agentleFS
Sign inStart free
timothywarner-orgtimothywarner-org/claude-code/segment_1_quickstart/CLAUDE.md

claude-code / segment_1_quickstart

CLAUDE.md223 starsChanged 4 months agoMITView on GitHub

This directory teaches install + first contact with Claude Code. The lesson goal is to demonstrate that CLAUDE.md is the smallest, sharpest lever for giving a stateless model project state. This file itself becomes a teaching artifact in Segment 2. Plain-spoken senior engineer. Bold key terms. No em dashes. No "leverage." No "ask" as a noun. If you're tempted to edit anything outside this directory, leave a <!-- TODO: Agent E review --> comment instead. Segments 2-4 are owned by…

The file

We split this CLAUDE.md into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep examples under 60 lines: If a demo grows past that, split it - learners need to read it on a projector.

    line 15
  2. Very specific:

    Real model IDs in strings: Use claude-sonnet-5 literally, not a placeholder.

    line 16
  3. Very specific:

    If you're tempted to edit anything outside this directory, leave a <!-- TODO: Agent E review --> comment instead.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Segment 1 - Zero (Claude Code Quick Start)

This directory teaches install + first contact with Claude Code. The lesson goal is to demonstrate that CLAUDE.md is the smallest, sharpest lever for giving a stateless model project state. This file itself becomes a teaching artifact in Segment 2.

What lives here

  • 01_installation.md - the segment guide (5-block shape: cold open, mental model, demo, try-it-now, check understanding)
  • 02_verify_setup.ts - environment verification script
  • 03_terminal_workflows.ts - basic workflow demos

Conventions for code in this segment

  • TypeScript only, run via npx tsx <file.ts>. No build step. No tsc. No compiled output committed.
  • No class state. Demos are top-level scripts or pure functions. We're teaching mental models, not OOP.
  • Keep examples under 60 lines. If a demo grows past that, split it - learners need to read it on a projector.
  • Real model IDs in strings. Use claude-sonnet-5 literally, not a placeholder. Aliases (sonnet, opus) are fine in shell examples.
  • No @anthropic-ai/sdk calls. This segment is CLI-only. SDK usage belongs to later segments.

Voice

Plain-spoken senior engineer. Bold key terms. No em dashes. No "leverage." No "ask" as a noun.

Cross-segment etiquette

If you're tempted to edit anything outside this directory, leave a <!-- TODO: Agent E review --> comment instead. Segments 2-4 are owned by other agents this sprint.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free