OpenAI published how to prompt GPT-6 Astra and clean up your skills and AGENTS.md. Here's what to steal.
Some of the instructions you wrote for older models are now making Astra worse. OpenAI says so in their own words. This page takes their guidance, shows you the exact lines, and turns each one into something you can paste into Codex today.
Quotes are from OpenAI's developer blog post "Rethinking skills and prompts for GPT-6 Astra" and the GPT-6 Astra model guidance page. Everything else is our reading of them.
Drop your email and the whole guide unlocks right here, with copy buttons on every prompt and a Markdown download. You'll also get one practical AI system most weeks.
OpenAI's opening line says it plainly: "With more capable models, what used to require a lot of handholding and scaffolding no longer does." The rest of the guidance is about removing scaffolding, and adding a few precise lines in its place.
Two documents. They overlap, and together they are what this page decodes.
The short essay about cleaning house: skill descriptions, progressive disclosure, AGENTS.md, decision boundaries and persistence. Ends with the suggestion to have Astra audit your setup.
The reference page with the actual prompt snippets: initiative and follow-through, instruction following, writing style, subagent delegation, testing and verification.
"GPT-6 Astra is stronger at general instruction following than our previous models, giving you greater control over its behavior. It can be more sensitive to instructions contained in skills and other files, such as AGENTS.md. We strongly recommend auditing skills and other files accessible to your model for instructions that could influence its behavior."
That sensitivity is the whole story. Astra follows your instructions more literally than GPT-5.6 Sol did. So a rule you added to stop an older model going too far now stops Astra from finishing.
You should be approving something you can see, not a plan.
"Prompt the model to ask for approval only after preparing a concrete, reviewable result. This avoids blocking the task before the model has done the work it can, and often leads to quicker task completion."
OpenAI's snippet for this goes in your AGENTS.md or system instructions. It's the one that stops Astra from pausing at "shall I proceed?" before it has done anything.
Notice the last line. Publishing still needs your approval. Everything reversible before it doesn't. That is the split the whole guide keeps coming back to.
There is a companion snippet for the "can you" problem, where Astra answers "yes I can" and stops:
Fix the conflicting rule instead of typing "keep going" for the tenth time.
"Unclear or conflicting guidance in a skill file may cause the model to pause and block work early. Make the priority of user instructions and skills explicit."
"Asking the model to identify the skill and instruction that caused it to pause or change direction can also be effective in providing transparency into model behavior."
Two lines from OpenAI do this. The first sets the pecking order. The second makes Astra show its working when it stops.
Why it works: OpenAI says to use this "to find silent and conflicting guidance when your application loads many skills and instruction files such as AGENTS.md." Once Astra quotes the rule, you delete or rewrite the rule. The stall doesn't come back.
Left alone, Astra formats everything. Lists, tables, headers, a summary at the end.
"The model tends toward detailed, formatted responses and may use recurring phrases across sessions. Specify the writing style and structure your application needs."
OpenAI also published a list of the words and patterns it wants gone. Worth pasting as-is if Astra writes anything a human reads.
For technical work, OpenAI adds one more line: "Use plain language over jargon, and reference technical details only to the degree that it helps illustrate an idea or your work to the user."
Changing a button label shouldn't trigger endless rounds of testing.
"Previous models needed encouragement to run tests and check their work. GPT-6 Astra does that on its own, so the same instructions can lead to unnecessary testing."
The flip side: if there is a test suite you know is safe, tell Astra it's allowed to run it without checking in. OpenAI's example for an AGENTS.md line:
Delete the old line. If your AGENTS.md still says "always run all tests" from the GPT-5 days, that rule is now doing the opposite of what you wanted.
Before you download another massive prompt pack, get the model to check the instructions you already have.
"A new model is a good opportunity to clean your house, but you don't need to review everything manually: ask GPT-6 Astra to do an audit based on what was discussed in this article, then go build something you wouldn't have attempted before!"
