Behavioral differences and prompting patterns for Claude Opus 5, covering response verbosity, agentic narration, task scoping, subagent delegation, self-correction, and output artifacts when thinking is disabled.
Prompting Claude Opus 5.5
Behavioral differences from Claude Opus 5 and the prompting and harness patterns that address them: effort calibration, thinking behavior in API integrations and chat, progress updates, unattended and multiagent tasks, safeguard refusals, frontend design, complex visual inputs, multi-app workflows, and pasted text in user messages.
Introducing Claude Opus 5.5
Claude Opus 5.5 leads in agentic coding and knowledge work, and costs 40% less to run than Opus 5 on typical workloads.
Introducing Claude Opus 5
Opus 5 is a step change improvement for the Opus tier powering long-running agents while delivering improvements in coding and professional work.
Introducing Claude Opus 4.6
Claude Opus 5: The System Card
Claude Opus 5 is trying to be the best of both worlds.
Claude Opus 5 Is Highly Capable, But Is No Mythos
Claude Opus 5 is a weirder than usual release to evaluate, for two reasons.
Opus 4.7 Part 2: Capabilities and Reactions
Claude Opus 4.7 raises a lot of key model welfare related concerns.
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
Opus 4.7 isn't dumb, it's just lazy — Shimin Zhang
Some follow up experiments with Claude Opus 4.7 based on Simon Willison's Pelican Benchmark Shocker.
Introducing Agent Skills | Claude by Anthropic
Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources that Claude can load when needed. Claude will only access a skill when it's relevant to the task at hand.
Introducing Agent Skills | Claude
Claude can now use Skills to improve how it performs specific tasks. Skills are folders that include instructions, scripts, and resources that Claude can load when needed. Claude will only access a skill when it's relevant to the task at hand.
Claude Opus 5.5 anthropic.com/claude-opus-5-5
