Claude Code
: How to use it, features, and the business problems it solves

Last updated: 2026.11.02

Add bookmark

What is Claude Code?

Claude Code is an AI coding agent from Anthropic that works directly on your codebase. Centered on the terminal, it can also be used from your IDE (VS Code/JetBrains), the web, Slack, mobile, and GitHub to handle everything from building and debugging to shipping. Agentic search grasps your codebase in seconds, and it supports multi-file editing, issue-to-PR workflows, subagents, routines, and computer use. It runs locally and asks for permission before making changes. Pricing is included with Claude Pro/Max/Ultra (Pro from $20/Max $100/Ultra $200), while access via the Console is billed as pay-as-you-go API usage.

Business problems it solves

【Engineer】

About "Claude Code"

What is Claude Code

Claude Code is an AI coding agent from Anthropic that works directly on your codebase. Centered on the terminal, it can also be used from your IDE (VS Code, JetBrains), the web, Slack, mobile, and GitHub to handle everything from building and debugging to shipping. Agentic search lets it grasp your entire codebase in seconds, and it handles edits that span multiple files as well as full workflows from issue to pull request. It runs on macOS, Linux, and Windows.

Talk to your codebase directly, from the terminal

What sets Claude Code apart is that you can bring Claude in as a coding agent without changing the terminal or development tools you already know. Agentic search automatically maps out your project's structure and dependencies, so there's no need to hand-pick context files. It runs locally and always asks for permission before changing files or running commands.

Run several sessions in parallel in the desktop app

You can also use Claude Code from the Code tab of the Claude desktop app (no need to install Node.js or the CLI; macOS and Windows, with Linux in beta). With the update on October 14, 2026 (US time), when you ask Claude to run tasks in parallel, it starts a nested session for each one, and each reports its result back to your main session when it's done. You can save a combination of folders, an SSH host, or the cloud as an "environment" and create a Git worktree per folder, see which sessions are working and which need your input in the sidebar, and ask side questions in a separate tab with /btw without stopping the main work. It's available on the Pro, Max, Team, and Enterprise plans. For how these differ from /rewind and /fork in the CLI, see our guide to Claude Code session management.

How to use it

Install Claude Code

Run curl -fsSL https://claude.ai/install.sh | bash in your terminal to install it. Extensions for VS Code and JetBrains are also available.
Sign in

Sign in with a Claude Pro/Max/Ultra plan or your Claude Console credentials.
Ask it to do a task

Describe what you want in natural language, such as "Fix this bug" or "Write tests."
Work through planning and approval

Claude Code investigates and implements, asking for permission before making changes or running commands. It supports multi-file edits.
Teach it your way of working with rules

Place a CLAUDE.md file in your repository to reflect your coding conventions and preferred approach. You can even hand off everything from issue to submitting a PR.

Features

01Understand and edit

Grasp the codebase and fix it.

Agentic search — Grasp structure and dependencies in seconds
Multi-file editing — Reliable changes that understand dependencies
Issue → PR — From reading to implementing, testing, and submitting a PR

02Agentic capabilities

In parallel, automatically, continuously.

Subagents — Dozens to hundreds of parallel subagents (dynamic workflows)
Routines — Scheduled runs, API, and event responses
Agent view / computer use — Centralized session management, app and browser control

03Integrations and environment

Enhance your existing stack as-is.

CLI, IDE, Slack, web, mobile — Access it from anywhere
MCP, GitHub/GitLab — Connect to tools and extend it
Runs locally — Asks permission before changes, no remote index required

Pricing

Claude Code is included with a Claude subscription. Individuals can use it on the Pro, Max, or Ultra plans, and via Claude Console (API) it's available on standard pay-as-you-go API token pricing (prices shown in USD, as of November 2026). Plan usage limits are shared with the rest of your Claude usage, such as chat.

