Claude Code
Anthropic's agentic coding tool that reads a codebase, edits files, runs commands and verifies its work from the terminal, IDE or web.
- Developer
- Anthropic
- Model family
- Claude
- Released
- 2025-02 (research preview)all 2025 milestones
Claude Code runs an agentic loop: gather context, take an action, verify the result, repeat. Its behaviour is shaped by standing instructions in CLAUDE.md, permission settings, hooks that run deterministic checks, subagents for delegated work, skills for reusable procedures and MCP servers for external tools.
Connected
- AnthropicAmerican artificial intelligence corporation
- Claudelarge language model family developed by Anthropic
- CLAUDE.mdA Markdown file of standing instructions that Claude Code loads at the start of every session, at user, project and folder level.
- Claude Code hooksShell commands that Claude Code runs automatically at lifecycle events such as before or after a tool call, so rules can be enforced by code rather than requested in prose.
- Claude Code subagentsSpecialised agents with their own instructions, tools and context window that the main Claude Code session can delegate tasks to.
- Agent SkillsFolders of instructions, scripts and resources that Claude loads on demand when a task matches the skill's description, introduced by Anthropic in October 2025.
- Model Context Protocol (MCP)An open protocol, introduced by Anthropic in November 2024, that standardises how AI applications connect to external tools and data sources.
- Claude Code slash commandsBuilt-in and custom commands typed with a leading slash in Claude Code, such as /init to draft a CLAUDE.md or project-defined commands stored as Markdown.
- Plan modeA Claude Code mode in which the agent researches and proposes a plan without editing files until the user approves.
Linked from
- Altitude, depth and rangeFelix Rieseberg’s framework for ambition with AI models: speed repeats work faster, altitude targets outcomes, depth uses expert instruments and range combines disciplines.
- Felix RiesebergSoftware engineer and author of the October 2026 essay How to be more ambitious: A tutorial for humans with models, which describes speed, altitude, depth and range.
- Claude DuetAnthropic’s proactive personal agent: it works in connected apps on a cloud computer and returns briefs, files and approval requests. Launched as an invitation-only US Pro and Max research preview in October 2026.
- Agent evaluationRepeatable testing of an AI agent's complete task, tool use, permissions and final system state against explicit acceptance criteria. A successful demo is not a production reliability estimate.
- agent-html-kitAn open-source template kit and Claude Code skill (kit.js) that lets agents emit content-only HTML components while design lives in one shared file, published with a 72-run HTML vs Markdown benchmark.
- Karpathy-inspired CLAUDE.md rulesA widely starred public CLAUDE.md with four behaviour rules: think before coding, simplicity first, surgical changes and goal-driven execution.
- Frontend design skillAn Anthropic-published Agent Skill that steers Claude away from generic interfaces toward distinctive, production-grade front-end design.
- Codex CLIOpenAI's open-source coding agent that runs in the terminal, released in April 2025.
- CursorAn AI-first code editor built on VS Code by Anysphere, with agent mode, codebase indexing and project rules.
- Gemini CLIGoogle's open-source terminal agent for Gemini models, released in June 2025.
- Git worktrees for parallel agentsUsing git worktree to give each coding agent its own checkout of the same repository, so parallel sessions don't overwrite each other.
- Claude Agent SDKAnthropic's SDK that exposes the agent harness behind Claude Code so developers can build their own agents.
- AI for software developmentUsing language models and coding agents to write, refactor, test and review code.
Field notes that cover Claude Code
More agent tooling & protocols
- AGENTS.mdAn open, tool-neutral Markdown convention for giving coding agents project instructions, introduced by OpenAI in August 2025 and now stewarded by the Linux Foundation's Agentic AI Foundation.
- Agent2Agent (A2A) protocolAn open protocol, launched by Google in April 2025, for agents from different vendors to discover each other and exchange tasks.
- Agent Payments Protocol (AP2)Google's open protocol, announced in September 2025, for agents to make payments on a user's behalf using signed mandates.
- Agentic Commerce Protocol (ACP)An open standard from OpenAI and Stripe, announced in September 2025, that lets AI agents complete purchases with merchants, first used for Instant Checkout in ChatGPT.
- llms.txtA proposed convention, published by Jeremy Howard in September 2024, for a Markdown file at a site's root that tells language models what the site is and where to read more.
- robots.txtThe Robots Exclusion Protocol file that tells crawlers, including AI crawlers such as GPTBot and ClaudeBot, which paths they may fetch; standardised as RFC 9309 in 2022.