Ask HN: Are you using an agent orchestrator to write code?

Re:Ask HN: Are you using an agent orchestrator to write code? by petesergeant on Friday February 13, 2026 @12:26AM (#46999229)

"Claude writes, Codex reviews" has shown huge promise as a pattern for me, so I wrote a Dockerfile and some instructions on how to make that happen for agents, and ended up with https://github.com/pjlsergeant/moarcode

I am spending most of my day in this harness. It has rough edges for sure, but it means I trust the code coming out much more than I did just Claude.

[ Parent | on HN ]

Re:Ask HN: Are you using an agent orchestrator to write code? by joshuaisaact on Friday February 13, 2026 @12:48AM (#46999350)

I don't think you need two separate models for this - I get similarly good results re-prompting with Claude. Well, not re-prompting, I just have a skill that wipes the context then gets Claude to review the current PR and make improvements before I review it.

[ Parent | on HN ]

Re:Ask HN: Are you using an agent orchestrator to write code? by neumann on Friday February 13, 2026 @12:47AM (#46999340)

I tried to opposite because claude was not coding as well as codex some additional modules for my codebase and codex could. Then I tried to get claude to read and critique and it got so many fundamentals wrong I was wondering if I am using the wrong model.

[ Parent | on HN ]