Claude-skill-registry git-safety-guard
git clone https://github.com/majiayu000/claude-skill-registry
T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/git-safety-guard" ~/.claude/skills/majiayu000-claude-skill-registry-git-safety-guard && rm -rf "$T"
skills/data/git-safety-guard/SKILL.mdGit Safety Guard
Use this skill when setting up or configuring protection against destructive git/filesystem commands in Claude Code.
Overview
Git Safety Guard intercepts Bash commands before execution and blocks dangerous operations that could permanently destroy uncommitted work or important files. The guard uses regex pattern matching with an allowlist to distinguish between safe and dangerous variants of commands.
Key Features:
- CLI command for pattern checkingterraphim-agent guard- PreToolUse hook - Intercept Claude Code tool calls before execution
- Allowlist support - Safe patterns override dangerous patterns
- Fail-open semantics - If guard fails, commands pass through
Architecture
Claude Code PreToolUse | v git_safety_guard.sh (shell wrapper) | v terraphim-agent guard --json "$COMMAND" | v Pattern Matching (Regex) | +---> SAFE_PATTERNS (allowlist) -> Allow | +---> DESTRUCTIVE_PATTERNS -> Block with reason | +---> No match -> Allow
Commands Blocked
| Command Pattern | Reason |
|---|---|
| Discards uncommitted changes permanently |
| Discards uncommitted changes (except --staged) |
| Destroys all uncommitted changes |
| Can lose uncommitted changes |
| Removes untracked files permanently |
| Destroys remote history |
| Same as --force |
| Force-deletes branch without merge check |
(non-temp paths) | Recursive file deletion |
| Permanently deletes stashed changes |
| Deletes ALL stashed changes |
| Bypasses pre-commit and commit-msg hooks |
| Same as --no-verify |
| Bypasses pre-push hooks |
Commands Explicitly Allowed
| Command Pattern | Why Safe |
|---|---|
| Creates new branch, doesn't modify files |
| Creates orphan branch |
| Only unstages files, doesn't discard changes |
/ | Preview only, no actual deletion |
| Safer force push with remote check |
| Temp directories are designed for ephemeral data |
| System temp directory |
| User's temp directory |
For Humans
Quick Start
# Install terraphim-agent from GitHub releases (latest version) # macOS ARM64 (Apple Silicon) gh release download --repo terraphim/terraphim-ai \ --pattern "terraphim-agent-aarch64-apple-darwin" --dir /tmp chmod +x /tmp/terraphim-agent-aarch64-apple-darwin mv /tmp/terraphim-agent-aarch64-apple-darwin ~/.cargo/bin/terraphim-agent # macOS x86_64 (Intel) # gh release download --repo terraphim/terraphim-ai \ # --pattern "terraphim-agent-x86_64-apple-darwin" --dir /tmp # Linux x86_64 # gh release download --repo terraphim/terraphim-ai \ # --pattern "terraphim-agent-x86_64-unknown-linux-gnu" --dir /tmp # Note: crates.io version (cargo install terraphim_agent) is outdated (v1.0.0) # and missing the guard command. Use GitHub releases for latest features. # Test guard command echo "git checkout -- file.txt" | terraphim-agent guard --json # Output: {"decision":"block","reason":"git checkout -- discards...","command":"..."} echo "git checkout -b new-branch" | terraphim-agent guard --json # Output: {"decision":"allow","command":"git checkout -b new-branch"}
Installation
Project-local installation:
# Copy hook script cp .claude/hooks/git_safety_guard.sh /your/project/.claude/hooks/ # Add to .claude/settings.local.json { "hooks": { "PreToolUse": [{ "matcher": "Bash", "hooks": [{ "type": "command", "command": ".claude/hooks/git_safety_guard.sh" }] }] } }
Global installation (~/.claude/):
# Run install script with --global flag ./scripts/install-terraphim-hooks.sh --global
CLI Usage
# Check a command (JSON output) echo "git reset --hard" | terraphim-agent guard --json # Check a command (human output - exits with code 1 if blocked) echo "rm -rf /home/user" | terraphim-agent guard # Fail-open mode (always exit 0) echo "git checkout -- ." | terraphim-agent guard --fail-open
For AI Agents
Detecting Guard Availability
# Check if terraphim-agent is available if command -v terraphim-agent >/dev/null 2>&1; then echo "Guard available" elif [ -x "./target/release/terraphim-agent" ]; then AGENT="./target/release/terraphim-agent" fi
Using Guard in Hooks
PreToolUse Hook Pattern:
#!/bin/bash # Read JSON input INPUT=$(cat) TOOL_NAME=$(echo "$INPUT" | jq -r '.tool_name') COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command') # Only process Bash commands [ "$TOOL_NAME" != "Bash" ] && exit 0 # Check command RESULT=$(terraphim-agent guard --json <<< "$COMMAND") # If blocked, output deny decision if echo "$RESULT" | jq -e '.decision == "block"' >/dev/null; then REASON=$(echo "$RESULT" | jq -r '.reason') cat <<EOF { "hookSpecificOutput": { "hookEventName": "PreToolUse", "permissionDecision": "deny", "permissionDecisionReason": "BLOCKED: $REASON" } } EOF fi exit 0
Guard Response Format
Blocked command:
{ "decision": "block", "reason": "git checkout -- discards uncommitted changes permanently. Use 'git stash' first.", "command": "git checkout -- file.txt", "pattern": "git\\s+checkout\\s+--\\s+" }
Allowed command:
{ "decision": "allow", "command": "git checkout -b new-branch" }
Error Handling
The guard uses fail-open semantics:
- If terraphim-agent is not found: pass through unchanged
- If pattern matching fails: allow command
- Errors logged to stderr only in verbose mode
Enable verbose mode:
export TERRAPHIM_VERBOSE=1
What Happens When Blocked
When Claude tries to run a blocked command, it receives feedback like:
BLOCKED by git_safety_guard Reason: git checkout -- discards uncommitted changes permanently. Use 'git stash' first. Command: git checkout -- file.txt If this operation is truly needed, ask the user for explicit permission and have them run the command manually.
The command never executes. Claude sees this feedback and should ask the user for help.
Testing
# Manual test - should be blocked echo "git checkout -- test.txt" | terraphim-agent guard --json # Manual test - should be allowed echo "git checkout -b feature" | terraphim-agent guard --json # Run unit tests cargo test -p terraphim_agent guard_patterns # Test hook script echo '{"tool_name":"Bash","tool_input":{"command":"git reset --hard"}}' | \ .claude/hooks/git_safety_guard.sh
Troubleshooting
| Issue | Solution |
|---|---|
| Hook not triggering | Check configuration |
| Command not blocked | Verify pattern matches with |
| Agent not found | Build with |
| Permission denied | Run |
| jq not found | Install jq: or |
The Incident That Prompted This
On December 17, 2025, an AI agent ran
git checkout -- on multiple files containing hours of uncommitted work from another agent. This destroyed the work instantly and silently. The files were recovered from a dangling Git object via git fsck --lost-found, but it was a close call.
Instructions alone don't prevent accidents. Mechanical enforcement does.
Related Skills
- Knowledge graph-based text replacementterraphim-hooks
- For building custom guardsimplementation
- For validating guard behaviortesting
- For CI/CD integration with hooksdevops