{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreihsorrwvzpafxg22ico4u2r766ico2r2kv6q4o35n2ss55xzto6mu",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mnubtcjuu3w2"
  },
  "path": "/t/using-chatgpt-for-planning-vs-codex/1382876#post_15",
  "publishedAt": "2026-06-09T12:06:44.000Z",
  "site": "https://community.openai.com",
  "textContent": "Well, generally, all your markdown files can go into one file as long as you label each section cleanly for Chatgpt and name it something like codex markdowns\n\nThe pain in the butt is having to update them manually but you can carefully instruct codex to produce the new markdowns in the format i just suggested for you as a text doc it supplies to you in it’s report, to cut down on the low-level click-soup that part of the flow demands.\n\nYou want your codex to leave itself docs and lint pretty often, having a master list of those docs, their path, so that chatgpt can know which docs to invoke in a new session for codex.\n\nI do a lot of screenshots and webpage saves when codex is working on websites, which get uploaded to ChatGPT in a prompt so that it can see better. And generally, that’s for an area of work pertaining to the most recent codex pass, or as a reference point to plan changes from prior to using codex for a goal…\n\nBasically, like what this thread is about, the planning stage with ChatGPT… can happen anywhere with a couple of screenshots once your Chatgpt has enough of an understanding of the project…\n\nIt also has pretty decent memory within project sessions so it starts to tune the project more to your goals with Codex.\n\nThe most important thing I can think of in this sort of flow is a ChatGPT rules file about how to prompt Codex…\n\nNew sessions have to have a lot more constraints in prompts,\nOlder and very focused codex sessions don’t need all the repeated constraints every prompt.\n\nThat’s the part that I think having other people’s experience and eyes will help us out with… It’s the part that I just default to and let ChatGPT treat each prompt constraint heavily.\n\nYou can also stick some of your actual repo files into your project container in ChatGPT (not in a zip) as then chatgpt can prompt based on your file needs, but also track where Codex is slipping up faster than you probably could reading all the reports on your own.\n\nI leave my codex pet, hovering on the computer, when I’m alerted that a pass is finished, I click it, copy the report, and ChatGPT is reading it before I’ve even scanned it..\nThen I go back to whatever i was doing when chatgpt has supplied the next prompt, and I’ve fired it into codex.\n**\nDon’t skip on scanning your ChatGPT analysis of those reports.\nThat’s the only way you’re going to know if you need to scan Codex’s report as well and make a decision about something.\nSometimes chatgpt will want you to provide screenshots to help it see the work**…\n\nDon’t let chatgpt automate every visual inspection with codex unless you’re willing to pay for those extra credits.**\n**\n\nIf you get too lazy in this flow, the bots will spiral out onto ‘safe passes’ and get a lot of nothing done…\n\nIt’s more effective long-term than just a full plan + codex prompt from ChatGPT.\n\nMy favorite bonus is I can recalibrate, replan with ChatGPT in the middle parts of a project and it’s not completely clueless about what’s going on in the repo… It makes those plans stick better imho.\n\nso yes there’s a lot of manual updating depending on the scope of your work, but it’s easier and cheaper than having codex fix major errors from a wayward pass.\n\nThose errors can still occur, on occasion, but chatgpt is the better part of fixing them…",
  "title": "Using ChatGPT for Planning vs Codex?"
}