Plan	Best for	Key details
Pro (from $20/mo)	Small, short coding sessions	Includes Claude Code. For smaller codebases
Max ($100/mo, formerly Max 5x)	Daily use at scale	5x Pro's usage (every 5 hours and every week)
Ultra ($200/mo, formerly Max 20x)	Power users	10x Pro's usage (every week). No 5-hour limit for verified accounts
Claude Console (API)	Pay-as-you-go	Available at standard API token pricing

On October 30, 2026 (US time), Max 5x was renamed "Max" and Max 20x was renamed "Ultra". Prices stay the same and current subscribers don't need to do anything (official X post). The 5-hour limit is removed on Ultra for verified accounts; a temporary limit applies until verification is complete. See the pricing section of the Claude product page for details.

It's also available on premium seats for Team and Enterprise. Features such as Fast mode (a high-speed setting for Opus 5) are provided as well.

The monthly API credits added to Max (now Max and Ultra) and Team on October 7, 2026 cannot be used for interactive Claude Code (terminal, IDE, desktop, web). They apply when you run claude -p or the Claude Agent SDK with an API key from your linked Claude Console organization. If you run claude -p while signed in with your plan, usage still counts against your plan's limits (per the official help center as of October 2026).

How it differs from other AI coding tools

Claude Code stands out for "talking to your codebase directly from the terminal, powered by Claude's reasoning". It doesn't assume you'll switch to a dedicated editor; it enhances your existing development environment as-is.

	Claude Code	Codex	Cursor
Provider	Anthropic	OpenAI (ChatGPT)	Anysphere
Form	Terminal-centered + IDE/web/Slack	ChatGPT + IDE extension + CLI	AI-native dedicated editor
Strengths	Claude's reasoning, local operation, parallel subagents	ChatGPT integration, parallel processing	Refined editor experience

If you want a coding agent on the ChatGPT side, Codex is a comparison point; for an experience in a dedicated editor, Cursor; and for GitHub integration and completions, GitHub Copilot.

The information on this page is based on content published on the official website as of August 2026. Please check the official website for the latest specifications and pricing.

Try Claude Code

Frequently compared services

WebTerm

WebTerm is a free, browser-based Linux terminal built for practice. It implements 100+ commands — pwd, ls, cd through grep, find, chmod, pipes and redirection, Vim and Git — and grades each step by the actual state of the filesystem, so copying an answer doesn't get you past it. 15 mission-style tutorials plus a free-play sandbox. No install, no sign-up, 8 languages including Japanese (desktop browsers only).

# Programming & CLI Learning# Education# Japanese Supported

Devin

An autonomous AI software engineer from the startup Cognition (a coding agent). From a natural-language instruction it autonomously plans, implements, tests, and opens a Pull Request in its own environment, supporting multiple repos and parallel sessions. The current Devin 2 generation offers Core from $20/mo (metered ACU), Team $500/mo, and Enterprise, and integrates with GitHub/Slack/IDE and MCP/API.

# Code Generation# AI Agent# Automation & Labor Reduction# Productivity Improvement

Cursor

Cursor is an AI coding agent (AI code editor) from Anysphere. A VS Code-based desktop app (macOS / Windows / Linux), it takes natural-language instructions and has an agent that understands your codebase handle planning, implementation, and fixes. You can choose its in-house Composer model, Grok, or frontier models from various providers, and it supports running multiple tasks in parallel, cloud agents, agentic code review by Bugbot, MCP, skills, and hooks, and privacy mode. A Cursor CLI and iOS app are also available. Pricing includes Hobby free, Pro $20, Pro+ $60, Ultra $200, and Teams $40 (per user, per month), among others.

# Code Generation# AI Model Development & Management# AI Agent# Operational Efficiency# Japanese Supported

Windsurf（現Devin Desktop）

Windsurf (formerly Codeium) was an AI coding tool known as an AI-native code editor, but in 2025 it was integrated into Cognition, the company behind Devin, and is now offered as "Devin Desktop" (windsurf.com redirects to devin.ai/desktop). Devin Desktop is a desktop app that lets you plan, delegate, and review a group of local and cloud AI agents in a single screen (a Running/Waiting for review/Done session board) without leaving the editor. It is distributed for macOS and other platforms.

