Tuesday, January 6, 2026
Claude Code Skills & Agents
Users are discussing leveraging Claude Code's skills and agents, including challenges with context window limits, sub-agent reliability, and effectively utilizing skills for consistent and reproducible results.
Do people know about the "claude-mem" plugin for Claude Code? Gives Opus 4.5 in Claude Code memory. Tracks your project details locally using an LLM so CC can reference them later. There is even an open PR to merge the Titans memory framework from GDM. Really excellent.
Even with GitHub Copilot, you can now select something like Claude Opus 4.5 in this way, but I'm curious whether there's a significant performance difference between Claude Code and GitHub Copilot even when the AI model is set to Opus 4.5. Also, it seems that a Plan mode has been