Single-Agent Codex Astra xhigh Usage for a Feature Build
Melvin Vivas · X post · 2026-09-10 · Open on X
Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP · Level: intermediate
Summary
Melvin Vivas shares his Codex usage for building one Coworker feature with a single Astra agent at xhigh, working step by step with no subagents. He warns that codebase size and complexity change the numbers, so treat them with caution.
Key points
- Setup: one Astra agent at xhigh, working step by step, with no subagents.
- Task: adding a feature to an existing app (Coworker).
- Usage depends on codebase size and complexity, so other people's numbers don't transfer directly.
- Treat shared token-usage numbers with a grain of salt.
Resources mentioned
- Coworker (donvito/coworker) · repo · github.com · free
The creator's agent/bot tool. Version 0.7.0 adds a Primary Bot, free web search, an activity dashboard and support for open models through OpenRouter.
Also in: Coworker: a local-first desktop AI coworker that works with any model (Melvin Vivas on X · notes), Liquid AI's LFM2.5-24B-A2B: a local MoE model for agent tasks (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Coworker v0.7.2: Open-Source Desktop AI Assistant (Melvin Vivas on X · notes) and 59 more
Try this
- Compare usage numbers against your own codebase instead of copying other people's numbers.
More in AI Dev Tools & Productivity
- Making Product Demo Videos with Codex: The Coworker Desktop App Demo
- Codex Astra Making a Demo Video with HyperFrames
- Measure Your Own Codex Token Burn: Orchestrator+Subagents vs Single Agent
- Measuring Codex Usage Burn Rate: Astra (high) Without Subagents
- Editing a GitHub Repo From ChatGPT Work on iOS
- Codex as an All-Round Dev Companion