Astra Quality Fixes: Skills Written for Older Models Misfire
Melvin Vivas · X post · 2026-09-12 · Open on X
Topics: AI Dev Tools & Productivity, AI Agents, Tool Use & MCP, Prompt & Context Engineering · Level: intermediate
Summary
The creator mentions a Codex usage reset and quotes an update on Astra quality issues. The update says some skills written for earlier models were triggering too often or stopping the model from checking its work. The lesson: check your skills again when you move to a new model.
Key points
- Codex usage limits were reset at midnight.
- Skills written for earlier models may trigger too often on a new model.
- Old skills can also stop the model from checking its own work.
- After a model upgrade, review your skills and agent instructions.
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
- Check whether skills written for older models trigger too often or stop the model from checking its work.
More in AI Dev Tools & Productivity
- LM Studio's Bionic: importing skills from Codex and Claude Code
- Coworker v0.5.1 Release: Dark Mode and Easier Theme Switching
- T3 Code: An Agent App Praised for Its UX
- T3 Code Opens Your Project in Any Installed IDE
- T3 Code's Built-in Hints for Tagging Folders and Using Skills
- Opinion: Enterprises Pick GitHub Copilot, but Cursor Is Better