Back to skills

Agent Skill

Git Guardrails Claude Code

git-guardrails-claude-code

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

MattpocockDevOpsShell
github.com/mattpocock/skills/tree/main/skills/misc/git-guardrails-claude-code

62K installs

•

mattpocock/skills

•

by Mattpocock

Score

8.9

/ 10

Installs

62K

Repo Stars

140.9K

Last Updated

4d ago

Fresh

Quality Ratio

97%

Description

Verified

Language

Shell

First Published

Feb 2026

Summary

The Git Guardrails Claude Code agent skill intercepts and blocks dangerous git commands like `git push` (all variants), `git reset --hard`, `git clean -f`, and `git branch -D` before the AI agent can execute them. This agent skill is designed for developers and teams leveraging Claude Code or similar AI agents who need to prevent accidental data loss or repository corruption during AI-assisted git operations. It is an emerging or highly specialized skill with limited adoption so far. This agent skill functions by installing a `PreToolUse` hook that scrutinizes Bash commands, preventing the AI from performing specified destructive actions like `git push` or `git reset --hard`. When a blocked command is attempted, Claude receives a message indicating it lacks the necessary authority. Users should note that installation requires manually copying a hook script and modifying Claude's settings JSON for either project-specific or global application.

Skill Definition

Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them.

What Gets Blocked

  • git push (all variants including --force)
  • git reset --hard
  • git clean -f / git clean -fd
  • git branch -D
  • git checkout . / git restore .

When blocked, Claude sees a message telling it that it does not have authority to access these commands.

Steps

1. Ask scope

Ask the user: install for this project only (.claude/settings.json) or all projects (~/.claude/settings.json)?

2. Copy the hook script

The bundled script is at: scripts/block-dangerous-git.sh

Copy it to the target location based on scope:

  • Project: .claude/hooks/block-dangerous-git.sh
  • Global: ~/.claude/hooks/block-dangerous-git.sh

Make it executable with chmod +x.

3. Add hook to settings

Add to the appropriate settings file:

Project (.claude/settings.json):

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
          }
        ]
      }
    ]
  }
}

Global (~/.claude/settings.json):

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "~/.claude/hooks/block-dangerous-git.sh"
          }
        ]
      }
    ]
  }
}

If the settings file already exists, merge the hook into existing hooks.PreToolUse array — don't overwrite other settings.

4. Ask about customization

Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.

5. Verify

Run a quick test:

echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>

Should exit with code 2 and print a BLOCKED message to stderr.

How to Use

Use in O-mega

Claude Code

npx skills add mattpocock/skills git-guardrails-claude-code
Git Guardrails Claude Code | Agent Skills | o-mega