> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/sanbuphy/claude-code-source-code/llms.txt
> Use this file to discover all available pages before exploring further.

# Claude Code

> An AI-powered coding assistant CLI with an agentic loop, 40+ built-in tools, 80+ slash commands, and multi-agent orchestration — extracted from @anthropic-ai/claude-code v2.1.88.

Claude Code is Anthropic's production-grade AI coding assistant. It embeds a streaming agentic loop powered by Claude, capable of reading files, executing shell commands, searching the web, spawning sub-agents, and managing long-running tasks — all within your terminal.

This documentation covers the source code extracted from the `@anthropic-ai/claude-code` npm package v2.1.88, providing an in-depth reference for the architecture, tools, commands, and internal systems.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get Claude Code running in minutes with authentication and your first query.
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install options: npm global, run pre-built CLI, or build from source.
  </Card>

  <Card title="Core Concepts" icon="lightbulb" href="/concepts/agent-loop">
    Understand the agent loop, tool system, permission model, and context management.
  </Card>

  <Card title="Architecture" icon="diagram-project" href="/architecture/overview">
    Deep dive into the query engine, multi-agent system, MCP integration, and persistence.
  </Card>
</CardGroup>

## Explore the reference

<CardGroup cols={2}>
  <Card title="Built-in Tools" icon="wrench" href="/reference/tools/file-operations">
    40+ tools for file operations, search, execution, agents, and MCP protocol.
  </Card>

  <Card title="Slash Commands" icon="terminal" href="/reference/commands/overview">
    80+ slash commands for session management, configuration, and workflow control.
  </Card>

  <Card title="Configuration" icon="gear" href="/configuration/settings">
    Settings, environment variables, hooks, and the CLAUDE.md memory system.
  </Card>

  <Card title="Analysis Reports" icon="magnifying-glass" href="/reference/analysis/telemetry-privacy">
    Research findings: telemetry, hidden features, remote control, and roadmap.
  </Card>
</CardGroup>

## Key capabilities

<Steps>
  <Step title="Agentic loop">
    Claude Code runs a continuous loop: send a prompt to Claude, receive a response, execute any requested tools, append results, and loop back — until Claude stops requesting tool calls.
  </Step>

  <Step title="Permission system">
    Every tool call passes through a layered permission system: pre-tool hooks, always-allow/deny rules, and interactive prompts. Configure permissions via `settings.json` or CLI flags.
  </Step>

  <Step title="Multi-agent orchestration">
    Spawn sub-agents via `AgentTool` in fork, worktree, or in-process mode. Coordinate teams of agents sharing a task board and message inbox using `TeamCreateTool` and `SendMessageTool`.
  </Step>

  <Step title="MCP integration">
    Connect to any Model Context Protocol server (stdio, SSE, HTTP, WebSocket) to extend Claude Code with custom tools and resources using the standard MCP protocol.
  </Step>
</Steps>

<Note>
  This repository contains decompiled source code for technical research and educational purposes. All source code is copyright Anthropic. Commercial use is prohibited.
</Note>