# AI Agent# No-Code Automation# Notification & Task Integration# Operational Efficiency

Cline

Cline is an open-source AI coding agent that runs inside the editor and terminal you already use (built by Cline Bot Inc., Apache 2.0). You can use the same agent from a VS Code extension, JetBrains, a CLI, or an SDK, and with Plan/Act it separates planning from execution so you approve as it goes, autonomously handling multi-file edits and command execution. It supports every provider — Claude, GPT, Gemini, local models and more — and with bring your own key there is no vendor lock-in. The extension and CLI are open source and free for individuals (the only cost is usage-based model inference). Used by more than 8 million developers, with 66,000 GitHub stars.

# Code Generation# AI Model Development & Management# API & SDK# AI Agent

GitHub Copilot

GitHub Copilot is an AI coding assistance service provided by GitHub (a Microsoft subsidiary). In addition to code completion, it includes an agent mode that implements autonomously, a cloud agent that works in the cloud, automatic PR review, and the Copilot CLI. It can be used in VS Code, JetBrains, GitHub, the terminal, and more, and you can choose from major models such as Claude, GPT, and Gemini. For individuals there is the free Free plan, Pro $10, Pro+ $39, and Max $100; for businesses there are Business $19 and Enterprise $39 (per user/month, on a GitHub AI credit system).

# Code Generation# AI Model Development & Management# API & SDK# AI Agent

Antigravity

Google's agent-first development platform where AI agents autonomously plan, execute, and verify across editor, terminal, and browser. Now Generally Available as a family of Antigravity 2.0 (Agent Manager)/CLI/SDK/IDE. Choose Gemini 3.x, Claude 4.6, GPT-OSS, and more; free for individuals (macOS/Windows/Linux).

# Code Generation# Image Generation# Design Generation# AI Agent# Productivity Improvement# Quality Improvement & Creative Support

Kilo Code

Kilo Code is an MIT-licensed open-source AI coding agent that runs the same way in VS Code, JetBrains, the CLI, and the cloud. You switch between purpose-built agents — Code, Plan, Ask, Debug, and Review — to generate code, refactor, chase bugs, and review changes. It supports 500+ models with mid-task switching, and charges no markup on AI inference: you pay the provider's rate. You can bring your own API keys or run local models with Ollama. Platform access is free for individuals and $15 per user per month for Teams. Anaconda acquired the company in July 2026, and Kilo Code now has more than 3 million users.

# Code Generation# AI Agent# API & SDK# Productivity Improvement# Japanese Supported

Jules

An asynchronous AI coding agent from Google. Connect a GitHub repository and describe a task, and Jules fixes bugs, writes tests, and updates dependencies in parallel on cloud virtual machines, all the way to creating a pull request. Free for up to 15 tasks a day, with higher limits as a Google AI Pro / Ultra benefit.

# Code Generation# AI Agent

Runcrate

A GPU cloud for AI developers and AI agents from Aeonmind LLC. Rent 20 GPU models such as H100, A100 and RTX 4090 by the hour (most billed by the second), and call 223 models through an OpenAI-compatible inference API. Its MCP server lets Claude Code, Codex and Cursor launch GPUs. Pay as you go from a prepaid balance (from $20, no monthly fee).

# AI Model Development & Management# API & SDK# Generative AI (LLM)# AI Agent

Founden

An AI app builder from O-mega Enterprise, Inc. that turns a description into a website, a customer app with sign-in and a back office, wired up with payments, email, a database and your own domain, and publishes them. With Autopilot on, the AI keeps shipping improvements, answering email and working on growth after launch. Web version and Mac app (building with Claude Code, Codex or Antigravity). Pro from $29 a month, with an 8-day free trial.

