Anthropic publishes Claude Opus 5 prompting guide for long-horizon coding agents
heypearlai · x · 2026-07-29
Anthropic published a prompting guide for Claude Opus 5 and says the model behaves differently enough from Opus 4.8 that some habits need to change.
- Opus 5 is tuned for long-horizon, agentic coding and enterprise work, and it handles difficult multi-file refactors better when given the full task spec up front.
- The guide highlights changes in verbosity, task scoping, self-correction, subagent delegation, and output artifacts when thinking is disabled.
- It also says Opus 5 tends to do better at code review and bug finding, with high precision and recall, making it less useful to keep prompting patterns that were designed for earlier models.
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