how to set up claude code

📖 Bu rehber ToolPazar ekibi tarafından hazırlanmıştır. Tüm araçlarımız ücretsiz ve reklamsızdır.

Step 1 — Install

Claude Code is Anthropic’s terminal-native coding agent. It reads your entire repo, edits files, runs commands, and drives git — all from natural language. Powered by Claude Opus 4.7 (released April 16, 2026), it’s the most capable autonomous coding agent you can actually use today, and in developer satisfaction surveys it sits at the top of the pack.

Step 2 — Your first session

This guide covers installation, your first real session, sub-agents, skills, and the permission model — in that order. Assumes you’ve used a terminal before and have an Anthropic API key.

Step 3 — Understand the permission model

Claude Code ships as an npm package. You need Node.js 18+.

Step 4 — CLAUDE.md

Then, from any project directory:

Step 5 — Sub-agents

On first run it will ask you to log in (or paste an API key). A few IDE extensions wrap it — VS Code, JetBrains — but the terminal is the canonical surface; the wrappers just render the same session inline.

Step 6 — Skills

Pick something real but bounded. Good first-session prompts:

Step 7 — MCP servers

Don’t start with “refactor the whole app.” Claude Code is most reliable when the scope fits in a single PR’s worth of change. Large scopes should be decomposed — often into sub-agents, which we’ll cover in step 5.

Step 8 — Budget

Claude Code never runs a write command without your permission. You’ll see three prompts frequently:

How to tell it’s working

Resist the urge to “auto-approve everything.” Review mode slows you down for about three sessions, then becomes fast muscle memory. It’s also how you notice an agent about to delete the wrong directory, which is worth an hour of friction.