Author: will_tygart

Claude Code is an agentic coding tool that works directly inside your codebase — reading files, writing code, running tests, and making changes with your approval. It’s fundamentally different from asking Claude questions about code in chat. Here’s how to use it effectively from your first session.

Starting a Session

Open the Code tab in Claude Desktop (or run claude in your terminal), then select your session type:

• Local — Claude works on your machine with direct file access. Changes happen locally. Best for everyday development.
• Remote — Claude runs on Anthropic’s infrastructure. The session continues even if you close the app. Best for long autonomous tasks.
• SSH — Claude connects to a remote server over SSH. Best for server-side or cloud VM development.

Select your project folder and choose a model — Sonnet 4.6 for most work, Opus 4.6 for the most complex tasks. You can’t change the model after the session starts.

What to Ask Claude Code to Do

Claude Code works best with clear, specific tasks. Unlike chat, it has your full codebase as context — so you can refer to actual files, functions, and patterns without explaining them.

How Claude Code Makes Changes

Claude Code doesn’t modify your files silently. When it wants to make a change, it shows you a diff — the exact lines it plans to add, remove, or edit — and waits for your approval before writing anything. You can accept the change, reject it, or ask Claude to revise its approach.

This review-before-write pattern means Claude Code is safe to use even on code you’re not fully familiar with. You see every change before it happens.

CLAUDE.md: Persistent Project Instructions

Create a CLAUDE.md file in your project root to give Claude Code persistent context about your codebase — coding conventions, architecture decisions, testing patterns, libraries to prefer or avoid. Claude Code reads this file at the start of every session, so you don’t re-explain your project each time.

# CLAUDE.md example

## Stack
- Python 3.11, FastAPI, PostgreSQL, SQLAlchemy
- Tests use pytest with fixtures in conftest.py

## Conventions
- Functions should have type hints
- No bare except clauses — always catch specific exceptions
- Use Pydantic models for all request/response schemas

## Do not modify
- legacy/ directory — kept for backward compatibility

Common Workflows

Debugging: Paste the error message and stack trace, ask Claude to find and fix the root cause. It reads the relevant files and proposes a fix.

Refactoring: Describe the refactor goal — “extract this into a separate service,” “replace all these conditionals with a strategy pattern” — and Claude Code walks through the changes systematically.

Test writing: “Write unit tests for all functions in this file” or “add edge case tests for the payment processing flow.” Claude reads your existing test patterns and matches them.

Code review: “Review this PR for security issues, missing error handling, and anything that violates our conventions.” Claude reads the changed files and gives structured feedback.

Documentation: “Add docstrings to all public functions” or “generate a README that explains this project’s architecture.”

Tips for Getting the Most Out of It

• Start small. First session, give it a small, contained task in a file you know well. Calibrate your trust before handing it larger work.
• Be specific about constraints. “Don’t use async/await,” “keep changes backward compatible,” “match the style of the existing tests.” Claude Code holds these throughout the session.
• Use CLAUDE.md. Any convention you find yourself re-explaining belongs in this file.
• Review every diff. Claude Code is capable but not infallible. Read each proposed change before approving — especially on production code.
• Use Remote for long tasks. Autonomous multi-file refactors or test generation across a large codebase work better in a Remote session that won’t be interrupted.

For pricing details, see Claude Code Pricing: Pro vs Max. For how it compares to other tools, see Claude vs GitHub Copilot and Claude Code vs Windsurf.

Frequently Asked Questions

Claude Desktop is Anthropic’s native app for Mac and Windows — a dedicated application that brings Claude out of the browser and into your system, with features that aren’t available in the web interface. It’s free to download for all plan types, including the free tier.

What Claude Desktop Includes

The Three Tabs: Chat, Cowork, and Code

Claude Desktop is organized around three modes. Chat is general conversation — identical to claude.ai but accessible from your dock without opening a browser. Cowork is an autonomous background agent that works on tasks in a cloud VM while you do other things — research synthesis, file organization, document generation, spreadsheets. Code is Claude Code with a graphical interface — an interactive coding assistant with direct access to your local project files, where you review and approve each change in real time.

