{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreifz25ozi5aponqetgzzrgllokbixmdidromowf3cedkcyakxujkl4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mp6hxtt52rv2"
  },
  "path": "/t/add-persistent-user-preference-recall-across-codex-cli-conversations/1378787#post_18",
  "publishedAt": "2026-06-26T07:26:47.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "@VeitB"
  ],
  "textContent": "@VeitB I believe that’s a helpful clarification, especially the point about multiple AGENTS.md files in a project.\n\nI agree the master-project approach is a reasonable workaround for some workflows, but I think the distinction from earlier still matters: it helps with reuse of preferences, while a central preference layer would solve ownership, precedence, and lifecycle more explicitly.\n\nThe nearest-AGENTS.md behavior is a good example of scoped control done well. In a monorepo, it gives the repo a way to say: “these rules apply here, not everywhere.” This maps neatly onto the repo/user/chat model: repo instructions can be local and nested, user defaults should travel across repos, and chat overrides should stay temporary.\n\nSo I’d see these as complementary rather than competing mechanisms:\n\n  * nested AGENTS.md for local codebase/module behavior\n  * user defaults for cross-project working preferences\n  * chat overrides for temporary exceptions\n\n\n\nThe missing piece is making those layers visible and enforceable enough that users can trust which one is active at any moment, without a workaround blurring ownership of the context.",
  "title": "Add persistent user preference recall across Codex CLI conversations"
}