{"slug": "quick-impressions-a-week-of-using-codex-more-than-claude", "title": "Quick impressions: A week of using Codex more than Claude", "summary": "A developer's week-long comparison found OpenAI's Codex produced simpler Ruby/Rails code with fewer comments than Anthropic's Claude, but required more explicit instructions and caused a rebase mishap that created a pull request with over 4,000 additions. The user noted Codex felt more technical and faster for main changes, yet Claude was preferred for urgent debugging due to familiarity and better handling of Jira integration.", "body_md": "Some quick and very personal impressions from using Codex more than Claude this week (I will do a full analysis during the weekend hopefully).\n\n(1) While I tried this year to keep Claude and Codex on par, having the same set of plugins/skills and so on, Claude had more skills, as I created skills out of some sessions and not all of them were ported to Codex. Fix for this is simple: Point Codex at the Claude skills folder and ask it to transform them for Claude\n\n(2) When I was in a rush (like debugging something that felt urgent), I still opened Claude as somehow I felt more at home with it. I am not saying it was better, but it was familiar, and when debugging, using tools that I know is important.\n\n(3) Changes created by Codex had fewer comments in Ruby/Ruby on Rails code. I liked that a lot, and I will soon share some experiments I ran on this.\n\n(4) The output of the Codex agent harness is much more “technical” than the one from Claude. Claude feels more like your colleague in a Tuple session writing to you while Codex feels more like a version of Data from Star Trek.\n\n(5) I want to open many more sessions of Codex and keep them focused instead of a big session of Claude as I was doing before. This may not be specific to Codex, but I noticed it while working with Codex.\n\n(6) It feels to me that Codex does changes faster than Claude. But after making the main changes, it took a lot to finish the pull request: rerunning many tests, review, and so on. I like the thoroughness of this, but in the end, there was no win in terms of time difference.\n\n(7) It felt to me that Codex created a much simpler solution in terms of code architecture than Claude. Claude usually goes on to create a lot of things: abstractions, concepts, Sorbet signatures, type aliases, and so on. Codex was a bit more contained and created less. This week I also tested an improved flow of `code research -> design change -> review change -> implement -> verify`\n\n. But I made both of them implement the same requirement using the same documents, and Claude’s code was a bit more complex but handled cases.\n\n(8) Codex also made some mistakes. Claude could understand my intention to branch out from other work and keep them in sync. Codex did some nasty things like `branch A targets branch B that targets main,`\n\nand when I asked it to rebase, it rebased with `main,`\n\nwhich created some PR with 4000+ additions. I had to be explicit and ask it to rebase only with the target.\n\n(9) For Codex, working with Jira and Atlassian was a hassle in my environment where I use the CLI tool and not the MCP. It opened JIRA to prompt me to log in, then switched to the CLI, then back to the browser. In this case, Claude was much more eager to try to get what I want and to do it the way I want it done, based on previous sessions.\n\n(10) Working with MCPs, I like the Codex CLI approach more, where it asks me to execute `codex mcp login`\n\nand every time it opens the right authentication and authorization flow. Claude sometimes tries to run it automatically in a turn, and it can get stuck.\n\nI think the main difference I feel between Claude and Codex is that Claude tries to go above and beyond what is asked and guess what you might want and then directly do it, while Codex is more like a companion that does what you tell it but will not overdo it. It will stop at the first sign that it might be done.", "url": "https://wpnews.pro/news/quick-impressions-a-week-of-using-codex-more-than-claude", "canonical_source": "https://allaboutcoding.ghinda.com/a-week-of-using-codex-more-than-claude/", "published_at": "2026-08-21 19:51:48+00:00", "updated_at": "2026-08-21 20:15:01.835095+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "generative-ai", "artificial-intelligence"], "entities": ["OpenAI", "Anthropic", "Codex", "Claude", "Jira", "Atlassian", "Ruby on Rails", "MCP"], "alternates": {"html": "https://wpnews.pro/news/quick-impressions-a-week-of-using-codex-more-than-claude", "markdown": "https://wpnews.pro/news/quick-impressions-a-week-of-using-codex-more-than-claude.md", "text": "https://wpnews.pro/news/quick-impressions-a-week-of-using-codex-more-than-claude.txt", "jsonld": "https://wpnews.pro/news/quick-impressions-a-week-of-using-codex-more-than-claude.jsonld"}}