Anthropic publish most of the system prompts for their chat models as part of their release notes. They recently shared the new prompts for both Claude Opus 4 and Claude …
donald on Twitter / X
I made this with one prompt using Opus 5.5I spoke to my computer for 5mins, claude worked for 12 hours, and I woke up to thisfull prompt: https://t.co/BrxmiF90wd pic.twitter.com/2lxO8SAIEb— donald (@donaldjewkes) September 23, 2026
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.
Anthropic works on customizable Commands for Claude Code
Anthropic is developing a new Customize section for Claude, centralizing Skills, Connectors, and upcoming Commands for Claude Code.
