Skip to content
Back to skills

Git Guardrails Claude Code

ASecurity

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.

  • 8 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
developmentpythongobashrailsgitsecurity

Works with

  • claude code
  • cli

Security analysis

A100/100

Pro scans all 5 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add huytran1120/vietnam-agentic-skills --skill git-guardrails-claude-code --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Git Guardrails Claude Code?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Git Guardrails Claude Code
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/huytran1120-git-guardrails-claude-code/badge)](https://www.skillsdirectory.com/skills/huytran1120-git-guardrails-claude-code)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: git-guardrails-claude-code
description: >-
  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.
category: "workflow"
risk: "critical"
source: "https://github.com/mattpocock/skills/tree/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/misc/git-guardrails-claude-code"
source_repo: "mattpocock/skills"
author: "Matt Pocock"
license: "MIT"
license_source: "https://github.com/mattpocock/skills/blob/5beb35b040e3de97e54fa9e386d7e42d15c295c2/LICENSE"
source_revision: "5beb35b040e3de97e54fa9e386d7e42d15c295c2"
source_path: "skills/misc/git-guardrails-claude-code"
tags:
  - mattpocock
  - workflow
  - coding-agents
  - git
  - claude-code
  - hooks
---
_Source: [Matt Pocock / skills](https://github.com/mattpocock/skills/tree/5beb35b040e3de97e54fa9e386d7e42d15c295c2/skills/misc/git-guardrails-claude-code), MIT, revision `5beb35b040e3`. See [UPSTREAM-NOTICE.md](UPSTREAM-NOTICE.md) for import changes._

## VAS integration

This VAS adaptation takes precedence over the upstream process below.
Use only the scope the user requested. Delegate work, publish tracker changes or
pull requests, install dependencies, and create persistent hooks only when the
user has authorized those actions. Otherwise work directly or prepare a draft.
Use the current client's available tools; named upstream slash commands are
skill references, not a guarantee that a command or integration is installed.
Preserve existing user work and configuration.

Manage catalog discovery and installation with `./vas` or `python3 vas.py`.
Dependencies named by the workflow are prerequisites for the target project,
not dependencies of the VAS catalog manager.

This hook targets Claude Code, not every VAS-supported agent. Require Bash and jq before configuring it. Its pattern matching is a guardrail, not a security sandbox or complete Git command parser.


# Setup Git Guardrails

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](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`):

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

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

```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 the 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:

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

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

Files in this skill

  • SKILL.md4 KB
  • UPSTREAM-LICENSE.txt1 KB
  • UPSTREAM-NOTICE.md533 B
  • agents/openai.yaml112 B
  • scripts/block-dangerous-git.sh507 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.