claude-code-training AGENTS.md

Development instructions for a Codex training course for professional software developers. The course includes slides, lab exercises, instructor guidance, sample projects, and custom commands.

In plain words
What is it for?
Use them when adding or changing lessons, labs, instructor materials, sample projects, or command integrations.
Why use it?
They keep new teaching material aligned with the course structure, supported languages, and practical learning goals.

Instructions file for CodexOpenCode

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/claude-code-training/agents-md
Clone the repo
git clone --depth 1 https://github.com/kousen/claude-code-training

Made for: Codex, OpenCode.

Per session 1,121 This file is loaded in full into every session.
When invoked 1,121 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.01121 $0.01121
Opus 5 $0.00561 $0.00561
Sonnet 5 $0.00224 $0.00224
Haiku 4.5 $0.00112 $0.00112

Measured 2d ago against content hash 96b5ed06688e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude-code-training AGENTS.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 2d 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

Copies of this mod

1 near-identical copy found in the catalogue:

AGENTS.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Training Course Development

This project contains comprehensive training materials for teaching Codex to professional software developers. The course emphasizes practical, hands-on learning with real-world scenarios.

Project Structure & Standards

Core Course Materials

  • slides.md: Main Slidev presentation with progressive learning path
  • lab_handout.md: Six progressive hands-on labs (Lab 0-6) for students
  • instructor-guide.md: Detailed instructor guidance with specific demo scenarios
  • exercises/: Collection of real-world sample projects across multiple languages

Sample Projects Architecture

  • Python Projects:
    • weather-app: Clean Flask application for feature addition exercises
    • flask-api: Intentionally poorly-written API for refactoring demonstrations
  • JavaScript/TypeScript:
    • lyrics-trainer: Interactive web app with TypeScript and comprehensive test suite
  • Java Projects:
    • certificate-service: Modern Spring Boot application with PDF generation
    • shopping-service: Legacy Grails/Groovy application for modernization exercises

Custom Commands Integration

  • custom-commands.md: Comprehensive showcase of workflow automation commands
  • commands/: Ready-to-use command files for immediate copying to ~/.Codex/commands/
  • Commands cover Java modernization, Spring scaffolding, security reviews, documentation generation, and onboarding automation

Development Workflow

Presentation Development

  1. Run development server: pnpm dev
  2. Build for production: pnpm build
  3. Export to PDF locally: pnpm export (produces slides-export.pdf, gitignored)
  4. Export to PowerPoint: pnpm export --format pptx --output slides-export.pptx

Note: For local exporting, you may need to install Playwright's Chromium first:

pnpm exec playwright install chromium

Slides PDF distribution

The published PDF is not committed to the repo. .github/workflows/build-slides-pdf.yml auto-builds on every push to main that touches slides.md (or package.json / pnpm-lock.yaml / the workflow itself) and attaches slides-export.pdf to a rolling slides-latest release. Stable URL:

Read the full file on GitHub · 110 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. 2d ago First seen · 110 lines · 1,121 tokens per session scan A 96b5ed06688e

Subscribe to this mod's changes

claude-code-training AGENTS.md is an instructions file published in the GitHub repository kousen/claude-code-training (335 stars, last pushed 5d ago), licensed MIT. It adds 1,121 tokens to every session, about $0.0056 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.

Related

Other instructions, from other repositories