---
title: "Claude Code | AgentRQ Glossary"
url: https://agentrq.com/glossary/claude-code
description: "Claude Code is Anthropic's agentic coding assistant that runs in your terminal, autonomously reading files, editing code, running tests, and using tools to complete software development tasks."
---

[Back to Glossary](https://agentrq.com/glossary/)

# Claude Code

**Claude Code** is Anthropic's agentic coding assistant. It runs directly in your terminal and operates as a full [autonomous agent](https://agentrq.com/glossary/autonomous-agent) — reading files, editing code, running shell commands, executing tests, and iterating until a task is complete.

## What Claude Code Can Do

- → **Read and understand codebases** — Explore files, understand architecture, trace dependencies
- → **Write and edit code** — Implement features, fix bugs, refactor, write tests
- → **Run commands** — Execute shell commands, run test suites, build projects
- → **Use tools** — Call external APIs, search the web, interact with databases
- → **Connect via MCP** — Use [MCP servers](https://agentrq.com/glossary/mcp-server) like AgentRQ to notify humans and await approval

## Claude Code as an Agent

Claude Code follows a perceive-plan-act loop. When you give it a task like "add rate limiting to the API," it will:

1. Read the relevant source files
2. Plan the implementation
3. Write the code
4. Run tests to verify
5. Report back — or ask for guidance when needed

This makes it fundamentally different from a code completion tool. Claude Code acts on your codebase autonomously.

## Claude Code + AgentRQ

By connecting Claude Code to [AgentRQ](https://agentrq.com/) via [MCP](https://agentrq.com/glossary/mcp), you gain real-time visibility into what your agent is doing. Claude Code agents can:

- → Create [tasks](https://agentrq.com/glossary/task) on your [task board](https://agentrq.com/glossary/task-board) for work they're undertaking
- → Send [notifications](https://agentrq.com/glossary/notification) when they hit a blocking question
- → Wait for your [approval](https://agentrq.com/glossary/approval) before taking risky or irreversible actions
- → Continue autonomously once you've replied

This is [human-in-the-loop](https://agentrq.com/glossary/human-in-the-loop) agent collaboration at the task level.

## Getting Started

bash

```bash
# Install Claude Code
npm install -g @anthropic-ai/claude-code

# Add AgentRQ MCP server to your config
# See: https://agentrq.com/docs/getting-started
```

## Related Terms

- → [Agent](https://agentrq.com/glossary/agent)
- → [Autonomous Agent](https://agentrq.com/glossary/autonomous-agent)
- → [MCP](https://agentrq.com/glossary/mcp)
- → [Human-in-the-Loop](https://agentrq.com/glossary/human-in-the-loop)
- → [Tool Use](https://agentrq.com/glossary/tool-use)