Command
Get a second opinion from OpenAI Codex and have the codex-advisor subagent check it critically against the code.
1 3d ago A 25 tokens
original MIT
Permission profiles that stop the OpenAI Codex CLI from reading your secrets. The sandbox restricts writes, not reads — these profiles close the gap.
Command
Get a second opinion from OpenAI Codex and have the codex-advisor subagent check it critically against the code.