> ## 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.

# Introduction

> Overview of Claude Code — what it is, what it does, and what you'll find in this research repository.

Claude Code is an AI coding assistant CLI built by Anthropic. It wraps the Claude API in a production-grade agent harness that can read, edit, and execute code across your local filesystem, all from the terminal.

This documentation is based on the decompiled TypeScript source extracted from the published npm package `@anthropic-ai/claude-code` version **2.1.88**. The source is provided strictly for technical research and educational purposes.

<Warning>
  All source code in this repository is the intellectual property of **Anthropic and Claude**. Commercial use is strictly prohibited. This repository exists for research, study, and educational exchange only. If any content infringes your rights, contact the repository owner for immediate removal.
</Warning>

## What Claude Code is

Claude Code is a terminal-native AI agent. You give it a prompt — or open an interactive session — and it uses a built-in tool system to read files, run shell commands, search codebases, call external APIs, and write changes back to disk. Everything runs locally, coordinated by the agent loop in `query.ts`.

The compiled CLI ships as a single 12 MB `cli.js` bundle requiring only Node.js >= 18. The `src/` directory in this repository contains the unbundled TypeScript source extracted from the npm tarball.

## Repository stats

| Item                          | Count                               |
| ----------------------------- | ----------------------------------- |
| Source files (`.ts` / `.tsx`) | \~1,884                             |
| Lines of code                 | \~512,664                           |
| Largest single file           | `query.ts` (\~785 KB)               |
| Built-in tools                | 40+                                 |
| Slash commands                | 80+                                 |
| npm dependencies              | \~192 packages                      |
| Runtime                       | Node.js >= 18 (compiled Bun bundle) |

## Major capabilities

<CardGroup cols={2}>
  <Card title="Agent loop" icon="arrows-rotate" href="/concepts/agent-loop">
    A `while`-loop that calls the Claude API, checks `stop_reason`, executes tools, appends results, and repeats — wrapped with streaming, compaction, and permission checks.
  </Card>

  <Card title="40+ built-in tools" icon="wrench" href="/reference/tools/file-operations">
    File read/write/edit, glob, grep, bash execution, web fetch, web search, MCP protocol, sub-agent spawning, todo management, and more.
  </Card>

  <Card title="80+ slash commands" icon="terminal" href="/reference/commands/overview">
    In-session commands for authentication, memory, configuration, MCP servers, context compaction, plan mode, session resumption, and code review.
  </Card>

  <Card title="Multi-agent system" icon="network-wired" href="/architecture/multi-agent">
    Spawn sub-agents as child processes or in-process teammates. Coordinate work via a shared task board and message inbox.
  </Card>

  <Card title="MCP integration" icon="plug" href="/architecture/mcp-integration">
    Connect to external MCP servers over stdio, SSE, HTTP, or WebSocket. Tools are registered dynamically under the `mcp__<server>__<tool>` naming convention.
  </Card>

  <Card title="Session persistence" icon="database" href="/architecture/session-persistence">
    Every conversation is appended to a JSONL transcript under `~/.claude/projects/`. Resume any session with `--continue` or `--resume <id>`.
  </Card>

  <Card title="Permission model" icon="shield-halved" href="/concepts/permission-model">
    Three-layer authorization: pre-tool hooks → allow/deny rules → interactive prompt. Each tool reports whether it is read-only, destructive, or concurrency-safe.
  </Card>

  <Card title="Context management" icon="compress" href="/concepts/context-management">
    Three compression strategies — `autoCompact`, `snipCompact`, and `contextCollapse` — keep long sessions within the model's context window.
  </Card>
</CardGroup>

## Repository purpose

This repository contains the decompiled TypeScript source of `@anthropic-ai/claude-code` v2.1.88, published to npm as a 12 MB bundled `cli.js`. The `src/` directory was extracted from the npm tarball for research purposes.

The source is **not directly compilable** from this repository alone. 108 feature-gated internal modules were dead-code-eliminated by Bun at Anthropic's build time and are not recoverable from any published artifact. See [Installation](/installation) for what is and isn't possible when building from source.

The repository also includes [deep analysis reports](/reference/analysis/telemetry-privacy) covering telemetry, hidden features, undercover mode, remote control mechanisms, and the future roadmap derived from reading the source.