2026-07-26

Added

• trq212-claude-5-context-engineering - Thariq (@trq212) shares Anthropic's finding that cutting ~80% of Claude Code's system prompt for Claude 5 models caused no measurable eval loss — old "rules/examples/upfront" context engineering has become anti-patterns in favor of judgement, interface design, and progressive disclosure (claude doctor rightsizes skills/CLAUDE.md).