ai-engineering-from-scratch: Skill for Claude Code

.claude/skills/build-project/SKILL.md

build-project is a skill for Claude Code from rohitg00/ai-engineering-from-scratch. It costs 90 tokens per session (1,489 once invoked), scanned A, original, MIT.

A hands-on tutor for learning AI engineering by building real projects one stage at a time. It gives hints rather than complete solutions, runs the stage's grader, and records progress.

In plain words
What is it for?
Use it to start or resume a project stage, read its lesson, predict the result, write code, run the checks, reflect, and update the learning record.
Why use it?
It gives learners a structured way to practise instead of only reading lessons or copying finished code. Each session keeps the learner responsible for writing and checking the code.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code; mentions Codex.

This is rohitg00/ai-engineering-from-scratch's own configuration. It tells Claude Code how to work on ai-engineering-from-scratch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-engineering-from-scratch configures →

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/project_test.py <project-id> --init <workspace>.

About the project

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.

rohitg00/ai-engineering-from-scratch · 77,007 stars · on GitHub · aiengineeringfromscratch.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/.claude/skills/build-project/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/rohitg00/ai-engineering-from-scratch

Made for: Claude Code.

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 build-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/build-project/github.svg)](https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/build-project)
Your own site
<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/build-project"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/build-project/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.

agentmods 80×15 button for build-project

Your own site · 80×15
<a href="https://agentmods.dev/skills/rohitg00/ai-engineering-from-scratch/build-project"><img src="https://agentmods.dev/badge/skills/rohitg00/ai-engineering-from-scratch/build-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 29 Sept 2026
  • Snyk warn 29 Sept 2026
How audits are shown
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 5.1 $0.00090 $0.01489
Opus 5.5 $0.00036 $0.00596
Sonnet 5.5 $0.00018 $0.00298
Haiku 4.5 $0.00009 $0.00149

Measured 1mo ago against content hash 6e3962779e30, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

build-project 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 1mo 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.

.claude/skills/build-project/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build Project

You are the project tutor for the AI Engineering from Scratch Projects section. One invocation teaches one stage of one project. The learner writes the code. You read, ask, hint, run the grader with them, and record progress.

Host invocation contract

Host Start or resume
Claude Code /build-project or /build-project <project-id>
Codex build-project, or choose it from /skills
Other compatible hosts Use build-project to start or resume my project.

Never present one host's syntax as universal.

Content sources

Every project lives in projects/<project-id>/ and is described by projects/<project-id>/project.json: its level, stages in order, prerequisite lessons, language choices, and requirements. For each stage, read:

  • projects/<id>/stages/<stage-id>/docs/en.md: the lesson for the stage
  • projects/<id>/stages/<stage-id>/starter/: the stubs the learner fills in
  • projects/<id>/stages/<stage-id>/tests/: what the grader checks

Prefer local files. If the repository is not cloned, fetch from https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/<path> and teach in conceptual mode (see below). The project list is the set of folders under projects/ that contain a project.json, excluding _template. Planned projects in projects/roadmap.json are not buildable yet.

Never open projects/<id>/solution/ or projects/<id>/heldout/ to show the learner code or answers. You may read the solution yourself only to diagnose why a correct-looking attempt fails, and then give a hint, not the code.

Step 0: find or create progress

Use PROJECTS-LEARNING.md in the learner's working directory. It can hold several projects. Never overwrite existing notes.

If it does not exist, create it:

# My Projects
<!-- Managed by the build-project tutor. -->

## research-report-agent
- Started: <YYYY-MM-DD>
- Workspace: <absolute path to the learner's project folder>
- Mode: Executable or Conceptual
- Current stage: 1 of <N>

| Stage | Status | Grader result | Date | Note |
|---|---|---|---|---|
| 01-<slug> | Next | | | |

Read the full file on GitHub · 143 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. 1mo ago First seen · 143 lines · 90 tokens per session scan A 6e3962779e30

Subscribe to this mod's changes

build-project is a skill published in the GitHub repository rohitg00/ai-engineering-from-scratch (77,007 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,489 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 2026-09-30.

Related

build-project compared with skills from other repositories

build-project next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
build-projectrohitg00/ai-engineering-from-scratchSkill77kyesterdayMITA90Claude Code
playwrightopenai/openai-agents-pythonSkill31ktodayMITA19Claude Code, Codex
show-mehumanlayer/humanlayerSkill13kyesterdayApache-2.0A25Claude Code
eli5genkit-ai/genkitSkill6.6kyesterdayApache-2.0A16Claude Code, Codex
deck-course-modulenexu-io/html-anythingSkill9.4k24d agoApache-2.0A25Claude Code, Codex
skill-contract-reviewerfancyboi999/ai-engineering-from-scratch-zhSkill1.3k3d agoMITA24Claude Code, Codex
skill-invocation-routerfancyboi999/ai-engineering-from-scratch-zhSkill1.3k3d agoMITA38Claude Code, Codex