Pinned Loading

1. socratic socratic Public

   self questioning skill for agents , claude code , codex etc

   107 17

2. detonate detonate Public

   Run untrusted AI tools in a sandbox and report what they actually do, not what their manifest claims.

   Go 10

3. asrt-bench asrt-bench Public

   Fire a frozen attack pack at your AI agent, verify what lands, and diff safety across versions.

   Python 1

4. reconRelate reconRelate Public

   ReconRelate is a CLI-first reconnaissance relationship mapper.

   Python 1