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/owainlewis/youtube-tutorials/agents-mdgit clone --depth 1 https://github.com/owainlewis/youtube-tutorialsWhat 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 | $0.00729 | $0.00729 |
| Opus 5 | $0.00365 | $0.00365 |
| Sonnet 5 | $0.00146 | $0.00146 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
youtube-tutorials 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Instructions
This repo contains public teaching material for Owain's YouTube tutorials.
The quality bar is simple.
Each tutorial should feel like one clear lesson, not a folder of notes.
Before Editing
Read /Users/owainlewis/.codex/CONTEXT.md before writing or rewriting Owain's content.
Use tutorials/TUTORIAL-STANDARD.md as the source of truth for tutorial structure and writing style.
Use the YouTube skill when creating or rewriting a lesson.
Create A Tutorial
Use the scaffold command.
just new-tutorial my-topic "My Tutorial Title"
This creates:
tutorials/my-topic/
README.md
LESSON.md
code/
resources/
resources/prompts.md
resources/slides/
Do not hand-create a new tutorial folder unless the Justfile is unavailable.
After scaffolding, edit LESSON.md first.
The lesson is the source of truth.
Tutorial Standards
Every tutorial should have:
README.mdas the short entry point.LESSON.mdas the one main teaching document.code/for runnable code and setup files.resources/for prompts, references, checklists, images, slides, and supporting files.resources/prompts.mdfor reusable prompts.resources/slides/for polished slide decks or visual explainers.
Keep the tutorial root clean.
Move extra Markdown files into resources/ unless they are README.md or LESSON.md.
Tutorial-specific AGENTS.md and CLAUDE.md examples belong in resources/, not at the tutorial root.
If a reference file becomes required reading, fold the teaching back into LESSON.md.
Writing Standards
Write like Owain talks to a capable developer.
Use plain language.
Explain basics first, nuance second.
Use concrete commands, files, examples, and tradeoffs.
Use diagrams when they make the idea easier to understand.
Prefer Mermaid diagrams in LESSON.md.
Use slides when the idea needs visual polish for recording.
Avoid hype, guru phrasing, clever analogies, and em dashes.
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.
- yesterday First seen · 123 lines · 729 tokens per session scan A e0e372f28862
youtube-tutorials AGENTS.md is an instructions file published in the GitHub repository owainlewis/youtube-tutorials (365 stars, last pushed 10d ago), licensed MIT. It adds 729 tokens to every session, about $0.0036 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 instructions, from other repositories
erpaval CLAUDE.md
Instructions for theagenticguy/erpaval, covering erpaval-plugin, repo structure, version management, tools and hooks.
ai-engineering-from-scratch AGENTS.md
Instructions for rohitg00/ai-engineering-from-scratch, covering agents.md, philosophy, repo layout, hard rules and dependencies.
ai-engineering-from-scratch-zh AGENTS.md
Instructions for fancyboi999/ai-engineering-from-scratch-zh, covering agents.md, 定位, 仓库结构, 强制规则 and 依赖约束.
opencode-primer AGENTS.md
AGENTS.md instructions for wesammustafa/opencode-primer, covering agents.md, what this repo is, repo layout, editing rules and always.
alignfirst AGENTS.md
Instructions for paleo/alignfirst, covering repository guidelines, tooling, packages, docmap - seek documentation and workspaces.
claude-code-hooks CLAUDE.md
Instructions for shanraisshan/claude-code-hooks, covering claude code hooks, project structure, critical: hook count consistency, agent hooks and workflows.