OpenAI's GPT-6 Astra prompting guide: trim your SKILL and AGENTS.md rules, the model is that strong
xiaohu · x · 2026-09-06
OpenAI released a prompting guide for its new flagship GPT-6 Astra, covering model traits, new API features, prompt techniques, and migration from older versions.
Model traits
- Astra chains multi-step work across code, browser, and professional software; benchmarks show notably fewer output tokens, so per-task API cost can be lower despite higher per-token pricing (with caveats).
- It favors boundary awareness, cautious execution, and clarifying questions; defaults include verbose formatted answers, fewer sub-agents, and over-testing small changes.
Async tool calls
- Setting async: true on tool definitions lets the model keep reasoning and calling other tools while the app executes one; results are returned via the original callid.
Prompting takeaways
- Five prompt categories adjust defaults for continuous progress, rule conflicts, style, delegation, and verification, with bilingual templates.
- Astra is more sensitive to instructions in context: stale rules in SKILL.md or AGENTS.md can stall execution, so prune them aggressively; if it keeps stopping, check what skill/project files it actually reads.
Migration
- Check interfaces, reasoning effort, deprecated parameters, and caching; validate per-task cost on your own workloads.
Related event: OpenAI's GPT-6 Astra prompting guide: trim your rules(3 posts)→
More from coding & agent
- User tests OpenAI Astra computer use: one PPT slide took nearly 15 minutes — bookwormengr · 2026-09-06
- asc CLI 5.0.0 ships, largely Astra-driven: 76 command groups for App Store automation — rudrank · 2026-09-06
- Yacine teases free AI-powered CAD service tonight, built as a manifoldcad wrapper — yacineMTB · 2026-09-06
- FONarch beta frees Adobe Creative Cloud subscription fonts into named folders on Mac — AIandDesign · 2026-09-06
- CryptoMesh VPN ships MCP companion letting agents join private networks with in-app approval — ActuaryGlad80 · 2026-09-06
- Models are already good enough: the AI bottleneck is user skill, not capability — dotey · 2026-09-06