Claude Code Mods Released — Customize with JS/TS Hooks

AI Frontier8 days ago

Translated from Korean

Starting with version v2.1.287, Claude Code Mods is officially supported. It's a hook system that allows you to write plugins in JS and TS to directly customize Claude Code's internal operations. Now you can control your CLI agent environment exactly how you like without needing complex external wrapper tools.

The most notable features are tool execution control and prompt rewriting. You can now detect and block sensitive information or dangerous actions before the model executes commands, and create your own custom commands (/command) that run instantly without passing through the model. It even includes UI extensions to launch custom side panels in the terminal.

// Claude Code Mod 예시: 위험 명령어 차단 훅
export function onBeforeToolCall(tool) {
  if (tool.name === 'execute_command' && tool.args.cmd.includes('rm -rf')) {
    throw new Error('위험한 명령어가 감지되어 실행을 차단했습니다.');
  }
}

If you frequently use terminal-based AI agents, this should be very useful for setting up security guardrails or automating repetitive tasks. The setup is easier than you'd think, so update to the latest version of Claude Code and give it a try. 😄

Comment

Comment