What is git-guardrails-claude-code?

A safety setup for Claude Code that blocks selected dangerous Git commands before they run, including commands that delete work or send changes to a remote repository.

Use it to install project-level or global Claude Code hooks that block commands such as git push, git reset --hard, git clean, and git branch -D.

It reduces the chance that an automated coding agent will accidentally discard local changes or publish them.

git-guardrails-claude-code — Skill for Claude Code by JustineDevs

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add JustineDevs/premortem --skill git-guardrails-claude-code

Clone the repo

git clone --depth 1 https://github.com/JustineDevs/premortem

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/justinedevs/premortem/git-guardrails-claude-code.svg)](https://agentmods.dev/skills/justinedevs/premortem/git-guardrails-claude-code)

Your own site

<a href="https://agentmods.dev/skills/justinedevs/premortem/git-guardrails-claude-code"><img src="https://agentmods.dev/badge/skills/justinedevs/premortem/git-guardrails-claude-code.svg" alt="Measured on agentmods" height="20"></a>

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 588 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin 92% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00588
Opus 5	$0.00031	$0.00294
Sonnet 5	$0.00012	$0.00118
Haiku 4.5	$0.00006	$0.00059

Measured 3d ago against content hash 03c4de7613c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

git-guardrails-claude-code scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/block-dangerous-git.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Ask the user: install for **this project only** (`.claude/settings.json`) or **all projects** (`~/.claude/settings.json`)?

Origin

This is a copy

92% identical to git-guardrails-claude-code — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/engineering/misc/git-guardrails-claude-code/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

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):

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
          }
        ]
      }
    ]
  }
}

Global (~/.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 existing hooks.PreToolUse array — don't overwrite other settings.

4. Ask about customization

Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.

5. Verify

Run a quick test:

echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>

Should exit with code 2 and print a BLOCKED message to stderr.

Read the full file on GitHub · 96 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/block-dangerous-git.sh 507 B runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago First seen · 96 lines · 62 tokens per session scan B 03c4de7613c7

Subscribe to this mod's changes

git-guardrails-claude-code is a skill published in the GitHub repository JustineDevs/premortem (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 62 tokens to every session and 588 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 92% identical to git-guardrails-claude-code, differing in 2 lines, and is treated as a copy.

Git and workflow Security ai arize-phoenix azure bitbucket claude cli

bitbottle

Reference for the bitbottle CLI — a gh-style tool for Bitbucket Server/DC and Cloud. Load when the user asks about bitbottle commands, auth setup, PRs, repos, branches, tags, commits, pipelines, or why a command failed. Load even if the user just says "bitbottle", mentions "Bitbucket", or pastes a bitbottle error…

proggarapsody/bitbottle · 84 tokens

share-a-library

Use when a managed library is ready to publish to GitHub and hand to teammates as an install command. Run the GitHub publishing steps, then return the exact shareable install command.

MoizIbnYousaf/Ai-Agent-Skills · 41 tokens

install

This skill should be used when the user asks to "install pikiclaw", "build and install", "deploy locally", "update local binary", "release", or "publish".

xiaotonng/pikiloom · 39 tokens

release

Prepare and publish Perigon.CLI patch releases, including versioning, release notes, bilingual docs, validation, and the nuget-branch CI handoff.

AterDev/Perigon.CLI · 34 tokens

hash-anchored-edit

A file-editing procedure that uses SHA-256 hashes to check whether a file changed before and after an edit. It also describes ownership rules for files handled by parallel agents.

Insajin/autopus-adk · 18 tokens

uploads-cli

Reference for the uploads CLI and its stdio/hosted MCP tools — exact flags, keys, and contracts for put and attach, screenshot capture, stable PR/issue keys, the managed attachments comment, metadata and search, galleries, config defaults, login/doctor, and output formats. Use when driving the uploads CLI or its MCP…

buildinternet/uploads · 215 tokens

git-guardrails-claude-code