Guard Git
SkillDocs & knowledgeBlocks risky git commands like force push and resets before your AI agent runs them.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Guard Git skill
About this skill
Block dangerous git commands (push, force push, reset --hard, clean, branch -D, checkout/restore .) and enforce Conventional Commits & Branch Protection before an AI agent runs them. Installs hook scripts for Claude Code, Cursor, Cursor CLI, and Gemini CLI; documents Google Antigravity Terminal deny
What this skill tells your AI
The instructions your AI receives, as published by danielvm-git/bigpowers in skills/guard-git/SKILL.md and read by ahel’s review.
HARD GATE — HARD GATE — Before committing, verify: branch is not main/master, author is correct, git user is configured. Bad commits are hard to fix.
Installs a shared hook that blocks destructive git operations and enforces workflow discipline. Requires jq on the agent's PATH when the hook runs.
What gets blocked/enforced
- Safety:
git push --force,git reset --hard,git clean -f,git branch -D,git checkout .,git restore .. - Discipline: Blocks direct commits or pushes to protected branches (
main,master) unlessGIT_BIGPOWERS_LAND=1(set only byscripts/land-branch.sh). - Allows:
git push origin <feature-branch>for backup/CI; solo land push tomainonly insideland-branch.sh. - Standardization: Enforces Conventional Commits for all
git commitcommands. - Secrets: Blocks commits containing common secret patterns (
sk-,ghp_,AKIA,xoxb-,-----BEGINprivate keys) — see REFERENCE.md.
Quick start
- Scope: ask project-only vs global (paths differ per product).
- Write the hook bundle from REFERENCE.md into the client's hooks directory.
- Run
chmod +xonpre-tool-use.sh. - Merge the hook snippet from REFERENCE.md into the right settings file — do not wipe unrelated keys.
- Verify with the tests in REFERENCE.md.
| Client | Mechanism | Config |
|---|---|---|
| Claude Code | PreToolUse (Bash) | .claude/settings.json or ~/.claude/settings.json |
| Cursor / Cursor CLI | beforeShellExecution | .cursor/hooks.json or ~/.cursor/hooks.json |
| Gemini CLI | BeforeTool + run_shell_command | .gemini/settings.json or ~/.gemini/settings.json |
| Google Antigravity | Built-in Terminal Deny list | Settings UI (no shell hook) |
Modes (env on the hook command): GIT_GUARDRAILS_MODE is claude (default) or cursor → stderr + exit 2 on block. Set gemini for Gemini CLI → JSON decision on stdout.
Customization
To add or remove patterns or protected branches, edit pre-tool-use.sh.
Advanced
Full JSON examples, merge rules, Antigravity deny-list entries, and test commands: REFERENCE.md.
Signals
- GitHub stars
- 248
- Forks
- 19
- Last commit
- Sep 2026
ahel review
K4info
destructiveK4binfo
destructive-scopedK6info
bundled executables the agent is told to runK4binfo
destructive-scoped (in scripts/lib/git-guardrails-core.sh)K4info
destructive (in REFERENCE.md)K4binfo
destructive-scoped (in REFERENCE.md)
Automated review, not a security audit. Ruleset v1+k2.
Advanced
- Item type
- skill
- Key
guard-git- Source
- github.com/danielvm-git/bigpowers