Single Agent vs Subagents in Codex: Trying Astra Only
Melvin Vivas · X post · 2026-09-10 · Open on X
Topics: AI Agents, Tool Use & MCP, AI Dev Tools & Productivity · Level: intermediate
Summary
Melvin Vivas plans to work a full day in Codex using only the Astra model, with no subagents. Other users report this works better, and someone at OpenAI reportedly discouraged subagents. The open question is whether usage limits will last with a single strong agent.
Key points
- Experiment: use only Astra in Codex for a full day, with no subagent orchestration.
- Community reports say a single strong model can do better than an orchestrator + subagents setup.
- A post from someone at OpenAI reportedly discouraged subagents in favor of Astra alone.
- The main risk is that usage limits run out with a single high-capability model.
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
Try this
- Compare a single-agent workflow with an orchestrator + subagents setup on your own tasks, tracking quality and usage.
More in AI Agents, Tool Use & MCP
- Using Codex Subagents to Produce a Video End-to-End with No Manual Edits
- Running Parallel Subagents in Codex with an Orchestrator Skill
- Coworker v0.4.1: Open-Source Desktop AI Agent App Adds CLI & Headless Mode
- Codex Astra/Luna Orchestrator: Reasoning Defaults for Pro vs Plus
- Coworker: open-source agent that runs on local models
- Codex setup: Astra orchestrator with Luna subagents