Install
$ agentstack add skill-droodotfoo-agent-skills-git-guardrails ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Git Guardrails
Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them.
What You Get
- PreToolUse hook blocking destructive git operations
- Project-scoped or global installation
- Customizable blocked command patterns
- Verification test command
What Gets Blocked
git push(all variants including--force)git reset --hardgit clean -f/git clean -fdgit branch -Dgit checkout ./git restore .
When blocked, Claude sees a message telling it that it does not have authority to run these commands.
WRONG: no guardrails, Claude runs destructive commands silently
# Claude decides to "clean up" and runs:
git reset --hard HEAD~3 # 3 commits of work gone
git clean -fd # untracked files deleted
git push --force # rewrites shared history
CORRECT: hook blocks before execution
$ echo '{"tool_input":{"command":"git push --force"}}' | block-dangerous-git.sh
BLOCKED: git push is not allowed. Ask the user to run it manually.
Setup Steps
- Ask scope -- project (
.claude/settings.json) or global (~/.claude/settings.json)? - Copy hook script -- bundled at [scripts/block-dangerous-git.sh](scripts/block-dangerous-git.sh). Copy to
.claude/hooks/(project) or~/.claude/hooks/(global). Make executable. - Add to settings -- see [settings-config.md](settings-config.md) for the JSON
- Customize -- ask if user wants to add/remove patterns from the blocked list
- Verify --
echo '{"tool_input":{"command":"git push origin main"}}' |should exit code 2 with BLOCKED message
Reference
| File | Topic | |------|-------| | [settings-config.md](settings-config.md) | Project and global settings JSON | | [scripts/block-dangerous-git.sh](scripts/block-dangerous-git.sh) | The hook script |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: DROOdotFOO
- Source: DROOdotFOO/agent-skills
- License: MIT
- Homepage: https://droo.foo/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.