{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreievvhkmzi7gk4hwtbzyxcgr5ushymlrnvaxd6uq4otcobfrnz5vi4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mlnhrfyyike2"
  },
  "path": "/t/how-do-you-guys-work-with-codex-in-auto-approval-mode/1380717#post_1",
  "publishedAt": "2026-05-12T08:57:10.000Z",
  "site": "https://community.openai.com",
  "textContent": "Hi everyone, quick question.\n\nI’m using Codex in allowed repositories with permissions set to auto-approve. I’ve noticed that when Codex needs to run CLI commands or similar actions, it often first hits a sandbox permission error, then retries with an elevated permission request, gets auto-approved, and only then runs the command.\n\nIs there a way to configure Codex so that, when auto-approval is enabled, it requests elevated permissions upfront for commands that need them?\n\nI tried adding this to the instructions, but the results are inconsistent and the logic gets messy. Maybe I’m missing a setting or a better approach.",
  "title": "How do you guys work with Codex in auto-approval mode?"
}