Best Practices

When creating or editing slides (especially in Slidev format):

One Idea Per Slide

  • Each slide should contain ONE major concept
  • Avoid the "bullet-riddled corpse" anti-pattern
  • Better to have many simple slides than few dense ones
  • 60+ focused slides work better than 30 cramped ones

Content Guidelines

  • Maximum 5-6 bullet points per slide
  • Use progressive disclosure across multiple slides
  • Keep code examples short and focused (5-10 lines max)
  • Leave visual breathing room

Visual Design for Dark Mode

  • Use high contrast colors for text on colored backgrounds
  • Test all color combinations for readability
  • Prefer lighter text shades (e.g., #dbeafe instead of white on blue)
  • Add borders to colored boxes for definition
  • Keep Mermaid diagrams simple to avoid parsing errors

Example Structure

---
## Single Concept Title

Key point or statement

Supporting detail if needed
---

Lab Instructions Format

When creating lab instructions:

Structure

  1. Learning Objectives - Clear, measurable goals
  2. Prerequisites - Tools and knowledge required
  3. Parts - Logical progression from simple to complex
  4. Tasks - Numbered, specific actions
  5. Expected Outcomes - What success looks like
  6. Common Issues - Troubleshooting section
  7. Challenge Extensions - Optional advanced tasks
  8. Reflection Questions - Reinforce learning

Writing Style

  • Use clear, imperative language for tasks
  • Provide example code and expected output
  • Include timing estimates for each section
  • Add hints for common stumbling blocks

Project-Specific Patterns

File Organization

/
├── slides.md           # Main presentation (source of truth)
├── slides.pdf         # Exported for distribution
├── labs/
│   ├── labA-java-rest/
│   │   ├── README.md
│   │   ├── .junie/AGENTS.md
│   │   └── [starter code]
│   └── [other labs...]
├── .junie/
│   └── skills/
├── resources/
│   ├── cheat-sheets/
│   ├── prompts/
│   └── quick-reference.md
└── demo-playwright/

Read the full file on GitHub · 149 lines

Changes

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.

  1. 5d ago First seen · 149 lines · 1,112 tokens per session scan A 0ebaf110ea21

Subscribe to this mod's changes

junie-training CLAUDE.md is an instructions file published in the GitHub repository kousen/junie-training (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,112 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to junie-training AGENTS.md, differing in 32 lines, and is treated as a copy.