# Using Claude Code and Codex to iteratively improve coding plans

DevFeed: [Using Claude Code and Codex to iteratively improve coding plans](<https://devfeed.tech/articles/agent-kombat-25209.md>)

Original publisher: [Read original article](<https://kau.sh/blog/agent-kombat/>)

Author: Kaushik Gopal

Published: 2026-04-25T07:00:00Z

Content type: tutorial

Language: en

Sources: [Kaushik Gopal's Site](<https://devfeed.tech/sources/kaushik-gopal-s-site.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [coding](<https://devfeed.tech/topics/coding.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>)

## AI overview

The article describes Agent Kombat, a workflow in which Claude Code and Codex independently draft plans for the same coding requirement, critique each other's plans, and revise them over several rounds. A separate judge agent may then synthesize the plans or run a focused replay.

## Source excerpt

Most multi-agent coding setups I see today look like task parallelism. You split the work, hand each piece to a different agent, and merge the results at the end. That is useful. I do it too. But I've been trying a different approach and really liking it: Put two agents on the same problem and make them argue constructively before I trust the plan. The manual version is simple: I spin up Claude Code with Opus 4.7 and ask it to draft a plan: my-plan-claude.md. Then I spin up Codex with GPT-5.5 and ask it to draft a plan for the same requirement: my-plan-codex.md. Now the useful part starts... I ask Claude to read the Codex plan, steal whatever is better, update its own plan, and give me a concrete list of deficiencies in the Codex plan. Then I take those deficiencies back to Codex and ask it to do the same thing: read Claude's updated plan, steal the good parts, defend or fix the weak parts, and update my-plan-codex.md. Then back to Claude. I do this about three times. This works annoyingly well. The final plan is usually much better than the first one-shot plan from either model. Each model forces the other one to look at the problem from a slightly different angle. I started calling this Agent Kombat. And because copy-pasting between two terminals gets old fast, I built a small program that runs the loop for me. Agent Kombat Download the script here The loop ## The loop has only a few rules: Both agents start from the same requirement. Each agent writes its own plan before seeing the other plan. Each round, the agent must name what is stronger in the other plan. Each round, the agent must update its own plan. Each round, the agent must list concrete deficiencies in the other plan. After a few rounds, a separate judge (agent) decides whether to synthesize or run one focused replay. The "concrete deficiencies" part does most of the work. If I just ask, "what do you think?", the models get polite. They compliment each other, merge a few phrases, and call it convergence.