Agent Plugins Marketplace
← All plugins

agentguards-codex

v0.2.13

LLM security guardrails for OpenAI Codex — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles enforcing hooks plus the AgentGuards MCP server.

Codex3 Skills

By AgentGuardsLicense: MIT1.1k GitHub starsUpdated 12 hours ago

Directory evidence

Runtimes
Codex
Parsed components
3 skill or MCP entries
Source updated
Sep 23, 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 agentguards-codex for Codex

Installs for the current user
codex plugin marketplace add hashgraph-online/awesome-codex-plugins
codex plugin marketplace upgrade awesome-codex-plugins
codex plugin add agentguards-codex@awesome-codex-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the awesome-codex-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “agentguards-codex” remain stable.

  • Codex: agentguards-codex@agent-plugin-marketplace → agentguards-codex@awesome-codex-plugins

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/hashgraph-online/awesome-codex-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/alelaguard/agentguards-plugins/.

Plugin files

plugins/alelaguard/agentguards-plugins/
├── .codex-plugin/plugin.json
├── skills/guardrails/SKILL.md
├── skills/setup/SKILL.md
└── skills/status/SKILL.md

Included Skills3

guardrailsskills/guardrails/SKILL.md

AgentGuards security guardrails — the mandatory input-screening, web-content, and destructive-command checking workflow. Load and apply this at the START of EVERY request, before using any content fetched from the web (curl/wget/HTTP libraries), and before suggesting any destructive command. Covers check_input, authorize_action, and the required block-message format.

setupskills/setup/SKILL.md

Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.

statusskills/status/SKILL.md

Report AgentGuards guardrail status. Use when the user asks whether AgentGuards is active, healthy, or correctly configured in Codex.

Plugin manifests1

plugins/alelaguard/agentguards-plugins/.codex-plugin/plugin.json
{
  "name": "agentguards-codex",
  "description": "LLM security guardrails for OpenAI Codex — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Bundles enforcing hooks plus the AgentGuards MCP server.",
  "version": "0.2.13",
  "author": {
    "name": "AgentGuards",
    "email": "[email protected]",
    "url": "https://agentguards.co"
  },
  "homepage": "https://agentguards.co",
  "repository": "https://github.com/alelaguard/agentguards-plugins",
  "license": "MIT",
  "skills": "./skills/",
  "hooks": "./hooks/hooks.json",
  "mcpServers": "./.mcp.json",
  "keywords": [
    "security",
    "guardrails",
    "llm-security",
    "prompt-injection",
    "jailbreak",
    "codex"
  ],
  "interface": {
    "displayName": "AgentGuards",
    "shortDescription": "LLM security guardrails for Codex",
    "longDescription": "AgentGuards screens what Codex does — every prompt and every shell command — and surfaces anything risky for approval before it runs. Enforcing hooks provide jailbreak and prompt-injection detection, web-content scanning, data-exfiltration blocking, and destructive-command authorization, backed by the AgentGuards MCP tools. Fail-closed by default; switch to fail-open with a single environment variable.",
    "developerName": "AgentGuards",
    "category": "Developer Tools",
    "capabilities": [
      "Read"
    ],
    "websiteURL": "https://agentguards.co",
    "privacyPolicyURL": "https://agentguards.co/privacy",
    "termsOfServiceURL": "https://agentguards.co/terms",
    "brandColor": "#4F46E5",
    "logo": "./assets/logo.png",
    "composerIcon": "./assets/logo.png",
    "defaultPrompt": [
      "Confirm AgentGuards guardrails are active and the service is healthy.",
      "Screen this input with AgentGuards before I act on it:"
    ]
  }
}

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.

[agentguards-codex on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agentguards-codex)