# Code Generation# No-Code Automation# AI Agent# Automation & Labor Reduction

Z.ai

The official service for the GLM family of large language models developed by Z.ai (Zhipu AI). In chat (chat.z.ai), GLM-5.3-Flash can write, analyze data and build slides and websites. For developers, Z.ai offers an API (GLM-5.3 costs $1.4 input / $4.4 output per 1M tokens) and the "GLM Coding Plan", a flat-rate plan for using GLM in 20+ tools such as Claude Code and Cline (Lite $18, Pro $80, Max $168 per month). Model weights are published on Hugging Face. Officially supported model languages are English and Chinese, and the interface is in English.

# Generative AI (LLM)# AI Chatbot# Code Generation# AI Agent# API & SDK# Text Generation

Superwhisper

An AI dictation app from SuperUltra, Inc. (US). It turns what you say into clean text without filler words and pastes it straight into the app you are using, such as Slack, Gmail or Cursor. You can choose between local voice models that run on your device, such as Whisper, and cloud models, and switch writing styles with task-specific "modes" for email, messages and more. On the Mac it also records meetings with speaker labels and summaries, and Pro adds audio and video file transcription. Available on Mac, Windows, iPhone and Android. The Free plan offers unlimited dictation with local Whisper models; Pro costs US$8.49 per month, US$84.99 per year or US$249.99 lifetime.

# Speech Recognition & Synthesis# Speech Synthesis & Transcription# Meeting Minutes# Productivity Improvement# Japanese Supported

Articles featuring Claude Code

DeepSeek-V4.1-Flash-1017とは【2026年10月17日公開】APIの料金（円換算）・商用利用・安全性・V4-Proとの違い

DeepSeek（ディープシーク）は2026年10月17日、V4.1-Flashの小改良版「DeepSeek-V4.1-Flash-1017」を公開し、Web版・アプリ・API（deepseek-flash）を同日に切り替えました。重みはMITライセンスで商用利用でき、コード修正のベンチマークDeepSWE v1.1では77.0とClaude Opus 5（74.0）を上回りますが、数字は自己申告で、Opus 5が上の項目も多くあります。この記事では、公式のAPIドキュメントとHugging Faceのモデルカードにもとづいて、何が変わったか、APIの料金を円でいくらか（日本時間のピーク時間帯と半額のオフピーク）、11月1日から課金が始まるSearch／Fetch API、V4-Proの現状、中国のサーバーに保存されるデータの扱いと自社の環境で動かす選択肢を整理します。

Claude MaxのAPIクレジットとは【2026年10月最新】毎月$100〜の受け取り方・使える範囲・Claude Codeは対象か・Haiku 5.5で何回動くか

2026年10月7日（米国時間）、AnthropicはClaudeのMax・Teamプランに毎月のAPIクレジットを付けると発表しました。Max 5x（現在のMax）は月$100、Max 20x（現在のUltra）は月$200、Teamは1席あたりStandard $20・Premium $100をチームで1つの残高にまとめ、上限は$500です。この記事では、Xで食い違って広まったTeamの付き方（オーナー1人が受け取るプール方式）を公式ヘルプにもとづいて正し、使える範囲（Claude API・Managed Agents・Agent SDK・APIキーで動かすclaude -p）と使えない範囲（対話で使うClaude Code・Bedrock等の経由）、claude.aiの請求設定から組織を連携する受け取り方、7日の待機期間と繰り越し不可の条件を整理します。あわせて、同時公開のClaude Haiku 5.5の料金（入力$0.10・出力$0.50／100万トークン）で$100がどれだけの処理になるかを試算し、Pro・Max・Teamの選び方の目安を示します。

What Jev Is [October 2026]: The AI That Generates No Text — How to Use It, Pricing, and How It Differs from Microsoft-Decision-1

