Agent Plugins Marketplace
← All plugins

agentguard

v0.1.1

Local tool policy gates and signed, content-free decision records for Codex and ChatGPT Work.

Agent Plugins3 Skills1 MCP serverstdio

By MerchantGuardOpsLicense: SEE LICENSE IN LICENSE0 GitHub starsUpdated 6 days ago

Directory evidence

Runtimes
Agent Plugins
Parsed components
4 skill or MCP entries
Source updated
Sep 18, 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 →

Get the plugin

git clone https://github.com/MerchantGuard/agentguard-codex-plugin

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

This listing currently publishes only the generic Agent Plugins format. Automatic install commands for other clients are not generated yet.

Plugin files

agentguard/
├── plugin.json
├── skills/agentguard-policy/SKILL.md
├── skills/agentguard-status/SKILL.md
├── skills/agentguard-verify/SKILL.md
└── mcp.json

Included Skills3

agentguard-policyskills/agentguard-policy/SKILL.md

Author or edit AgentGuard tool policies for matter budgets, session allowlists, and ethical-wall denies when the operator requests a policy change.

agentguard-statusskills/agentguard-status/SKILL.md

Read today's AgentGuard decisions, configured spend, blocks, and fail-open events from the local signed ledger without changing policy or tools.

agentguard-verifyskills/agentguard-verify/SKILL.md

Verify the AgentGuard signed chain and export a content-free receipt bundle to an operator-authorized location for a records custodian.

MCP servers1

agentguardstdio
command
node
args
${PLUGIN_ROOT}/runtime/mcp.cjs

MCP configuration uses runtime-provided plugin path placeholders such as ${PLUGIN_ROOT} or ${CLAUDE_PLUGIN_ROOT}. Review the manifest for the runtime-specific expansion rules.

Plugin manifests1

plugin.json
{
  "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
  "name": "agentguard",
  "version": "0.1.1",
  "description": "Local tool policy gates and signed, content-free decision records for Codex and ChatGPT Work.",
  "author": {
    "name": "MerchantGuardOps",
    "url": "https://agentguard.run"
  },
  "homepage": "https://agentguard.run",
  "repository": "https://github.com/MerchantGuard/agentguard-codex-plugin",
  "license": "SEE LICENSE IN LICENSE",
  "keywords": [
    "governance",
    "security",
    "tool-policy",
    "receipts",
    "codex"
  ],
  "extensions": {
    "com.openai": {
      "apps": "./.app.json",
      "hooks": "./hooks/hooks.json",
      "interface": {
        "displayName": "AgentGuard",
        "shortDescription": "Tool policies, spend limits, and signed local records",
        "longDescription": "Apply policies to supported local tool calls in Codex and ChatGPT Work. Record signed decisions and outcomes without retaining tool inputs or output text. Hooks fail open on internal errors.",
        "developerName": "MerchantGuardOps",
        "category": "Productivity",
        "capabilities": [
          "PreToolUse hooks",
          "PostToolUse hooks",
          "Read-only MCP"
        ],
        "websiteURL": "https://agentguard.run",
        "brandColor": "#2ABCB4",
        "composerIcon": "./assets/icon-128.png",
        "logo": "./assets/logo-512.png",
        "defaultPrompt": [
          "Use agentguard-policy to configure this session.",
          "Use agentguard-status to summarize today's decisions.",
          "Use agentguard-verify to verify and export the signed records."
        ]
      }
    }
  }
}

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.

[agentguard on Agent Plugins Marketplace](https://pluginsmp.com/plugins/agentguard-2)