What Makes Desktop Different From the Web

The practical differences over using claude.ai in a browser:

• Always accessible — lives in your dock, reachable from any app via hotkey without switching contexts
• Screenshot capture — take a screenshot and immediately ask Claude about what’s on screen
• Desktop extensions — connect to local files, your filesystem, calendars, email, and native Mac/Windows apps that web connectors can’t reach
• Claude in Chrome — let Claude control your browser directly from the desktop app
• Cowork background tasks — long-running autonomous tasks that continue while you work on something else
• Claude Code integration — work directly with your local codebase without copying files

How to Download and Install

1. Go to claude.ai/download
2. Download the appropriate installer — macOS PKG, Windows x64, or Windows ARM64
3. Run the installer — on Mac, drag to Applications; on Windows, run the setup file
4. Launch from your Applications folder (Mac) or Start menu (Windows)
5. Sign in with your Anthropic account

Linux is not currently supported. The app requires macOS or Windows.

Desktop Extensions

Desktop extensions are installable packages that connect Claude to your local tools — similar to browser extensions but for native applications. They give Claude access to your local file system, calendars, email, messaging apps, and other native applications that web-based connectors can’t reach. Browse and install extensions in Settings → Extensions after installing the app.

Syncing Across Devices

Your conversations, projects, memory, and preferences sync across Claude Desktop, the web interface, and the mobile app when you’re signed in with the same account. Start a session in the desktop app, continue on your phone, pick it back up on the web — the context travels with you.

For the Claude Code-specific features in the desktop app, see How to Use Claude Code. For a comparison of Desktop vs. the web interface for everyday use, see Claude AI Login: All Platforms and Apps.

Frequently Asked Questions

Claude is genuinely good at coding — and for specific types of development work, it’s the strongest AI coding assistant available. But the honest answer requires separating what it does well from where it has real limits. Here’s the actual assessment from someone running Claude across real production systems daily.

Where Claude Excels at Coding

Complex, multi-constraint code generation

Give Claude a detailed spec — specific patterns, error handling requirements, naming conventions, library preferences — and it holds all of them through a long response better than alternatives. Other models tend to drift from earlier constraints partway through. For production code where the specifics matter, Claude’s instruction adherence is a real advantage.

Debugging non-obvious errors

On tricky bugs where the error message points somewhere unhelpful, Claude is more likely to trace the actual root cause rather than addressing the symptom. It’s willing to say “this is probably caused by X upstream” and follow the logic chain. That kind of reasoning saves hours on complex debugging sessions.

Working across large codebases

Claude’s 200K token context window means it can hold significant portions of a codebase in context simultaneously. Understanding how a change in one file affects another, tracking architectural patterns across multiple files, maintaining awareness of project-wide conventions — Claude handles this better than models with shorter context windows.

Code review and security analysis

Claude is strong at finding security vulnerabilities, missing error handling, and logic errors. Give it the code and ask it to review specifically for security issues — SQL injection, authentication gaps, hardcoded credentials — and the findings are reliable and specific. See the full code review guide for prompts and examples.

Claude Code: Agentic development

Claude Code — Anthropic’s terminal-native coding agent — operates autonomously inside your actual codebase. Reading files, writing code, running tests, managing git. For autonomous development work, this is a qualitatively different capability from chat-based code assistance. See Claude Code pricing for tier details.

Claude’s Coding Benchmarks

On SWE-bench — the industry benchmark for real-world software engineering tasks — Claude has performed strongly relative to competing models. Claude 3.5 Sonnet’s performance on this benchmark in 2024 attracted significant developer attention. The current Claude Sonnet 4.6 continues that trajectory.

Benchmarks don’t capture everything — real-world tasks have context, requirements, and edge cases that synthetic benchmarks miss. But they’re a useful signal, and Claude’s performance on coding-specific benchmarks is consistently competitive.

Where Claude Has Coding Limits

Interactive code execution: Claude doesn’t run code interactively in the web interface by default. ChatGPT’s code interpreter lets you upload a CSV and get Python-generated charts in the same window. Claude can reason about data and write code that would do the same, but won’t execute it in-chat. Claude Code handles actual execution in a development environment.

Very specialized frameworks: For niche or rapidly evolving frameworks where training data is sparse, Claude may have less confident knowledge than it does for established technologies. Always verify generated code for less common libraries.

Business logic without context: Claude can generate technically correct code but can’t know your business domain’s rules without you providing them. The more context you give about what the code needs to do and why, the better the output.

How to Get the Best Coding Results From Claude

Frequently Asked Questions