by zhjai · Codex Skill · ★ 26
Agent Arena Evidence-first multi-agent debate for Claude Code × Codex — a second opinion that survives cross-examination. English · 中文 Get a real second opinion on high-stakes code and architecture decisions. Agent Arena makes Codex and Claude Code analyze your problem independently, critique each other's reasoning, verify evidence, and preserve dissent — instead of one agent confidently giving you one answer. Best for: architecture decisions · implementation plan review · PR review before merge · bug root-cause analysis · RAG claim verification
| Stars | 26 |
| Forks | 5 |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 67.4012709088015/100 |
| Last Updated | 2026-06-23 |
| Created | 2026-05-22 |
| Platforms | claude-code, codex |
| Est. Tokens | ~20k |
Explore other popular codex skill tools:
agent-arena is Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to independently review, red-team & judge high-stakes code and architecture decision. It is categorized as a Codex Skill with 26 GitHub stars.
You can find installation instructions and usage details in the agent-arena GitHub repository at github.com/zhjai/agent-arena. The project has 26 stars and 5 forks, indicating an active community.
agent-arena is released under the MIT license, making it free to use and modify according to the license terms.