{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreidlwpgywvgtl25ngjvyoi5rkdpwnc43ixqocumwevhuveartnocqi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mjbyqbpmhv22"
  },
  "path": "/t/add-persistent-user-preference-recall-across-codex-cli-conversations/1378787#post_3",
  "publishedAt": "2026-04-12T07:24:54.000Z",
  "site": "https://community.openai.com",
  "textContent": "`AGENTS.md` helps, but it is not the same thing as what I’m asking for.\n\nMy request is about persistent preference recall across new Codex CLI conversations, especially for user-level habits that repeat across repos and sessions. An `AGENTS.md` file is repo-scoped and project-specific. That makes it useful for things like build commands, test workflow, architecture constraints, and repo conventions, but it is a weaker fit for personal preferences such as:\n\n  * my preferred commit message style\n  * my default PR description structure\n  * my preferred response format for recurring tasks\n\n\n\nThere are a few reasons I see them as different:\n\n  1. `AGENTS.md` is tied to a repository, while many preferences are tied to the user.\n  2. It requires creating and maintaining files in each repo, even when the preference is global.\n  3. It is better for project instructions than for lightweight personal defaults.\n  4. It does not really solve continuity across unrelated projects or fresh workspaces.\n\n\n\nSo yes, `AGENTS.md` is a reasonable workaround today, and I would probably use it for repo-level conventions. But I still think there is a product gap: Codex CLI should ideally support explicit, persistent user preferences separately from repo instructions.\n\nA strong model would be:\n\n  * `AGENTS.md` for repository or team rules\n  * persistent profile/preferences for user-level defaults\n  * per-chat overrides when needed\n\n\n\nThat separation would be cleaner and closer to how engineers actually work.",
  "title": "Add persistent user preference recall across Codex CLI conversations"
}