optimize-claude-opus-5-prompts

Optimize Claude Opus 5 Prompts

Turn rough ideas and existing prompt stacks into copy-ready prompts for Claude Opus 5. Preserve the user's intent and hard constraints, clarify genuinely blocking gaps, and keep the result no more elaborate than the task requires.

Opus 5 performs well out of the box on prompts written for Claude Opus 4.8. Most real optimization here is subtractive plus a few targeted behavior instructions, not a rewrite into a larger template.

Use the official basis

Read references/official-guidance.md for model-specific rationale, runtime settings, and migration details. Read references/snippets.md for the copy-ready instruction blocks from Anthropic's guide. Treat the listed URLs as canonical and the prose as a dated working summary; fetch the live pages before making claims about current model IDs, parameters, availability, limits, or pricing.

Use the official model name Claude Opus 5 and the API model ID claude-opus-5. Treat Opus5, opus-5, and O5 as spelling variants unless context indicates a different product.

Follow the workflow

1. Capture the prompt contract

Identify the following from the user's message, pasted prompt, or referenced file:

• the user-visible outcome and why it matters;
• the inputs, source material, and context Claude will receive;
• hard constraints, facts, policies, and values to preserve;
• the required output, audience, language, and level of detail;
• tools, evidence, or verification the task genuinely depends on;
• whether Claude should assess, recommend, draft, implement, or take external action;
• authorized actions and actions that require approval;
• stopping and fallback behavior when a dependency is unavailable;
• which Opus 5 behavior the user has actually observed as a problem, and whether the prompt was carried over from Opus 4.8 or an earlier model.

Treat these as diagnostic dimensions, not mandatory prompt sections. Keep a simple prompt simple.