Measuring Codex Pro Runtime: Astra(low) + Luna(max) Subagents
Melvin Vivas · X post · 2026-09-08 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity, LLMOps, Deployment & Monitoring · Level: intermediate
Summary
Melvin Vivas reports real usage figures from Codex Pro (5x). A one-hour run with Astra (low reasoning) as orchestrator and Luna (max reasoning) as subagents used about 7% of the weekly limit. From that he estimates about 14.3 hours of runtime per week, and notes that a run using only Astra would burn limits faster.
Key points
- Setup: Astra at low reasoning as orchestrator, Luna at max reasoning as subagents.
- A 1-hour run left 93% of the weekly Pro 5x limit.
- That projects to about 14.3 hours of total runtime per weekly limit.
- Delegating to Luna subagents lowers usage; Astra alone would use limits faster.
- Measure usage per hour of runtime to plan your agent budget.
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 - 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: Glimpse: A Visual Reasoning Model That Uses a Visual Scratch Space (Melvin Vivas on X · notes), Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), GitHub Copilot Adds Intelligent Local Model Routing (Project HydraFusion) (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes) and 55 more - 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
- Track the % of your weekly limit used per hour of runtime to estimate your total budget.
More in AI Agents, Tool Use & MCP
- Codex Subagents: Astra Orchestrator + Luna Workers, and How to Swap Models
- Codex: Orchestrating Big Tasks with a Skill and Subagents
- Luna Subagents Save Usage Limits in Codex Pro
- Codex Orchestrator Skill: Astra Orchestrates, Luna Subagents Execute
- Codex Orchestrator: Astra/Sol Orchestrator with Luna Subagents
- JSONL Viewer v1.3.4: Inspecting Nested Codex Subagent Traces