Anthropic adds 'Mods' to Claude Code so developers can change how the coding tool looks and works

Anthropic has released Mods for Claude Code, a plugin-based middleware system that runs directly inside the AI coding tool. Mods are JavaScript or TypeScript functions that hook into specific events, from tool calls and user prompts to UI rendering. Developers can use them to add custom panels next to the chat, intercept tool calls or create new commands. Anthropic says some built-in features, including the /diff command, are already built as Mods, and it has posted sample Mods on GitHub. The system works in the command-line interface and the desktop app, and partly in the VS Code extension. Mods are not sandboxed. They run with the user's own permissions, so Anthropic advises installing them only from trusted sources. Organizations can control which Mods are allowed to load. The first official Mod plugin, "You Should Know," runs a separate agent that watches Claude's output and sends a "Heads up" message when it spots important information the user may have missed. The release gives teams more control over the tool's behavior. It also widens the range of third-party code running inside an agent that already has access to developers' machines, which makes the organization-level load controls relevant to security teams.