Claude Code - Claude Code Blog

Plan Mode is the difference between agents that ship the right thing and agents that confidently ship the wrong thing. Here's how it works, when to use it, and the habits that turn it into your biggest reliability lever.

Worktrees are the single biggest unlock for running multiple Claude Code agents at once without conflicts. Here's how they work, when to use them, and the failure modes that take down most teams the first week.

PMs, marketers, designers, and ops people are now opening Claude Code on real production repos. Here's how to actually ship useful changes — and the specific things that make engineers want to revoke your access.

Ultrareview (/ultrareview) runs a multi-agent cloud review of your current branch or a GitHub PR — parallel specialists reviewing security, architecture, correctness, and style. Here's what it is, how to run it, and when to reach for it.

The complete Claude Code cheat sheet for 2026. Every slash command, keyboard shortcut, CLI flag, hook event, and MCP setup step in one page — copy-paste ready, updated for Opus 4.7 and the 1M token context window.

Anthropic Labs just launched Claude Design — a new research preview that turns prompts into prototypes, slides, and one-pagers, powered by Opus 4.7. Here's what it is, how it works, and how to use it alongside Claude Code for real design workflows.

Claude Opus 4.7 is here, building on the 1M token context window with sharper reasoning, better tool orchestration, and tighter agentic workflows. Here's what's new, what's genuinely better, and how to put it to work.

Claude Code now ships with a persistent, file-based memory system that remembers user preferences, project decisions, and feedback across sessions. Here's how it works and how to get the most out of it.

Everything you need to know about Claude Managed Agents — Anthropic's new fully managed platform for running autonomous AI agents in the cloud. Covers architecture, tools, environments, sessions, code examples, and real-world use cases.

Claude Opus 4.6 brings a 1 million token context window, multi-platform Claude Code availability, fast mode, and background agents. Here's what these changes mean for how you build software with AI in 2026.

Context engineering is the most important skill for working with AI coding agents. Learn proven techniques to structure your project context, CLAUDE.md files, and prompts so Claude Code produces better code on the first try.

Everything you need to know about Claude Dispatch -- Anthropic's new feature that lets you assign tasks from your phone and have Claude execute them on your Mac. Covers setup, use cases, limitations, and how it compares to Remote Control.

Vibe coding is the fastest-growing trend in software development. Learn how to use Claude Code to build full applications by describing your intent in natural language — no line-by-line coding required.

Master Claude Code's subagent system to orchestrate specialized AI teams. Learn how to parallelize work, chain agent outputs, and build multi-agent workflows that tackle complex development tasks autonomously.

Learn how to build, configure, and deploy custom Claude Code agents that automate complex development workflows. Covers agent architecture, subagents, CLAUDE.md patterns, and real-world examples you can use today.

A contrarian look at whether the Model Context Protocol is dying or thriving. We examine the fragmentation, complexity, and adoption challenges -- alongside the reasons MCP might be more important than ever.

Learn how to use Claude Code Remote Control to access your local terminal sessions from your phone, tablet, or any browser. This guide covers setup, security architecture, CLI flags, MCP integration, and real-world workflows.

Claude Code skills aren't just for developers. Here are 15 practical skills for writing, research, project management, data analysis, and more — with ready-to-use templates.

Learn how to build custom skills for Claude Code — reusable slash commands that automate your most common workflows. Step-by-step tutorial with real examples.

Anthropic just launched its first official certification — the Claude Certified Architect. Here's what it covers, who it's for, and how to prepare.

Stop scrolling through plugin lists. Here are the Claude Code plugins that actually matter — organized by what you build, with install commands you can copy right now.

An in-depth comparison of Claude Code, Cursor, and GitHub Copilot covering AI models, agentic capabilities, terminal workflows, pricing, and real-world use cases. Find out which AI coding assistant fits your workflow.

Learn how to use Claude Code hooks to automate linting, testing, security scanning, and more. This step-by-step guide covers PreToolUse, PostToolUse, Notification, and Stop hooks with real examples you can copy today.

Stop using Claude Code like a fancy autocomplete. These 10 workflows combine hooks, MCP servers, agents, and skills into powerful automations that eliminate hours of repetitive work every week.

Learn what MCP servers are, how they work with Claude Code, and how to set up your first integration. Covers configuration, top servers, real-world workflows, and advanced patterns.

Learn how to write an effective CLAUDE.md file to supercharge Claude Code in your projects. Covers structure, best practices, advanced patterns, and real-world examples for every tech stack.

A deep dive into OpenClaw (formerly Clawdbot), the open-source AI personal assistant with 147K+ GitHub stars — what it does, how it works, and how it compares to Claude Code.