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 instructions/kousen/junie-training/claude-mdgit clone --depth 1 https://github.com/kousen/junie-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/instructions/kousen/junie-training/claude-md)<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>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 | $0.01112 | $0.01112 |
| Opus 5 | $0.00556 | $0.00556 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
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.
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.
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.,
#dbeafeinstead 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
- Learning Objectives - Clear, measurable goals
- Prerequisites - Tools and knowledge required
- Parts - Logical progression from simple to complex
- Tasks - Numbered, specific actions
- Expected Outcomes - What success looks like
- Common Issues - Troubleshooting section
- Challenge Extensions - Optional advanced tasks
- 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/
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 · 149 lines · 1,112 tokens per session scan A 0ebaf110ea21
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.
Other instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
agentic-ai-engineering-course AGENTS.md
AGENTS.md instructions for towardsai/agentic-ai-engineering-course, covering the what and course map (lessons ↔ code projects).
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.