All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

Undocumented Claude Code Features Revealed Through Source Code Analysis

By

André Figueira

3d ago· 14 min readenInsight

Summary

An in-depth technical analysis of the Claude Code source code revealing numerous undocumented configuration features. Key findings include the "YOLO Classifier" auto-mode permission system that accepts plain English environment descriptions, hook fields for rewriting commands mid-flight, persistent agent memory, auto-mode rules, and self-improving dream loops. The article provides copy-paste ready examples for all features discovered in the publicly distributed npm package.

Key quotes

· 3 pulled
Claude Code's auto-mode permission system is internally called the 'YOLO Classifier.' That's the actual variable name in yoloClassifier.ts.
This isn't in any documentation. It's one of dozens of undocumented capabilities buried in the Claude Code source code.
You can configure it with plain English descriptions of your environment, things like 'this is a staging server, destructive operations are acceptable,' that the classifier reads to decide what's safe to auto-approve.
Snippet from the RSS feed
Hook fields that rewrite commands mid-flight, persistent agent memory, auto-mode rules in plain English, self-improving dream loops, and every example is copy-paste ready.

You might also wanna read