Uncovering hidden capabilities in Claude Code

Analysis of Claude Code version 2.1.87’s source code reveals several undocumented features. A key finding is the YOLO Classifier permission system. It allows describing environments in plain text so the AI understands the security level of operations.
Specialized agents can be built using persistent memory at the user and project levels. A self-learning system was also found: the autoMemory and autoDream functions enable the model to extract knowledge from sessions and consolidate it every 24 hours. This creates a continuous learning loop without overtraining the model.
Up next
Anthropic raises $65B in Series H
Anthropic hits a $965B valuation and $47B in revenue. With this funding, they’re joining the ranks of Microsoft and Google in scale and ambition.
Related stories
- Tokendoctor cut its author’s Claude Code cost 38%
- Claude Code on desktop folds an iPhone Duo to test layouts
- memsaga gives Claude Code’s memory files a git history
- Claude Code 2.1.318: login expiry warning, runner log change
- Intent-lens spells out Claude Code calls before they run
- Codedict cuts Claude Code tokens 63%, but cost only 26%
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

