AI Engineering from Scratch is a free, open-source curriculum that teaches people to build AI systems through lessons and reusable artifacts such as prompts, skills, agents, and MCP servers. It is for learners who want practical foundations or want to create AI applications, and the catalogue skills support parts of that curriculum.
Borrowing it
Nothing to install: this file belongs to rohitg00/ai-engineering-from-scratch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/.claude/skills/course-style/SKILL.mdgit clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratchWrote 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/rohitg00/ai-engineering-from-scratch/course-style)<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/course-style"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/course-style/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/course-style"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/course-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 5.1 | $0.00097 | $0.01555 |
| Opus 5.5 | $0.00039 | $0.00622 |
| Sonnet 5.5 | $0.00019 | $0.00311 |
| Haiku 4.5 | $0.00010 | $0.00155 |
Grade A, and why
course-style 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 24d 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.
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.
Course style
This skill is the reference layer for the AI Engineering from Scratch look and voice. Other craft skills point here for exact values: blueprint-figure, motion-figure, isometric-explainer, and write-manual. Use it with Claude, Cursor, Codex, OpenClaw, Hermes, or any agent that reads SKILL.md. It holds no drawing method of its own. It tells you which colour, font, label, spacing, and word to use, and how to check each one.
When to use
- You write or review a page, a card, a figure, or a manual for the course.
- You need a token value for light or dark mode.
- You need the label format for a figure, a sub-figure, or a widget.
- You need to check prose against the plain technical English rules.
- You add motion and need the timing, the easing, and the reduced motion behaviour.
When not to use
- You draw a static SVG figure. Use blueprint-figure, which cites this skill.
- You build an animated or slider figure. Use motion-figure.
- You build an isometric machine explainer. Use isometric-explainer.
- You write a full manual. Use write-manual for the structure and the audit.
- The page belongs to a different product with its own brand.
Method
- Set the theme. Put the light tokens on
:rootand the dark tokens on[data-theme="dark"]. Copy them fromreferences/tokens.md. - Pick the token set. Pages use the site tokens. Manual figures use the
--m-tokens. - Load the three fonts with the exact link in
references/typography.md. Use the stacks as given. - Give each figure a label in the format from
references/labels-and-layout.md. - Build cards and figure frames with the measurements in
references/labels-and-layout.md. - Add motion only with the motion tokens. Add the reduced motion block from
references/accessibility.md. - Write the prose. Then check every line against
references/plain-english.md. - Run the checklist below. Fix each failure before you finish.
Rules
Colour
- Use one accent per page:
--blueprint(#3553fflight,#6b8effdark). Status tokens and manual figure hues are the only other colours. - Write every colour as a CSS variable. A hex value is allowed only as the default inside
var(). - Define every token in both themes. A token without a dark value is a defect.
- Put body text in
--inkor--ink-softonly. - Do not use
--ink-muteor--warnfor body text. Their contrast on the paper is below 4.5:1. - Keep the four fixed figure hues: rose for failure, grey for outside, amber for lifecycle, teal for durable state.
- Use no gradients except the paper dot grid and the dashed rule. Use no rounded corners on cards or frames.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago First seen · 110 lines · 97 tokens per session scan A 48c39f306a12
course-style is a skill published in the GitHub repository rohitg00/ai-engineering-from-scratch (77,007 stars, last pushed yesterday), licensed MIT. It adds 97 tokens to every session and 1,555 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-14.
course-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| course-stylerohitg00/ai-engineering-from-scratch | Skill | 77k | yesterday | MIT | A | 97 | Claude Code |
| design-systemfurkangonel/cowrangler | Skill | 1 | 1mo ago | MIT | A | 16 | Claude Code, Codex |
| design-mdmateaix/mateclaw | Skill | 1.2k | yesterday | Apache-2.0 | A | 14 | Claude Code, Codex |
| penpot-mcpar27111994/penpot-mcp | Skill | 30 | 4d ago | MIT | A | 175 | Claude Code, Codex |
| ui-designwpank/ai | Skill | 12 | 8mo ago | none | A | 51 | Claude Code, Codex |
| ui-ux-pro-maxwpank/ai | Skill | 12 | 8mo ago | none | A | 54 | Claude Code, Codex |
| component-family-consistencydembrandt/dembrandt-skills | Skill | 183 | 5d ago | MIT | A | 38 | Claude Code |