agent-guard

v3.5.0

Local-by-default, no-telemetry hooks inspect user prompts, supported tool inputs, outputs, and changed files in every enabled Claude Code or Codex session to block or mask secret leaks. Includes opt-in PII filtering and Git/CI backstops.

Codex

By Agent Guard contributorsLicense: MIT1.1k GitHub starsUpdated 12 hours ago

Directory evidence

Runtimes: Codex
Parsed components: 0 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 agent-guard 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 agent-guard@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 “agent-guard-2” remain stable.

Codex: agent-guard-2@agent-plugin-marketplace → agent-guard@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/JeongJaeSoon/agent-guard/.

Plugin files

plugins/JeongJaeSoon/agent-guard/

└── .codex-plugin/plugin.json

Plugin manifests1

plugins/JeongJaeSoon/agent-guard/.codex-plugin/plugin.json

{
  "name": "agent-guard",
  "version": "3.5.0",
  "description": "Local-by-default, no-telemetry hooks inspect user prompts, supported tool inputs, outputs, and changed files in every enabled Claude Code or Codex session to block or mask secret leaks. Includes opt-in PII filtering and Git/CI backstops.",
  "author": {
    "name": "Agent Guard contributors",
    "url": "https://github.com/JeongJaeSoon"
  },
  "homepage": "https://github.com/JeongJaeSoon/agent-guard",
  "repository": "https://github.com/JeongJaeSoon/agent-guard",
  "license": "MIT",
  "keywords": [
    "agent",
    "secrets",
    "gitleaks",
    "hooks",
    "security"
  ],
  "hooks": "./hooks.json",
  "skills": "./codex-skills/",
  "interface": {
    "displayName": "Agent Guard",
    "shortDescription": "Real-time secret-leak guardrails for AI coding agents",
    "longDescription": "Local-by-default, no-telemetry hooks inspect supported tool-call inputs, outputs, and changed files in every enabled Claude Code or Codex session. Agent Guard blocks secrets pasted into the user prompt; blocks risky `.env` reads, secret writes, and credential-dumping commands; masks secret-like tool output; and adds native Git-hook and GitHub Actions backstops. PII hook processing and HTTP providers are opt-in.",
    "developerName": "Agent Guard contributors",
    "category": "Developer Tools",
    "capabilities": [
      "Read"
    ],
    "websiteURL": "https://github.com/JeongJaeSoon/agent-guard",
    "brandColor": "#14532D",
    "composerIcon": "./assets/icon.png",
    "screenshots": []
  }
}