Agent skill
git-guardrails
Configure des hooks Claude Code pour bloquer les commandes git dangereuses (push, force-push, reset --hard, clean, branch -D, checkout/restore) avant leur exécution. Empêche les opérations git destructrices au niveau de l'agent.
Install this agent skill to your Project
npx add-skill https://github.com/Dedalus-ERP-PAS/hexagone-foundation-skills/tree/main/skills/git-guardrails
Metadata
Additional technical details for this skill
- author
- Foundation Skills
- adapted from
- DamienBattistella/skills/git-guardrails-claude-code
SKILL.md
Git Guardrails
Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude Code executes them.
When to Use This Skill
Activate when the user:
- Wants to prevent destructive git operations from being run by the AI agent
- Asks to add git safety hooks to Claude Code
- Wants to block
git push,git reset --hard, or other dangerous commands - Is setting up a new project and wants guardrails on git operations
What Gets Blocked
The following commands are intercepted and blocked before execution:
| Pattern | Description |
|---|---|
git push |
All push variants (prevents unreviewed pushes) |
git push --force |
Force push (rewrites remote history) |
git push --force-with-lease |
Force push variant |
git reset --hard |
Discards all uncommitted changes |
git clean -f / git clean -fd |
Deletes untracked files permanently |
git branch -D |
Force-deletes a branch without merge check |
git checkout . |
Discards all working tree changes |
git restore . |
Discards all working tree changes |
git rebase on main/master |
Prevents rebase of protected branches |
When blocked, Claude sees a message telling it that it does not have authority to run these commands. The user must run them manually if needed.
Setup Steps
Step 1: Ask Scope
Ask the user: install for this project only (.claude/settings.json) or all projects (~/.claude/settings.json)?
Step 2: Copy the Hook Script
The bundled script is at: reference/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:
chmod +x <path-to-script>
Step 3: Add Hook to Settings
Add to the appropriate settings file.
Project scope (.claude/settings.json):
{
"hooks": {
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
}
]
}
]
}
}
Global scope (~/.claude/settings.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. Do not overwrite other settings.
Step 4: Ask About Customization
Ask if the user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.
Common additions users may want:
- Block
git stash drop(prevents accidental stash loss) - Block
git tag -d(prevents tag deletion) - Allow
git pushbut only block--forcevariants
Step 5: Verify Installation
Run a quick test to confirm the hook works:
echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>
Expected result: exits with code 2 and prints a BLOCKED message to stderr.
Run a second test with a safe command:
echo '{"tool_input":{"command":"git status"}}' | <path-to-script>
Expected result: exits with code 0 (allowed).
How It Works
Claude Code supports PreToolUse hooks that run before any tool invocation. The hook:
- Receives the tool input as JSON on stdin
- Extracts the
commandfield usingjq - Checks the command against a list of dangerous patterns
- If a match is found, exits with code 2 (which tells Claude the command is blocked)
- If no match, exits with code 0 (which allows normal execution)
Important Notes
- The hook only blocks commands run by the AI agent. The user can still run any git command manually in their terminal.
- The blocked patterns use regex matching, so
git pushalso catchesgit push origin main --force. - If
jqis not installed, the script will fail open (allow all commands). Ensurejqis available. - The hook does not modify any git configuration; it only intercepts Claude Code tool calls.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ubiquitous-language
Extrait un glossaire de langage ubiquitaire style DDD de la conversation en cours, signale les ambiguïtés et propose des termes canoniques. Sauvegarde dans UBIQUITOUS_LANGUAGE.md. À utiliser quand l'utilisateur veut définir des termes métier, construire un glossaire, durcir la terminologie, créer un langage ubiquitaire ou mentionne « domain model », « DDD », « glossaire » ou « langage ubiquitaire ».
hexagone-web-feature-extractor
Explore any Hexagone Web space via Playwright headless browser, capture screenshots, and produce a PO-oriented Markdown document.
gitlab-issue
Crée, récupère, met à jour et gère les issues GitLab avec collecte complète du contexte. À utiliser quand l'utilisateur veut créer une nouvelle issue, voir les détails d'une issue, mettre à jour des issues existantes, lister les issues du projet ou gérer les workflows d'issues dans GitLab.
tdd
Développement piloté par les tests avec boucle red-green-refactor. À utiliser quand l'utilisateur veut construire des fonctionnalités ou corriger des bugs en TDD, mentionne « red-green-refactor », veut des tests d'intégration ou demande du développement test-first.
testing-patterns
Patrons et stratégies de test complets pour les projets JavaScript/TypeScript. Couvre les tests unitaires, d'intégration et E2E, les stratégies de mocking, l'organisation des tests et les anti-patrons courants. À utiliser quand l'utilisateur veut écrire des tests, améliorer la couverture de tests, établir une stratégie de test ou corriger des tests instables.
uniface-procscript
Navigue et interroge la documentation de référence officielle Uniface 9.7 ProcScript (594 entrées couvrant les instructions, fonctions, triggers, types de données, directives préprocesseur et fonctions struct). À utiliser quand l'utilisateur pose des questions sur la syntaxe ProcScript, les triggers Uniface, les opérations base de données, la gestion des listes, la manipulation d'entités, les fonctions de chaînes, la gestion d'erreurs ou tout sujet de programmation Uniface 9.7.
Didn't find tool you were looking for?