moudrkat/steeropathy

Agents that talk through model internals — activations & J-space — instead of text. No words pass between them. The lab on top of brainscope + hidden-directions.

1 file for Claude Code: new-experiment .

29Stars on the repository
1Files it configures its agents with
—Tokens loaded in every session
1Agent configured

Skills

These files are moudrkat/steeropathy's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.