Claude Skill

Block destructive Terraform, database, Kubernetes, cloud, and Git commands before Claude Code can execute them with Agen

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download agentskillexchange-skills-skills_block-destructive-terraform-database-kubernetes-cloud-and-git-commands-before-claude-code-can-execute-them-with-agent-guardrails-07beb56.zip · 0 KB

agentskillexchange/skills 45 57 forks MIT Updated 1d ago

Part of agentskillexchange/skills — 249 skills

Install

skills CLI

npx skills add https://github.com/agentskillexchange/skills/tree/main/skills/block-destructive-terraform-database-kubernetes-cloud-and-git-commands-before-claude-code-can-execute-them-with-agent-guardrails

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install agentskillexchange-skills@llmmart

Git git clone https://github.com/agentskillexchange/skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole agentskillexchange/skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Block destructive Terraform, database, Kubernetes, cloud, and Git commands before Claude Code can execute them with Agent Guardrails

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

Prerequisites

Claude Code, jq, shell access to project or user Claude config, repository clone of the guardrail scripts

Installation

Use the upstream install or setup path that matches your environment:

git clone https://github.com/roboticforce/agent-guardrails.git
Make all .sh files executable.

Requirements and caveats from upstream:

(if permissions require it)"}

Basic usage or getting-started notes:

Claude Code installed
jq installed (used by guard scripts to parse tool input)
Clone the repo:
Source: https://github.com/roboticforce/agent-guardrails
Extracted from upstream docs: https://raw.githubusercontent.com/roboticforce/agent-guardrails/HEAD/README.md

Documentation

https://github.com/roboticforce/agent-guardrails

Source

Agent Skill Exchange

Files (skills)

SKILL.md 2 KB

---
name: "Block destructive Terraform, database, Kubernetes, cloud, and Git commands before Claude Code can execute them with Agent Guardrails"
slug: "block-destructive-terraform-database-kubernetes-cloud-and-git-commands-before-claude-code-can-execute-them-with-agent-guardrails"
description: "Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them."
github_stars: 2
verification: "security_reviewed"
source: "https://github.com/roboticforce/agent-guardrails"
author: "Robotic Force"
publisher_type: "organization"
category: "Security & Verification"
framework: "Claude Code"
tool_ecosystem:
  github_repo: "roboticforce/agent-guardrails"
  github_stars: 2
---

# Block destructive Terraform, database, Kubernetes, cloud, and Git commands before Claude Code can execute them with Agent Guardrails

Add hard pre-execution guardrails to Claude Code so destructive shell commands are blocked before an agent can run them.

## Prerequisites

Claude Code, jq, shell access to project or user Claude config, repository clone of the guardrail scripts

## Installation

Use the upstream install or setup path that matches your environment:
- git clone https://github.com/roboticforce/agent-guardrails.git
- Make all .sh files executable.

Requirements and caveats from upstream:
- (if permissions require it)"}

Basic usage or getting-started notes:
- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) installed
- [jq](https://jqlang.github.io/jq/download/) installed (used by guard scripts to parse tool input)
- Clone the repo:

- Source: https://github.com/roboticforce/agent-guardrails
- Extracted from upstream docs: https://raw.githubusercontent.com/roboticforce/agent-guardrails/HEAD/README.md

## Documentation

- https://github.com/roboticforce/agent-guardrails

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/block-destructive-terraform-database-kubernetes-cloud-and-git-commands-before-claude-code-can-execute-them-with-agent-guardrails/)