Anthropic publishes an official prompting guide for Claude Opus 5

The guide flags things that are easy to miss if you just carry old prompts over from prior models. Opus 5 verifies its own work without being told to — if a prompt still contains instructions like “add a final verification step,” it’s worth removing them, since they trigger redundant re-checking and burn tokens for no benefit. The same goes for “double-check your answer” style instructions — the model already catches its own mistakes reasonably well on its own.

Another detail: Opus 5 delegates to subagents more readily than earlier versions, which can meaningfully raise cost and runtime on small tasks unless you set explicit limits on delegation. The model also gives longer answers by default and narrates intermediate steps more often — if that’s not what you want, you have to explicitly ask it to be brief.

The guide points to a 1M token context window as both the default and the maximum, strong chart, diagram, and UI recognition, and solid work with complex multi-sheet spreadsheets and slide decks.

The effort parameter — low, medium, high, xhigh — is now the main lever for controlling response cost and speed, and Anthropic recommends re-running an effort sweep on your own evals rather than carrying over defaults tuned for a prior model.