git-guardrails-claude-code

Savant verdict: Review advised

SkillSpector or the source hub flagged patterns to review before use.

Live evaluation

Not evaluated yet. Workspaces can request a live evaluation.

Safety (NVIDIA SkillSpector)

3 patterns found

• Tool Misuse: git reset --hardhigh · SKILL.md:13 · Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
• Agent Snooping: ~/.claude/settings.jsonhigh · SKILL.md:24 · Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.
• Agent Snooping: ~/.claude/settings.jsonhigh · SKILL.md:61 · Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.

Structure

• 1 referenced file isn't in the packagescripts/block-dangerous-git.sh. They may be binary, too large to catalog, or missing upstream.
• No license declaredConfirm you may reuse this skill before importing it into your repository.

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.
---

# 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.