Agentic WeeklyGet 5 use cases every Monday5 use cases, Mondays

How to use Claude Code: install, first session and daily workflow

To use Claude Code, install it with Anthropic's installer, open a terminal in your project and run claude. Sign in with a paid Claude plan or a Console account, then describe what you want in plain English and approve the edits. Use Shift+Tab for plan mode and /init for CLAUDE.md. Reported from Anthropic's docs, checked 2026-10-30.

By Agentic Weekly, operated independently from Texas, US · Last updated (America/Chicago) · How we work

Checked by Agentic Weekly's editorial process: vendor docs re-read.

Last verified: 2026-10-30 (America/Chicago) · Versions covered: Claude Code docs as read on 2026-10-30; latest GitHub release that day was v2.1.314. Our own smoke test used v2.1.310 with a local model · Evidence: Reported (see “What we tested”)

What Claude Code is

Anthropic describes Claude Code as "an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools" (overview, last checked 2026-10-30). It runs in the terminal, in VS Code and JetBrains, as a desktop app and on the web. This guide covers the terminal.

Everything below comes from Anthropic's docs, and the evidence label is Reported. We did not run these steps for this guide. Our separate smoke test ran Claude Code 2.1.310 on a small local model.

Before you start: what you need

  • A terminal and a code project.
  • A paid Claude plan (Pro, Max, Team or Enterprise), a Claude Console account with API credits, or access through Amazon Bedrock, Google Cloud or Microsoft Foundry. Claude Code is not on the free plan. See Claude Code pricing.
  • On native Windows, Anthropic recommends Git for Windows so Claude Code can use its Bash tool.

Step 1: Install Claude Code

Anthropic calls the native installer recommended, and says native installs update themselves in the background (quickstart).

macOS, Linux or WSL
curl -fsSL https://claude.ai/install.sh | bash
Windows PowerShell
irm https://claude.ai/install.ps1 | iex
Homebrew or WinGet (these do not auto-update)
brew install --cask claude-code
winget install Anthropic.ClaudeCode

Open a new terminal and run claude --version. It should print a version number followed by (Claude Code). If the shell says claude is not found, the install folder is not on your PATH yet. For more options, see How to install Claude Code.

Step 2: Start a session and sign in

Start Claude Code in your project
cd /path/to/your/project
claude

On first use, Claude Code asks you to log in in your browser. You only do this once. If ANTHROPIC_API_KEY is set and you approve it, Claude Code skips the login. Inside a session, /login switches accounts and /help lists commands.

Step 3: Ask about your code

The quickstart says "Claude Code reads your project files as needed. You don't have to manually add context." Start with questions like these:

First questions
what does this project do?
where is the main entry point?
explain the folder structure

To point at a file directly, type @ and the path, for example Explain the logic in @src/utils/auth.js (common workflows).

Step 4: Make a change and approve it

Describe the change in plain English. Claude finds the file, shows the edit and, in the default mode, asks before writing it. The quickstart's advice is to be specific. Instead of "fix the bug", write "fix the login bug where users see a blank screen after entering wrong credentials".

Permission modes, from Anthropic's docs (last checked 2026-10-30)
ModeWhat runs without askingUse it for
defaultReads onlyReviewing every action yourself
acceptEditsReads, file edits and common filesystem commandsIterating on code you are reviewing
planReads; edits wait until you approve a planExploring before changing anything
autoEverything, with background safety checksLong tasks, on supported models
bypassPermissionsEverythingIsolated containers and VMs only

Press Shift+Tab to cycle modes mid-session, or start in one with claude --permission-mode plan (permission modes).

Step 5: Plan before big edits

For larger changes, Anthropic suggests plan mode: "Claude reads files and proposes a plan but makes no edits until you approve." The status bar shows ⏸ plan mode on while it is active. Anthropic's cost docs say planning first also avoids wasted tokens on the wrong approach.

Step 6: Give it project memory with CLAUDE.md

A CLAUDE.md file holds instructions Claude reads at the start of every session: build and test commands, coding standards and conventions. Run /init and Claude drafts one from your codebase. If one already exists, /init suggests improvements instead (memory docs).

