Ai Coding - Claude Code Blog

Sonnet 5 landed June 30 with near-Opus coding ability, a 1M-token context window, and $2/$10 launch pricing through August. Here's what actually changed, the tokenizer fine print that affects your bill, and which model to run when.

Haiku, Sonnet, Opus, and now Fable — Anthropic ships four tiers, and picking the wrong one either burns money or fumbles the task. Here's a practical map of the lineup, what each model is for, and how to route work between them.

The /loop command runs a prompt or slash command on a repeating interval inside your active Claude Code session — polling a deploy, babysitting tests, iterating until something passes. Here's how it works, when to use it, and how it differs from routines.

Claude Code has six ways to extend it — CLAUDE.md, skills, subagents, MCP servers, hooks, and plugins — and they overlap just enough to be confusing. This decision guide explains what each one is, when to reach for it, when not to, and how to combine them.

Fable 5 is the first Claude model to sit above Opus — a new tier, a new name, and double the price. Here's what it is, when it's worth it, what changes in the API, and how to use it well in Claude Code.

Claude Opus 4.8 pushes the autonomous horizon from an hour to a workday, tightens subagent coordination, and ships meaningful gains on cost-per-task. Here's what's actually different, what to do with it, and where it still falls short.

A practical, no-hype comparison of Claude Code against every serious competitor in 2026 — Cursor, GitHub Copilot, Codex CLI, Aider, Cline, Windsurf, Devin, Replit Agent, Zed AI, and Sourcegraph Cody. Architecture, agentic depth, extensibility, pricing, and when to pick which.

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 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.