Wish: Automatic Model Selection for Codex Subagents
Melvin Vivas · X post · 2026-09-02 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator wants Codex to pick a model for each subagent automatically based on the task. Judging each task and choosing a model by hand adds mental load. The idea behind it is model routing in multi-agent systems.
Key points
- Choosing a model for each subagent task by hand adds mental load.
- Routing tasks to models automatically by difficulty could cut both effort and cost.
Resources mentioned
- OpenAI Codex · tool · openai.com · paid · recommended by both Bashiri Smith & Melvin Vivas
OpenAI's coding agent. In the diagram it writes code, fixes review findings and drives the build loop. The creator also used it to make this video.
Also in: Developers moving from ChatGPT/Codex to Claude (Melvin Vivas on X · notes), Creator Opinion: Codex Is Still the Best at Computer Use (Melvin Vivas on X · notes), OpenAI Codex Ambassador applications are open (Melvin Vivas on X · notes), GPT-Live-1.1: Multilingual Voice Update for ChatGPT and Codex (Melvin Vivas on X · notes) and 264 more
Try this
- Build a router that judges how hard a subagent task is and picks a suitable model automatically.
More in AI Agents, Tool Use & MCP
- Docs7: Serving Agent-Readable Documentation to Coding Agents via MCP
- ChatGPT Work: A Cloud Agent Built on the Codex Harness That Books Travel
- Share Pi Agent Traces on Hugging Face with pi-share-hf
- JSONL Viewer v1.3.0: View Codex, Claude Code, Pi and Hermes Agent Traces
- Assign Different Models per Role in ohmypi (Like Hermes)
- Coworker v0.4.0: Desktop AI Agent App Adds Browser Use