Claude Code v2.1.319, released November 6 2026, brings MCP task backgrounding, tighter auto-mode security behind LLM gateways, and a new deny-instead-of-prompt setting for unattended runs. Three changes every developer using AI agents should know about.
Claude Code 2.1.287 introduced Mods — TypeScript hooks that let developers directly modify how the agent behaves. Developers can rewrite prompts, block tool calls, replace UI elements, and redact secrets from outputs. Over 1,423 community builds are already listed. This turns Claude Code from a standalone coding tool into an extensible agent platform.
This post compiles practical principles and a checklist for protecting the personal data of students and staff when using AI tools in educational settings. Legal standards and real-world implementation methods are covered together.