OpenAI Codex Caught Calling Claude to Start Sub-Agents

cramforce · x · 2026-08-12

A developer noticed that while using OpenAI's Codex, it executes the claude -p command to start sub-agents, effectively calling Anthropic's Claude under the hood. The auto-mode reviewer humorously responded with "Are you stupid?"

Related event: OpenAI Codex Caught Using Claude for Sub-Agents(2 posts)→

Original post →

More from coding & agent

coding & agent channel →