  • Keep each CLAUDE.md under 200 lines, as the docs suggest. Longer files use more context and are followed less reliably.
  • Put team rules in ./CLAUDE.md and commit it. Put personal preferences in ~/.claude/CLAUDE.md, or CLAUDE.local.md (add it to .gitignore).
  • Claude can read a repository's AGENTS.md instead, if that is what your project uses.
  • Run /context to check which memory files loaded.

Step 7: Use Git through Claude Code

Git prompts from the quickstart
what files have I changed?
commit my changes with a descriptive message
create a new branch called feature/quickstart
help me resolve merge conflicts

To run two tasks in parallel without the edits colliding, start each in its own Git worktree with claude --worktree feature-auth. The repository needs at least one commit first.

Commands to remember

Everyday Claude Code commands, from Anthropic's docs (last checked 2026-10-30)
CommandWhat it does
claudeStart an interactive session
claude "task"Start with a first prompt
claude -p "query"Run one query and exit (for scripts and CI)
claude -cContinue the latest conversation in this folder
claude -rPick a previous conversation to resume
/clearClear the conversation; use it between unrelated tasks
/compactShrink a long conversation
/modelSwitch model
/usageSee plan usage and what counts against your limits
/initCreate or improve CLAUDE.md
/mcpCheck connected MCP servers
/helpList commands
Pipe output into Claude non-interactively
git log --oneline -20 | claude -p "summarize these recent commits"

Keep costs and limits in check

Anthropic says Claude Code across enterprise deployments averages "around $13 per developer per active day and $150-250 per developer per month" at API rates (cost docs, last checked 2026-10-30). On a subscription, it shares your plan's five-hour and weekly limits with Claude chat.

  • Use Sonnet for most coding. The docs say it "handles most coding tasks well and costs less than Opus".
  • Run /clear between tasks and keep CLAUDE.md short.
  • Hand big exploration jobs to a subagent ("use a subagent to investigate how our auth system handles token refresh") so only the summary comes back into your context.

Next steps

What we tested

Nothing in this guide was run for this page. It is Reported from Anthropic's docs, last checked 2026-10-30. Separately, on 2026-10-25 we installed Claude Code 2.1.310 with the native installer and made one edit through a small local model. The first, vaguer prompt failed and a precise second prompt worked. See the test log.

  • Claude Code: Update now if you use the sandbox or run Claude Code on a cloud provider; skip if you wanted flashy new features, this is a hardening release. Tested (smoke test, 2026-10-25, local Qwen2.5-3B-Instruct, not vendor models).

FAQ

How do I use Claude Code for the first time?

Install it, open a terminal in your project folder, run claude and sign in with a paid Claude plan or a Console account. Then ask "what does this project do?" before you ask for a change. This follows Anthropic's quickstart, last checked 2026-10-30.

Do I need a paid plan to use Claude Code?

Yes. You need a Claude Pro, Max, Team or Enterprise plan, a Console account with API credits, or a supported cloud provider such as Amazon Bedrock. The free Claude plan does not include Claude Code, per claude.com/pricing on 2026-10-30.

Can I use Claude Code in VS Code?

Yes. Anthropic lists extensions for VS Code and JetBrains IDEs, a desktop app, a web version at claude.ai/code, Slack, and CI through GitHub Actions or GitLab, alongside the terminal. This guide covers the terminal version only.

What is plan mode in Claude Code?

In plan mode, Claude reads files and proposes a plan but makes no edits until you approve it. Press Shift+Tab until the status bar shows plan mode, or start a session with claude --permission-mode plan, per Anthropic's docs.

What is CLAUDE.md?

It is a markdown file of instructions that Claude reads at the start of every session, such as build commands, test commands and coding standards. Run /init to generate one from your codebase, and keep each file under 200 lines, as Anthropic suggests.

Have you tested this guide?

No. These steps are Reported from Anthropic's docs, last checked 2026-10-30. Our only hands-on run is a smoke test on 2026-10-25, where Claude Code 2.1.310 made one file edit through a small local model. The test log is linked under What we tested.

Sources

Page history

  • : First published. Anthropic's Claude Code docs read on this date; nothing was run for this guide.

Markdown version for agents: /guides/how-to-use-claude-code.md