Agent Plugins Marketplace
← All plugins

guardrails

v0.5.2

Checks each shell command the assistant runs before it runs. Blocks force-pushes to protected branches (main and master by default), git hooks skipped with the no-verify flag, and staging or committing files or added lines that look like secrets; asks for confirmation before git commands that discard uncommitted work (Codex cannot ask from a hook, so there those commands are blocked with the reason). It reads the command text, so it catches ordinary and accidental commands, not deliberately hidden ones. A skill explains each rule and its settings.

Claude Code1 Skill

By MojoAILicense: MIT0 GitHub starsUpdated 2 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Sep 22, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install guardrails for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install guardrails@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/MojoAI-King/Skilliton

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is packs/base/plugins/guardrails/.

Plugin files

packs/base/plugins/guardrails/
├── .claude-plugin/plugin.json
└── skills/guardrails/SKILL.md

Included Skills1

guardrailsskills/guardrails/SKILL.md

Use when a git command was blocked or paused by the guardrails hook, or when the user asks what is protected, why a git command was stopped, or how a team lead changes the protections. Explains each rule, why it exists, the safe alternative, and the settings.

Plugin manifests1

packs/base/plugins/guardrails/.claude-plugin/plugin.json
{
  "name": "guardrails",
  "description": "Checks each shell command the assistant runs before it runs. Blocks force-pushes to protected branches (main and master by default), git hooks skipped with the no-verify flag, and staging or committing files or added lines that look like secrets; asks for confirmation before git commands that discard uncommitted work (Codex cannot ask from a hook, so there those commands are blocked with the reason). It reads the command text, so it catches ordinary and accidental commands, not deliberately hidden ones. A skill explains each rule and its settings.",
  "version": "0.5.2",
  "author": {
    "name": "MojoAI"
  },
  "homepage": "https://github.com/MojoAI-King/Skilliton",
  "repository": "https://github.com/MojoAI-King/Skilliton",
  "license": "MIT"
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[guardrails on Agent Plugins Marketplace](https://pluginsmp.com/plugins/guardrails)