On 9 October 2026, Microsoft released Microsoft-Decision-1, a decision model at the same price as Jev ($0.042 per million input tokens, free output) and with the same question types. This article explains what Jev — released by TypeSafe AI on 15 September 2026 — is: a System One model that generates no text and returns Choice (classification), Score (rating) and Noul (a 0–1 truth value) with probabilities; speculative fan-out, where stacking questions barely changes latency; how to get started from the waitlist to the Python SDK, HTTP API and Claude Code skill; routing low-confidence answers to people; and use cases. It then compares Jev with Microsoft-Decision-1 (access, context length, availability, Japanese support), explains which to choose and whether you can use them from Japan, and covers Jev's latest status in October (Series A, rate limits, OpenRouter listing). It also covers the official note that CJK accuracy is lower than English and the weak spots TypeSafe publishes itself.

CLI and Programming Study in the Age of AI Coding Agents [August 2026]: 11 Services, Starting from the Terminal and Git

With Claude Code, Codex and Cursor in everyday use by 2026, what you need is no longer the ability to write from scratch but the ability to read the diffs an agent produces, interpret its errors and recover a broken state — and all of that happens in the terminal. This article compares 11 learning services — WebTerm, WebTerm Learn, Progate, dotinstall, paiza Learning, ZEN Study, Techpit, Recursion, Boot.dev, KodeKloud and DeepLearning.AI — by entry point (language or environment), format, language support, free tier and price. It also covers the courses rebuilt around agents, including Progate's Claude Code Introduction (beta), KodeKloud's Claude Code For Beginners (8h32m) and DeepLearning.AI's course co-produced with Anthropic, and lays out an order to learn in: environment, syntax, agent, evaluation.

Claude Fable 5 vs. GPT-5.5 vs. Gemini 3.1 Pro: Which Should You Choose? A Deep Dive into Performance, Pricing, and Use Cases [July 2026]

A thorough comparison of the latest flagship models from the industry's three leading AI labs, all released in the first half of 2026: Claude Fable 5, GPT-5.5, and Gemini 3.1 Pro. Covers benchmark performance, API pricing, context windows, multimodal support, and how to use them on consumer plans like ChatGPT Plus, Claude Pro, and Google AI Pro — with recommendations by use case, based primarily on official data.

What Is Claude Fable 5 | A Deep Dive into Anthropic's Latest Frontier Model: Performance, Pricing, and How to Use It

A comprehensive look at Claude Fable 5, Anthropic's latest model released in June 2026. Covers benchmark performance in coding, knowledge work, and science, how it compares to Mythos 5, API pricing, and usage guidance — all backed by official data.

Claude Code Session Management: How to Eliminate Backtracking with /rewind and /fork

A systematic guide to Claude Code's /rewind, /fork, /clear, and /compact commands. Covers how the context window works, checkpointing strategies, real-world scenarios, and a decision flowchart for using each command — turning session management into a core development strategy.

[2026 Edition] The Complete Guide to Claude Code: From Installation to Advanced Techniques

A comprehensive guide covering Claude Code installation, basic operations, practical tips, and pricing plans. Packed with best practices you can apply immediately to real projects — suitable for beginners through intermediate users.

[Claude Code Primer] Core Features and Getting Started with a Terminal-Based AI Coding Agent

A beginner-friendly introduction to Claude Code, the terminal-centric AI coding tool. Explains core features, practical use cases, and step-by-step setup instructions.

Top 4 AI Coding Tools Compared | Choosing Between Claude Code, Cursor, Codex, and Antigravity

A side-by-side comparison of the leading AI coding tools — Claude Code, Cursor, Codex, and Antigravity. Guides you to the right choice based on features, strengths, and ideal use cases.

[2026 Edition] 20 AI Tools Transforming Developer Workflows | Coding Assistance, Automated Code Review, No-Code Web Development, and Workflow Automation

A curated look at the best AI tools for developers in 2026. Covers 18 tools across coding assistance, automated code review, no-code development, and workflow automation — all aimed at improving productivity.

Claude Code: How to use it, features, and the business problems it solves