Claude Code
Also: Claude Code CLI
Claude Code is Anthropic's coding agent. You point it at a codebase and it reads files, writes and edits code, runs commands and tests, and works through a task until it is done, asking before risky steps. It runs in the terminal, in VS Code and JetBrains, in the Claude desktop app, on the web and in Slack, and cloud sessions keep working while your laptop is closed. It is included in Pro and Max, and on Team and Enterprise admins can push settings every developer must follow.
In practice
You're building a feature and open your terminal. You type your goal — "add pagination to this API endpoint" — and Claude Code reads your codebase, writes the changes, runs the tests, and fixes the failures, all without you specifying each step. It's Claude operating as a software engineer inside your actual project.
Related concepts
Where Claude Code shows up
11 articlesUse the Claude app for writing, research, analysis and finished documents. Use Claude Code when the work lives in a codebase and you want Claude to edit files and run commands. Updated November 2026, now that Claude Code runs on the web and desktop too.
Claude Code is a different product from Claude.ai — it is an agentic coding tool that runs in the terminal. Here is what it does and when it makes sense.
Engineers are often the last team to adopt Claude, and the first to find the most interesting uses once they do. The field note on what actually works — beyond autocomplete.
On April 30, 2026 Anthropic moved Claude Security from research preview into public beta for Claude Enterprise. It scans repositories for vulnerabilities, traces data flows across files, and writes patches you can review and apply. Here's what it does, who it's for, and where it fits next to existing security tools.
Anthropic's new `claude agents` CLI mode lets you fire off independent tasks simultaneously and navigate between them — turning Claude Code into a proper multi-agent terminal environment.
Shipped with Opus 4.8 as a research preview, Dynamic Workflows let Claude write a multi-step plan and fan it out across tens to hundreds of subagents running in the background. It's built for work one context window can't hold — codebase-wide migrations, sweeping audits. Here's what it is, how it differs from sub-agents and Agent Teams, and when it's worth the token bill.
Anthropic planned to move programmatic usage (Agent SDK, `claude -p`, Code GitHub Actions, third-party agent apps) off subscription limits and onto a separate metered credit on June 15, 2026. On June 15, it cancelled the change. Nothing changes for now: those surfaces still draw from your Pro, Max, Team, and Enterprise limits exactly as before. Here's the full story, why it matters, and what to watch for next.
Six changes landed on the Claude API and in Claude Code in June 2026 that affect how you build and what you pay. Rate-limit tiers were consolidated and raised, fast mode started winding down for older Opus models, the code execution tool gained persistent state, and Claude Opus 4 and Sonnet 4 were retired. Here is each one, the date, and what to do about it.
On August 14, 2026, auto mode became the default for new Claude Code sessions on Pro, Max, and Team plans — an AI classifier now approves safe commands instead of prompting you for each one. Enterprise and API remain opt-in. Here is what changed, the admin settings to know about, and the case for turning it off in specific places.
On October 15, 2026 Anthropic moved Code Review out of research preview for Claude Team and Enterprise. It reviews every new pull request automatically, with a depth setting per repository. How the setup works and how to pilot it.
Claude Code v2.1.323, released November 12, 2026, added Code Mode as an experimental opt-in. Claude writes a short piece of JavaScript that makes its tool calls, and Claude Code runs it in your session. It is off by default and works only in a terminal session on the Anthropic API. It also changes how auto mode reviews work, how your hooks get called, and which sessions you can resume. How to try it, what to check first, and how an admin blocks it.