Claude Opus 5 prompt tips say old harness habits now waste tokens
tengyanAI · x · 2026-07-25
A user shares prompting notes for Claude Opus 5 after testing it in agent-style workflows.
Their main takeaways: avoid redundant instructions like asking the model to verify or double-check, because it may already do that internally; don’t spawn subagents just to review its own work; and if you want concise output, say so explicitly. The post also suggests giving the model the full task up front and letting it run, since effort controls reasoning rather than verbosity.
Related event: Claude Opus 5 Early Tests: Better Efficiency but Overly Proactive(29 posts)→
More from coding & agent
- Alex Townsend posts 200 open problems in numerical linear algebra for humans and AI agents — IgorCarron · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- Steal this idea: prompt-to-hardware where agents assemble custom devices — paraschopra · 2026-09-11
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11