OpenAI doesn't publish the audit prompt itself. This is ours, built from the checklist in their article. Paste it in the root of the project you use most.
What you should get back: a file-by-file list of lines to delete, lines to shorten, and lines to add, with nothing changed yet. Approve the ones you agree with. Then let it edit.
Also from OpenAI: Codex has an official $openai-docs skill that can "apply the recommended changes in this guide" for API migrations. Our audit prompt is for your instructions, which that skill doesn't cover.
The guidance names three homes for instructions: skills, AGENTS.md and the task prompt. Put each change where it will apply at the right moment, and nowhere else.
| Change | Put it in | Because |
|---|---|---|
| 1 Approval after the work | AGENTS.md | You want it every session. The one-line version ("show me the preview, ask before publishing") goes in the task prompt when a task ends in a publish. |
| 2 Name the file, quote the rule | AGENTS.md | Stalls happen anywhere. You want the explanation without asking for it. |
| 3 Writing style | AGENTS.md for repos that produce copy; task prompt otherwise | A coding repo doesn't need prose rules on every task. A content repo does. |
| 4 Testing calibrated to the change | AGENTS.md | Replace the old "always run all tests" line rather than adding next to it. |
| 5 The audit | Task prompt, once per project | It's a job, not a standing rule. Re-run it when you switch models. |
Keep AGENTS.md short. OpenAI: "Because AGENTS.md applies whenever the model works in your repository, you should frequently revisit each instruction and ask yourself whether it's still needed."
OpenAI: "many descriptions are far too long, and when you add too many skills, Codex starts shortening their descriptions to fit. The model ends up seeing less of each description, making it harder to know which skill to pick."
Their rule for multi-workflow skills: "make the root document a minimal router that points to supporting docs and scripts." And a warning about recipes: "overly specific guidance can now hinder results where it previously helped."
OpenAI: "Requiring a stack of docs or a full repo map before every edit is excessive for a typo fix. GPT-6 Astra can work out what it needs to read without being pushed to review the whole project before every change."
OpenAI: "If you stated boundaries previously because you wanted to prevent other models from going too far and you're now switching to GPT-6 Astra, consider updating that language: Astra could take it too seriously and may stop work where you'd actually be happy for it to continue."
OpenAI: "GPT-6 Astra can feel more tentative about when to stop. It may reach a first implementation and come back for your review while there's still work to do." Their fix: "If the task includes getting the implementation running, inspecting the result, and fixing what fails, make that part of the request."
If you run subagents: OpenAI also notes Astra "may delegate less often than desired" and gives a one-line prompt for it: "If at any point you can parallelize work by delegating tasks to another agent (no matter if you are the root or subagent), you should do so using collaboration tools if it could save time or improve quality."
| Problem | What to try |
|---|---|
| Still asks "shall I proceed?" before doing anything | Check for an older "always ask before" rule in AGENTS.md or a skill. Use change 2 to make Astra quote it, then delete it. OpenAI's own troubleshooting note points at the initiative snippet in change 1. |
| Stops after the first implementation | Put "run it, inspect the result, fix what fails" in the task itself. OpenAI: "A requirement to stop for review after the first implementation will pull the model toward an earlier stopping point." |
| Runs a huge test pass for a tiny change | Find and remove the old "always run all tests" line. Add the change 4 snippet in its place, not beside it. |
| Answers in tables and bullet lists when you wanted prose | Paste the prose snippet from change 3 into the task prompt. If it persists across sessions, move it to AGENTS.md. |
| Loads a skill that has nothing to do with the task | The description is too broad. Rewrite it to name the specific workflow, the way OpenAI's migration example does. |
| The audit finds nothing | Ask it to list every instruction file it read. If it skipped nested AGENTS.md files or skill sub-docs, point it at them and run again. |
OpenAI updates these pages. If a snippet here differs from the live page, use the live page.
This is one build. AI Systems Lab is where the rest live: practical AI systems you can run in your own business.