First-party only — a session id and where you arrived from, so we can tell which pages are worth writing more of. No advertising, no third-party trackers, nothing that follows you off this site.
by Anthropic · reviewed July 25, 2026
Anthropic's agentic coding tool. Lives in the terminal, reads and edits your repo directly, and takes instructions from a CLAUDE.md file you write.
Claude Code runs as a CLI in your project directory and operates on the real filesystem — it reads files, runs commands, edits code and commits. Its behaviour is steered by a CLAUDE.md memory file, reusable skills, slash commands, hooks that fire on tool events, and a permission model that decides what it can do without asking. There are also desktop, web and IDE surfaces, plus an SDK for building your own agents on the same loop.
Claude models only (Opus / Sonnet / Haiku tiers)
Multi-file work in a repo you can describe well — the more context you put in CLAUDE.md, the further ahead it gets.
Reviewed July 25, 2026. Pricing changes often — check the official page before deciding.
Every tool here reads a project instruction file, and every one of them does better work when that file is accurate. The free Foundations track covers writing one; the Agent Operating Kit is the templates already written.