3 projects
piensalo
A cognitive operating layer for AI models: bounded loops, observable-defect inspection, targeted repair, and layered verification.
rulebench
Does your CLAUDE.md actually do anything? Trap-test your agent rules in isolated sessions and get honest deltas.
agent-zero-trust
Zero-trust repo intake for AI coding agents: scan the instruction environment before Claude Code, Cursor, Codex, or Gemini touches a repo.
