{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiec2or3dfjmfpsbnc64pcn76sy3dcotv6z4z7fh66mlcxnqqw4g2q",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mm6wquvec7g2"
  },
  "path": "/t/codex-usage-limits-seem-to-be-draining-unusually-fast-since-10-may-2026-even-with-light-gpt-5-3-codex-use-while-the-usage-tracking-ui-also-appears-buggy-or-missing/1380649#post_11",
  "publishedAt": "2026-05-19T07:44:28.000Z",
  "site": "https://community.openai.com",
  "textContent": "I agree with you. And I’d add one more observation from my own experience.\nCodex doesn’t live in one dimension — it lives in three. And the user pays for all three simultaneously without a clear breakdown.\nWhat is officially confirmed by OpenAI:\n**AGENTS.md** is read at the start of every session. Source: OpenAI documentation.\nLarger codebases and longer sessions consume significantly more per message. Source: OpenAI Help Center.\nLarge system files reduce how far a limit lasts. Source: OpenAI documentation.\nWhat OpenAI has never published:\nExactly which files get loaded at session startup beyond **AGENTS.md.**\n_Whether git operations like commit, diff, or push consume tokens.\nWhether reading screenshots or images costs tokens and how much.\nHow many tokens equal one percent of the 5-hour window._\nAnd that silence is the problem. Not the fact that tokens are consumed — **that’s expected.** The problem is that there is no public breakdown. No table. No estimate before a task starts. No receipt after it ends. _The user has no way to plan, predict, or verify what they’re actually paying for._",
  "title": "Codex usage limits seem to be draining unusually fast since 10 May 2026, even with light GPT-5.3 Codex use, while the usage-tracking UI also appears buggy or missing"
}