Anthropic Releases Official Prompting Guide for Claude Opus 5
heypearlai · x · 2026-07-29
Anthropic shipped an official prompting guide alongside Claude Opus 5, emphasizing that the new model's behavioral patterns differ significantly from version 4.8, requiring users to unlearn old habits.
Core Improvements:
- Agentic Coding: Strongest on difficult coding tasks like multi-file features and large refactors. Performs best when given the complete task specification up front and left to run.
- Code Review: Features high precision and recall, finding real bugs at a high rate.
Prompting Adjustments:
- Self-Correction: The model verifies itself by default; no need for explicit "double-check" prompts.
- Effort Parameter: Controls reasoning token consumption, not the length of the visible output.
- Subagent Delegation: The model readily spawns subagents, requiring explicit caps in prompts to manage costs and latency.
Related event: Claude Opus 5 Official Prompting Guide and Practical Tips(7 posts)→
More from coding & agent
- Harness open-sources desktop and mobile apps for orchestrating agent fleets across frameworks and machines — dee_hw · 2026-10-16
- Open-Source Google Analytics MCP Server Lets LLMs Query GA Data via Natural Language — modelcontextprotocol · 2026-10-16
- LLM ideation experiment: just ask for non-obvious ideas — and Opus beats smaller models by a wide margin — arjunrajlab · 2026-10-16
- a16z podcast: AI cut a 6-month feature to 10 days and widened engineer gaps 10x — a16z · 2026-10-16
- "Hold On, My Agents Are Freezing My Screen": The Daily Grind of the Agent Era — every · 2026-10-16
- Dev builds MCP feeding Claude 3,000 real launch videos to fix samey AI output — Designer_Landscape25 · 2026-10-16