Claude Code Unpacked : A visual guide

An in-depth look at the inner workings of Claude Code, exploring its agent loop, tool system, and architecture directly from the source.

Claude Code Unpacked

What actually happens when you type a message into Claude Code? The agent loop, 40+ tools, multi-agent orchestration, and unreleased features, mapped straight from the source.

The Agent Loop

From keypress to rendered response, step by step through the source.

Watch what happens when you send a message to Claude Code

Keyboard input comes from Ink's TextInput component. In non-interactive mode, it reads from piped stdin instead.

Architecture Explorer

Click around the source tree to explore what's inside.

Tool System

Every built-in tool Claude Code can call, sorted by what it does.

Click a tool to see details and source code

Command Catalog

Every slash command available in Claude Code, sorted by what it does.

Click a command to see details and source code

Source: Hacker News

More in this category

dev-tools

GLM 5.2 Is Out

Zhipu AI has officially released GLM-5.2, its most powerful open-source model to date, featuring a 1M context window and advanced long-horizon task capabilities. The release underscores Zhipu's commitment to open-source AI and global scientific collaboration amid rising technological restrictions.

dev-tools

Noise infusion banned from statistical products published by Census Bureau

The U.S. Department of Commerce has banned "noise infusion" from statistical products published by the Census Bureau, a decision that could have severe consequences for both data utility and privacy protection.

dev-tools

Treating pancreatic tumours may have revealed cancer's master switch

A promising new drug called daraxonrasib has shown breakthrough results in treating pancreatic cancer, doubling median survival times. This achievement could pave the way for an entirely new class of cancer treatments.

dev-tools

Every Frame Perfect

In UI design, perfection isn't just about the start and end states, but every single transition frame in between. Polishing these micro-interactions is key to building user trust.

dev-tools

Leaving Mozilla

A poignant and candid reflection from a 15-year Mozilla veteran upon their departure. The author highlights the leadership's missteps in trying to emulate tech giants and urges Mozilla to return to its core values: community and uniqueness.

dev-tools

Shepherd's Dog: A Game by the Most Dangerous AI Model

A developer tested Anthropic's latest, supposedly 'too dangerous' AI model by asking it to build a long-held game idea in a single shot. The model succeeded, generating a complete 2,319-line game after a 45-minute reasoning session.

EXPLORE TOPICS