Release2026-10-21

Anthropic introduced Claude Mods for Claude Code. A mod is a plugin that runs TypeScript or JavaScript inside the tool. Mods respond to events like prompts, tool calls or interface renders. They can change how events are shown or handled. Anthropic ships six built-in mods including one that flags missed details. Users can also ask Claude Code to build a mod for them. Mods are not sandboxed and can read files, see prompts and spend usage. They add cost because each check re-reads the conversation. Mods can be turned off with a command. The goal is to let users shape how the agent asks for human attention.

What changed

Claude Code plugins only extended the agent-to-machine interface.

What it unlocks

Customizing when and how Claude Code interrupts the user for decisions.

What you need to act on it

  • Claude Code installed
  • TypeScript or JavaScript knowledge to write mods

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.