Codex Orchestrator/Subagent Setup: Astra (medium) + Luna (max)

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

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

Summary

A real report on a Codex multi-agent setup used to build an eval app. GPT-6 Astra at medium reasoning acted as orchestrator and Luna at max reasoning ran as subagents. The build took about 8 dev hours and used about 27% of his weekly limit.

Key points

• Orchestrator: GPT-6 Astra with medium reasoning effort.
• Subagents: Luna with max reasoning effort.
• Cost: about 27% of the weekly Codex limit. Time: about 8 dev hours.
• Result: an eval app that works with local models or any OpenAI-compatible API (later released as local-evals).
• Pattern: a strong model plans and delegates, while subagents do the implementation work.

Resources mentioned

• OpenAI Codex · tool · openai.com · paid
  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: An agent bot that installs and drives Codex on its own (Melvin Vivas on X · notes), Asking a Coder bot to install Codex (Melvin Vivas on X · notes), Sign in with ChatGPT: Setting Usage Limits for Each App (Melvin Vivas on X · notes), Codex Cloud Environments Must Be Saved & Published Before Use (Melvin Vivas on X · notes) and 240 more
• GPT-6 Astra · tool · openai.com · paid
  The model announced in the quoted launch post, pitched as the developer's most capable model for work, coding, science and cybersecurity, and able to operate a computer.
  Also in: Customizing Your Coding Setup with Pi Coding Agent Extensions (Melvin Vivas on X · notes), Pi Agent Council: Ask Multiple LLMs in Parallel and Compare Their Advice (Melvin Vivas on X · notes), Use GPT-6.1 Sol by Default, Save Astra for Emergencies (Melvin Vivas on X · notes), Dots in ChatGPT: always-on AI agents that you hand responsibilities to (Melvin Vivas on X · notes) and 49 more
• Luna · tool · openai.com · paid
  The other model/agent the classifier routes tasks to; the post doesn't describe it further.
  Also in: GPT-6.1 Sol May Beat Luna for Subagents (Melvin Vivas on X · notes), Picking models for orchestrator and subagent roles in Codex (Melvin Vivas on X · notes), GPT-6 Sol Ultra Subagents Use Up Limits Fast (Melvin Vivas on X · notes), GPT-6 Sol vs Opus 5.5 in a Livestream Comparison (Melvin Vivas on X · notes) and 14 more

Try this

• Try a Codex setup with a strong orchestrator model and subagents, and track the share of your weekly limit it uses.
• Build an eval app for local or OpenAI-compatible models with a Codex orchestrator/subagent workflow.