Luna Subagents Save Usage Limits in Codex Pro

Melvin Vivas · X post · 2026-09-08 · Open on X

Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate

Summary

A short remark that delegating work to cheaper Luna subagents kept Astra from burning through all of his Codex Pro limits.

Key points

• Handing subtasks to a cheaper subagent model cuts usage from the expensive orchestrator model.
• Astra on its own uses Codex Pro limits very quickly.

Resources mentioned

• GPT 5.6 Luna · tool · openai.com · paid
  The OpenAI model used inside Codex for the demo. The transcript gives the variant name as 'Soul', which is unclear.
  Also in: Set Codex subagent model and reasoning to save usage limits (Melvin Vivas on X · notes), Use GPT-5.6 Luna in Codex for Terminal Tasks (Melvin Vivas on X · notes), Match Reasoning Effort to Task Length in Codex (Astra/Sol) (Melvin Vivas on X · notes), Run Coworker desktop agents cheaply with GPT-5.6 Luna on OpenRouter (Melvin Vivas on X · notes) and 24 more

Try this

• Use a cheaper model for subagents to stretch your usage limits.