Best Practices for Codex Let’s build a community-driven collection of practical tips to maximize productivity and efficiency when using OpenAI’s Codex. Share your favorite insights, and let’s improve our skills together! Initial tips: Choosing the Right Model: Stick to GPT-5.2-Codex medium/hi…

im mostly testing changes on a test suite i have for my software, i have successfully closed the loop and also with greptile reviews in my git repo when i do pr’s (thanks to th3o from t3)

While skills are designed to activate automatically, they can also be invoked on demand. Why would you want that workflow? For example: A common need across many AI tools is to create a plan that is materialized as a Markdown document and saved locally in some temp directory with the exact locati…

Still need to update the main list but the team is really pushing to get everyone on board with Codex. Learning opportunity at 2026-02-05T19:00:00Z (UTC) [image] OpenAI Developers @OpenAIDevs 🎙️ Let’s talk about your new Codex app workflow Got questions about building skills, setting …

Sorry. No Mac walled garden here to run their app. For next time: cross-platform, open source, interpreted, inspectable.

I’ve confirmed with the team that Linux and Windows versions are on the roadmap. No need to further derail the topic.

“BREAKING NEWS: gpt-5.3-codex is out! Upgrade to 0.98.0 to try it.” nit: gpt-5.3-codex announcement (#10775) committed 07:17PM - 05 Feb 26 UTC (UTC) [image] jif-oai …

@EricGT , circling back to the best practices discussion. You mentioned aiming for 100 percent code coverage. Do you mainly use this as a way to help Codex produce better and faster results, or do you see it as more general guidance for pairing with an AI while coding? From my perspective, defining …

[image] VeitB: Do you mainly use this as a way to help Codex produce better and faster results, or do you see it as more general guidance for pairing with an AI while coding? General guidance for pairing with an AI while coding is closer. In some situations, I think of a strong AI coding mod…

I think it’s a good approach to leverage tests for better results by building the validation loop at the very beginning of a task. Codex can then iterate over the results until the desired outcome is achieved. Designing the tests to be meaningful then becomes a necessary part of the planning phase.

One thing I am actively experimenting with and testing is something called “Tiger Style” programming which was created by the devs of the Tiger Beetle database. It’s a very strict and safe way to ensure that everything works and it is a technique I have never seen anyone else do in my over 11+ years…

Tips and Tricks for using Codex

Codex

EricGT March 3, 2026, 10:59am 21

Check the OpenAI Developer blog

Limited to two replies in a row so appending to second reply.

Make use the slash command /goal

Topic		Replies	Views
Can Codex Low match Medium on easy tasks? Codex gpt-5-codex	6	779	February 2, 2026
How can we clearly see token usage per Codex conversation/task, especially in Codex web? Codex	10	17480	June 24, 2026
When vibe coding turns into an unfixable mess Codex	21	1757	March 11, 2026
How to achieve greater code refactoring automation? Codex CLI chatgpt	15	337	July 6, 2026
Feedback from a remote Codex helper prototype: long-session performance, durable queue, and MCP process reuse Codex codex , codex-app , codex-desktop-app	20	535	May 21, 2026

Tips and Tricks for using Codex

Related topics