PreToolUse

PreToolUse is a hook for Claude Code from NYCU-Chung/my-claude-devteam. Its token cost is not measured, scanned C, original, MIT.

A set of checks that run before the coding agent uses tools such as Bash, file editing, reading, and connected services. The checks can stop dangerous commands, protect configuration and branches, and warn about large files.

In plain words
What is it for?
It is for adding safety checks to an agent's development workflow and running project-specific checks before tool commands.
Why use it?
It helps prevent accidental deletion, unsafe force-pushes, skipped Git checks, and other risky actions before they happen.

Hook for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

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 my-claude-devteam plugin — 12 agents, 5 hooks shipped together

One of 5 entries in hooks.json upstream. Installing this one merges just its entry into your config; the other 4 are separate, each on its own page.

Good fit It is for adding safety checks to an agent's development workflow and running project-specific checks before tool commands.

Compare 6 hooks from other repositories ↓
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 NYCU-Chung/my-claude-devteam
Claude Code
/plugin install my-claude-devteam

Made for: Claude Code.

Or install my-claude-devteam, the plugin that ships this one along with the rest of its 12 agents, 5 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/nycu-chung/my-claude-devteam/pre-tool-use.svg)](https://agentmods.dev/hooks/nycu-chung/my-claude-devteam/pre-tool-use)
Your own site
<a href="https://agentmods.dev/hooks/nycu-chung/my-claude-devteam/pre-tool-use"><img src="https://agentmods.dev/badge/hooks/nycu-chung/my-claude-devteam/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. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found 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 8d 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.

"command": "input=$(cat | jq -r '.input // empty'); if echo \"$input\" | grep -qE 'rm\\s+(-[a-zA-Z]*r[a-zA-Z]*f|--recursive.*--force|-rf)'; then echo 'BLOCKED: rm -rf is dangerous' >&2; exit 2; fi; exit 0",
hooks/hooks.json · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "input=$(cat | jq -r '.input // empty'); if echo \"$input\" | grep -qE 'rm\\s+(-[a-zA-Z]*r[a-zA-Z]*f|--recursive.*--force|-rf)'; then echo 'BLOCKED: rm -rf is dangerous' >&2; exit 2; fi; exit 0",
          "description": "Block rm -rf"
        },
        {
          "type": "command",
          "command": "input=$(cat | jq -r '.input // empty'); if echo \"$input\" | grep -qE 'git\\s+push.*(-f|--force).*\\s+(main|master)'; then echo 'BLOCKED: Force pushing to main/master is not allowed.' >&2; exit 2; fi; exit 0",
          "description": "Block force push to main/master"
        },
        {
          "type": "command",
          "command": "node -e \"let d='';process.stdin.on('data',c=>d+=c);process.stdin.on('end',()=>{const i=JSON.parse(d);const cmd=i.tool_input?.command||'';if(/--no-verify/.test(cmd)){process.stderr.write('[devteam] BLOCKED: --no-verify is not allowed. Let git hooks run.\\n');process.exit(2)}process.stdout.write(d)})\"",
          "description": "Block --no-verify flag (git hooks must run)"
        },
        {
          "type": "command",
          "command": "node ${CLAUDE_PLUGIN_ROOT}/hooks/branch-protection.js",
          "description": "Block direct commits / force pushes on main / master / production"
        },
        {
          "type": "command",
          "command": "node ${CLAUDE_PLUGIN_ROOT}/hooks/commit-quality.js",
          "description": "Pre-commit: block debugger statements and secrets in staged files"
        }
      ]
    },
    {
      "matcher": "Write|Edit",
      "hooks": [
        {
          "type": "command",
          "command": "filepath=$(cat | jq -r '.file_path // .filePath // empty'); if echo \"$filepath\" | grep -qE '\\.(env|pem|key)$|/secrets/|credentials'; then echo \"BLOCKED: Cannot modify sensitive file: $filepath\" >&2; exit 2; fi; exit 0",
          "description": "Block writes to .

Read the full file on GitHub · 74 lines

Same file

What else hooks.json configures

This page is one entry in a file that holds 5. Installing the file brings all of them; each is measured and scanned on its own page.

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. 8d ago First seen · 74 lines scan C 9257da026713

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository NYCU-Chung/my-claude-devteam (269 stars, last pushed 4mo 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). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.