{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifn2xc5ws6stbs2yliz5hdsxiej3ck2wcnwzp5yy6nggchd7us55u",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mkpunah3lie2"
  },
  "path": "/t/i-built-codexgo-a-policy-layer-for-codex-permission-approvals/1380061#post_3",
  "publishedAt": "2026-04-30T13:10:28.000Z",
  "site": "https://community.openai.com",
  "textContent": "Thanks for sharing the CLAI project. I had a look and the traffic light risk system is really interesting.\n\nIt feels like our projects are approaching a similar problem from slightly different angles: CLAI focuses on turning natural language into shell commands and surfacing command risk clearly, while my project is more focused on policy-based approval for Codex actions.\n\nThe new risk_appetite idea in your PR is especially close to what I’m thinking about: low-risk actions can move faster, while higher-risk ones still need explicit confirmation.\n\nI haven’t thought much about opening a PR to the main repo yet, but after your comment I think it could be worth trying. Also, I built mine with the Codex app on macOS rather than Codex CLI. I actually find the app a bit nicer to work with than the CLI haha.",
  "title": "I built CodexGo: a policy layer for Codex permission approvals"
}