Home / chinkan / rustfox · GitHub

git-guardrails-claude-code SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 5 indexed copies. Same content hash, so the same checks give both the same grade.

git-guardrails-claude-code from chinkan/rustfox is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add chinkan/rustfox/git-guardrails-claude-code@git:20260922.53f91f6

Pins git:20260922.53f91f6 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: chinkan/rustfox
Path: .agents/skills/git-guardrails-claude-code/SKILL.md
Versions recorded: 1
Latest version: git:20260922.53f91f6, committed Sep 22, 2026
Size: 2,313 bytes
Repository stars: 11
License: MIT

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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 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",
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add chinkan/rustfox/git-guardrails-claude-code@sha256:69b291d655626a01

The line at the top of this page pins the label git:20260922.53f91f6, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_bsodsfyas5oor5pw.svg)](https://markdownregistry.com/a/art_bsodsfyas5oor5pw)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 22, 2026.

version	committed	commit	size	audit
git:20260922.53f91f6 latest	2026-09-22	53f91f6	2,313 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (2313 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

chinkan/rustfox · 11 stars · license MIT · pushed 2026-11-03 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_bsodsfyas5oor5pw
GET https://markdownregistry.com/api/v1/resolve?ref=chinkan/rustfox/git-guardrails-claude-code
GET https://markdownregistry.com/api/v1/blob/69b291d655626a01602b998a1836fcb93c058ede68dfafddfd71e87f17074764

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from chinkan/rustfox

ask-matt SKILL.md skill

chinkan/rustfox · .agents/skills/ask-matt/SKILL.md · Ask which skill or flow fits your situation. A router over the skills in this repo.

git:20260922.53f91f6 · audit A · 11 stars

brainstorming SKILL.md skill

chinkan/rustfox · .agents/skills/brainstorming/SKILL.md · You MUST use this before any creative work - creating features, building components, adding functionality, or modifying…

git:20260408.ae338c2 · audit A · 11 stars

cavecrew SKILL.md skill

chinkan/rustfox · .agents/skills/cavecrew/SKILL.md · Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator`…

git:20260804.a62331b · audit A · 11 stars

caveman-commit SKILL.md skill

chinkan/rustfox · .agents/skills/caveman-commit/SKILL.md · Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning…