PreToolUse

PreToolUse is a hook for coding agents from xiaobei930/cc-best. Its token cost is not measured, scanned C, a copy of SessionStart, MIT.

A set of checks that run before the agent uses command-line or file-editing tools. They validate commands, pause before pushing to Git, look for secrets, protect sensitive files, and warn about long-running work.

In plain words
What is it for?
Use it to check shell commands, confirm Git pushes, scan command text for API keys and other sensitive values, protect files such as .env and .git, and warn before lengthy operations.
Why use it?
It catches risky commands, accidental secret exposure, and unsafe edits before they affect the project or its source history.

Hook

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cc-best plugin — 19 skills, 44 commands, 8 agents, 20 hooks shipped together

One of 20 entries in hooks.json — they are configured in one file and arrive together.

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add xiaobei930/cc-best
Claude Code
/plugin install cc-best

Or install cc-best, the plugin that ships this one along with the rest of its 19 skills, 44 commands, 8 agents, 20 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for PreToolUse

README.md
[![agentmods](https://agentmods.dev/badge/hooks/xiaobei930/cc-best/pre-tool-use.svg)](https://agentmods.dev/hooks/xiaobei930/cc-best/pre-tool-use)
Your own site
<a href="https://agentmods.dev/hooks/xiaobei930/cc-best/pre-tool-use"><img src="https://agentmods.dev/badge/hooks/xiaobei930/cc-best/pre-tool-use.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan C 1 finding. Scan, not verified.
Origin 55% copy Near-identical to another mod in the catalogue.
Security

Grade C, and why

PreToolUse scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"description": "命令验证: 阻止危险命令 (rm -rf /, git push --force 等)"
Origin

This is a copy

55% identical to SessionStart — 68 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

hooks/hooks.json · 71 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/validate-command.js\"",
          "timeout": 5
        }
      ],
      "description": "命令验证: 阻止危险命令 (rm -rf /, git push --force 等)"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/pause-before-push.js\"",
          "timeout": 5
        }
      ],
      "description": "推送确认: git push 前暂停确认"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/check-secrets.js\"",
          "timeout": 10,
          "statusMessage": "检查密钥泄露..."
        }
      ],
      "description": "密钥检测: 检查命令中是否包含 API 密钥等敏感信息"
    },
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/protect-files.js\"",
          "timeout": 3
        }
      ],
      "description": "文件保护: 阻止修改敏感文件 (.env, .key, .git/ 等)"
    },
    {
      "matcher": "Write",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/block-random-md.js\"",
          "timeout": 3
        }
      ],
      "description": "Markdown 文件保护: 阻止在根目录创建随机 .md 文件"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/node/hooks/long-running-warning.js\"",
          "timeout": 5
        }
      ],
      "description": "长时间命令警告: 检测开发服务器、watch 等长时间运行命令"
    }
  ]
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 71 lines scan C 04da23624fd2

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository xiaobei930/cc-best (50 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it C with 1 finding (recursive force delete). It is 55% identical to SessionStart, differing in 68 lines, and is treated as a copy.