{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreieam5vw2bmjojhfzsldf6dvzowadoy5t7vlreumkga5snzaffpahq",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mo5pz6ew3be2"
},
"path": "/t/how-to-stop-codex-from-rushing-fixes/1382830?page=3#post_47",
"publishedAt": "2026-06-13T07:18:32.000Z",
"site": "https://community.openai.com",
"textContent": "mgm2:\n\n> it claimed to have found the root cause but failed to fix it, and then it became completely reckless\n\nIt sounds like a problem with AGENTS.md. Also, you might want to add a layer of more detailed planning documents so it would be like this: ChatGPT internal planning tool > detailed external template-driven detailed plan/TODOs > execution of the detailed plan/TODOs.",
"title": "How to stop Codex from rushing fixes?"
}