Git Guardrails Skill
Install a Claude Code PreToolUse hook that blocks destructive git commands (push, reset --hard, clean -f, branch -D) before they ever execute.
---
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": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
}
]
}
]
}
}
```
**Global** (`~/.claude/settings.json`):
```json
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "~/.claude/hooks/block-dangerous-git.sh"
}
]
}
]
}
}
```
If the settings file already exists, merge the hook into existing `hooks.PreToolUse` array: don't overwrite other settings.
### 4. Ask about customization
Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.
### 5. Verify
Run a quick test:
```bash
echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>
```
Should exit with code 2 and print a BLOCKED message to stderr.
---
The companion files referenced above are bundled below. To use this skill as a folder, save each bundled file at its listed path alongside SKILL.md.
---
# Bundled file: scripts/block-dangerous-git.sh
```bash
#!/bin/bash
INPUT=$(cat)
COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command')
DANGEROUS_PATTERNS=(
"git push"
"git reset --hard"
"git clean -fd"
"git clean -f"
"git branch -D"
"git checkout \."
"git restore \."
"push --force"
"reset --hard"
)
for pattern in "${DANGEROUS_PATTERNS[@]}"; do
if echo "$COMMAND" | grep -qE "$pattern"; then
echo "BLOCKED: '$COMMAND' matches dangerous pattern '$pattern'. The user has prevented you from doing this." >&2
exit 2
fi
done
exit 0
```How to use
Guardrails as structure, not prompt: a PreToolUse hook can't be talked out of blocking git push the way an instruction can, which is the whole point. The skill walks through scope choice (project vs global), installs the block script, and verifies the hook fires. Blocked commands stay available to you in a separate terminal. This restrains the agent, not the human. Save as .claude/skills/git-guardrails-claude-code/SKILL.md, or install Matt's full MIT-licensed set (github.com/mattpocock/skills) with 'claude plugins install mattpocock-skills'.
More skill prompts
--- name: writing-documentation description: Write or update documentation from the code. Use when the user asks for a README, API reference, guide, docstrings, or says the docs are out of date. --- # Writing Documentation Documentation is a claim about behavior. Every claim must be checked against the code before it ships, because a wrSKILL.md
Documentation Skill
A skill that documents what the code does rather than what it should do: read first, examples from tests, unverifiable claims marked.
--- name: security-review description: Review code for security defects. Use before merging changes that touch authentication, authorization, user input, file handling, secrets, or external requests, or when the user asks for a security review. --- # Security Review Find defects an attacker could actually use. A finding without an attacSKILL.md
Security Review Skill
A skill that reviews changes for exploitable defects, follows untrusted input to where it lands, and reports only findings with an attack path.
--- name: accessibility-review description: Audit UI code for accessibility defects against WCAG. Use when building or changing components, forms, modals, or navigation, or when the user asks about accessibility, a11y, screen readers, or keyboard support. --- # Accessibility Review Judge the interface by whether a person can complete thSKILL.md
Accessibility Skill
A skill that audits UI against WCAG by keyboard, semantics, and state, reporting who is blocked rather than listing rule numbers.