loaditout.ai
SkillsPacksTrendingLeaderboardAPI DocsBlogSubmitRequestsCompareAgentsXPrivacyDisclaimer
{}loaditout.ai
Skills & MCPPacksBlog

claude-code-analysis

MCP Tool

thtskaran/claude-code-analysis

We read all 512K lines of Claude Code's accidentally exposed source. 82 docs, 15 diagrams, every subsystem mapped — from the hidden YOLO safety classifier to multi-agent swarms.

Install

$ npx loaditout add thtskaran/claude-code-analysis

Platform-specific configuration:

.claude/settings.json
{
  "mcpServers": {
    "claude-code-analysis": {
      "command": "npx",
      "args": [
        "-y",
        "claude-code-analysis"
      ]
    }
  }
}

Add the config above to .claude/settings.json under the mcpServers key.

About

How Claude Code Actually Works

> On March 31, 2026, a .map file in Claude Code's npm package accidentally exposed the full TypeScript source. We read all 512,000 lines. Here's everything we found.

[](https://github.com/instructkr/claude-code/stargazers)

---

The Stuff They Don't Tell You

Claude Code isn't just a chat-in-terminal wrapper. It's a 1,902-file TypeScript monolith with its own React rendering engine, a multi-agent swarm system, a two-stage AI safety classifier, and 88 hidden feature flags — many for features that don't exist yet.

Here are some of the things we found buried in the source:

There's a hidden AI that judges every command you run. Before Claude Code executes a tool call, a separate classifier called "YOLO" runs a two-stage evaluation. Stage 1 is a fast 64-token scan. If it's suspicious, Stage 2 does a full 4,096-token reasoning pass to decide: allow, deny, or ask the user. Temperature is zero. It errs on the side of blocking. → Full breakdown

Your conversations get secretly compressed. When context pressure exceeds 93%, Claude Code runs one of six compaction strategies — from lightweight microcompaction (clearing old tool results) to spawning an entire forked subprocess that summarizes your conversation into a 9-section format. You never see this happen. → How compaction works

It ships an entire React rendering engine for the terminal. Not a simple TUI library. A custom React Fiber reconciler, a Yoga flex-layout engine, a screen buffer with packed Int32Arrays, and a frame-diffing system that reduces terminal output from 10KB to 50 bytes on idle scroll. 7,743 lines of rendering code. → Ink pipeline deep dive

Multi-agent "swarms" communicate through files on disk. When Claude Code spawns parallel agents, they coordinate via a file-based mailbox system at `~/.

Tags

agentic-aiai-agentsanthropicarchitecture-analysisclaude-codecli-toolsllm-internalsmcpreact-inkreverse-engineeringsecurity-researchtypescript

Reviews

Loading reviews...

Quality Signals

7
Stars
0
Installs
Last updated15 days ago
Security: AREADME

Safety

Risk Levelmedium
Data Access
read
Network Accessnone

Details

Sourcegithub-crawl
Last commit4/2/2026
View on GitHub→

Embed Badge

[![Loaditout](https://loaditout.ai/api/badge/thtskaran/claude-code-analysis)](https://loaditout.ai/skills/thtskaran/claude-code-analysis)