You can also create a skill for reviewing (which calls gemini/codex as a command line tool) and set instructions on how and when to use. Very flexible.
Agent-to-agent pair programming
31–40 of 78 posts
Re: Agent-to-agent pair programming
#32The circle of slop.
Re: Agent-to-agent pair programming
#33If this approach turns out to be valuable, it's unlikely that it has anything to do with having multiple actual agents, but rather that it's valuable to have 2 configurations (system prompt, model, temp, context pruning, toolset etc.) of inside the same agent being swapped back and forth.
Re: Agent-to-agent pair programming
#34[flagged]
Re: Agent-to-agent pair programming
#35I’m curious whether anyone has measured this systematically. Right now most of the evidence for multi-agent setups still feels anecdotal.
And expensive, exactly the way a pay per use product would push its customers…
“It’s not working well enough!” We tell them. They respond with “Have you tried using it more?”
Re: Agent-to-agent pair programming
#36The PLAN.md question is the one worth pulling on. Once the plan lives in git or the PR it's already downstream of intent and whoever defined what to build has already handed off. The harder problem is giving agents access to the original intent, not just the implementation plan derived from it. When there's drift between what was planned and what got built, a git-resident PLAN.md makes it hard to trace back to why the decision was made in the first place.
Re: Agent-to-agent pair programming
#37[dead]
Re: Agent-to-agent pair programming
#38[dead]
Re: Agent-to-agent pair programming
#39Nice - I do something similar in a semi manual way. I do find Codex very good at reviewing work marked as completed by Claude, especially when I get Claude to write up its work with a why,where & how doc. It’s very rare Claude has fully completed the task successfully and Codex doesn’t find issues.
Claude is also good at that. I made a habit of asking "are you sure?" after a complex task. It usually says it overlooked something.
I find both to be true. I use Claude for most of the implementation, and Codex always catches mistakes. Always. But both of them benefit from being asked if they’re sure they did everything.
Re: Agent-to-agent pair programming
#40I’m curious whether anyone has measured this systematically. Right now most of the evidence for multi-agent setups still feels anecdotal.
And expensive, exactly the way a pay per use product would push its customers… “It’s not working well enough!” We tell them. They respond with “Have you tried using it more?”
Haha yeah... Wait until they start jacking up the subscription prices