Claude Code
Definition
Claude Code is Anthropic's AI agent that works inside your files and terminal: it reads a project, edits files, runs commands and connects to other tools. Anthropic built it for software work, but it also handles other tasks made of files, APIs and repeatable steps.
By Ronan Liedmeier, fractional head of growth and course author · Published 17 October 2026 · Last updated 17 October 2026
Also called: Claude Code CLI
Anthropic's docs list the terminal, IDE extensions, a desktop app and the browser as places it runs. Marketers and operators can point it at reports, exports, content folders or ad-platform APIs.
How it works
Its documentation calls Claude Code the harness and Claude the model inside it. You shape what it does in a few ways. A CLAUDE.md file holds standing project instructions that load at the start of every session. Skills package repeatable workflows. Hooks run a command at fixed points, such as before a file is edited. Subagents take side tasks in a separate context. MCP servers connect outside tools. It can also run without anyone watching, on a schedule or inside CI.
Example
A content lead keeps one folder per client, each with its own CLAUDE.md holding tone rules and banned phrases. A hook blocks any file write outside the client folder she is working in. Each Monday she asks Claude Code to draft five posts from that client's notes, and a subagent checks each draft against the tone rules before she reads them.
Common mistake
Many people write a safety rule such as "never touch files outside this folder" only in CLAUDE.md. The model can miss an instruction in a long session. A hook runs whether the model remembers or not, so rules that must hold go there.
Learn it in AI Academy
- Claude Code as the Agency OSExpert · 10 min
- Coding Agents for Non-CodersBeginner · 14 min
Related terms
- Coding agent
- A coding agent is an AI agent that works directly in a computer's files and command line: it reads, creates and edits files and runs commands based on plain-English instructions. Despite the name, it can do most file-based work, such as cleaning up spreadsheets or building a small app.
- Agent harness
- An agent harness is the software wrapped around an AI model that turns it into a working agent: it supplies the tools, file access, permissions, memory and the loop that chains actions together. The model does the reasoning; the harness decides what it can see and do.
- Agent skill (SKILL.md)
- An agent skill is a folder of instructions, built around a SKILL.md file, that teaches an AI agent how to do one specific task. The agent sees only the skill's name and description until a task matches, then loads the full instructions.
- Model Context Protocol (MCP)
- Model Context Protocol (MCP) is an open standard that lets AI apps connect to outside tools and data, such as a calendar, a CRM or a database, through one shared format. Apps that support MCP can then use those tools without a custom integration for each one.