MetaMynd AgentSafe Guard – Runtime Governance for AI Agents icon

MetaMynd AgentSafe Guard – Runtime Governance for AI Agents 

Every AI agent tool call authorized, signed and audited outside the agent

metamynd/agentsafe-guard · v0.1.0 · Tools & Integrations

by MetaMyndOwner verifiedAwesome AI Plugins

You can tell an AI agent to stay under its budget and use approved vendors. It will usually comply, but "usually" is not a control you can show an auditor.

InstallSource
Follow0
Trust Score94Security scanPartialComponents1
Protect this install with HOL Guard

Guard checks the skills and MCP servers a plugin adds on your machine and asks you before a risky action runs. The scores above are free, and no plan changes them.

Is Metamynd Runtime Governance for AI Agents a fit?

From the plugin's manifest and HOL's scan. Anything the plugin does not declare is shown as not declared.

Works with

  • Codex
  • Claude Code
  • 1 skill

Before you install

Sign-in
Not declared
Declared access
Read, Write
License
MIT

Check before relying on it

About Metamynd Runtime Governance for AI Agents

Metamynd Governance moves the decision out of the agent. Wrap a tool in three lines: every call is checked against a mandate the agent cannot edit, signed, and decided outside its process, and a refused call never reaches your code. Because the gate is default-deny, an agent cannot widen its own authority: ask for an action nobody delegated and the answer is NO_PERMISSION_FOR_ACTION, at $1 or $100,000.

Agent-side, MCP-server-side, Agent2Agent and HTTP guards with zero runtime dependencies, a deterministic open-source evaluator, and a Python client. MIT licensed.

What is MetaMynd AgentSafe Guard – Runtime Governance for AI Agents?

MetaMynd AgentSafe Guard – Runtime Governance for AI Agents is a published tools & integrations plugin for AI coding agents that works with Codex and Claude Code, developed by MetaMynd and distributed through the HOL AI plugin registry. Wrap an AI agent's tools so every call is authorized, signed and audited outside the agent's process, and a refused call never runs.

Canonical slug
metamynd/agentsafe-guard
Version
v0.1.0 · updated Nov 12, 2026

Registry snapshot

Owner verification
Verified on HOL as @metamyndai
Marketplace source
.claude-plugin/marketplace.json
Scanner
HOL plugin scanner
Security result
Partial scan
Digest verified
Yes
1 bundled skillRead, copy or download each SKILL.mdOpen skills

Trust and security

Trust & reputation

On-Chain Verified
94

HOL Trust Score

Per-metric points (0–100 each) combined via a weighted average into the overall score.

Installability
100/100
Maintenance
100/100
MCP server setup
100/100
Plugin Security
93/100
Provenance
80/100
Publisher Quality
100/100

Provenance

Plugin root
.
Source repo
https://github.com/Metamynd/agentsafe-guard
Source commit
72b2ea77ee25…
Publisher verified
Yes
Owner verified
@metamyndai
Agent Plugins 1.0
Not detected

README badge detected

The source repository README links to this HOL listing. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Security posture

See how the Trust Score is computed
Partial scan
Security result
93
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan. No blocking issue was found in the checks that did finish, but this is not a passed scan.

Provider
codex-plugin-scanner
Grade
A · Excellent
Version
3.24.2
codex:hol-plugin-scanner-XvWFZH / cisco-skill-scanner: failedcodex:hol-plugin-scanner-XvWFZH / cisco-mcp-scanner: skipped

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

16/16

6 checks

[claude:.] Operational Security

3/6

5 checks

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

31/31

9 checks

[codex:.] Security

16/16

9 checks

[codex:.] Operational Security

3/6

5 checks

[codex:.] Best Practices

9/12

5 checks

[codex:.] Marketplace

N/A

3 checks · not applicable

[codex:.] Skill Security

5/5

4 checks

[codex:.] Code Quality

10/10

2 checks

Published advisories

None matched in GitHub security advisories, checked . This covers published advisories only, not problems nobody has reported.

GitHub security advisories are those the source repository has published.

Findings

lowoperational-securityDEPENDABOT_MISSINGReported 2 times

Automation or dependency surfaces exist, but .github/dependabot.yml is missing.

Add Dependabot updates for GitHub Actions and dependency manifests.

infobest-practicesCODEXIGNORE_MISSING

A .codexignore file helps prevent accidental inclusion of local artifacts and secrets.

Add a .codexignore file with generated assets, local state, and secret paths.

Install guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

Optional: install HOL Guard for Claude Code first, so it can check this plugin's tools on your machine before Claude Code uses them.

  1. 1

    Add the marketplace

    Run this inside a Claude Code session. It registers the marketplace manifest shipped at the repository root. If the repository ships none, add the generated entry from the Advanced section below first.

    claude code
  2. 2

    Install the plugin

    Installs the agentsafe-guard entry from the metamynd marketplace.

    claude code
  3. 3

    Scripted alternative

    Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.

    shell
  4. 4

    Check it is installed

    Lists installed plugins. The entry should appear as enabled.

    shell

To remove it later, run claude plugin uninstall agentsafe-guard@metamynd.

Did setup work in Claude Code?

No setup reports for Claude Code yet. Self-reported by signed-in visitors. Copying a command is not counted, and most installs are never reported.

Attested installs: Fewer than 10 attested installs of this plugin in week 2026-W45, so no number is shown. Counted from opt-in HOL Guard install reports, once per machine and runtime, and never mixed with the answers above. How install reports work.

1 / 1

MetaMynd AgentSafe Guard – Runtime Governance for AI Agents demo video

Loading reviews

Plugin manifest

{
  "name": "agentsafe-guard",
  "version": "0.1.0",
  "description": "Add MetaMynd runtime governance to a Node agent: every tool call is allowed, refused or held for a person before it runs.",
  "author": {
    "name": "MetaMynd",
    "url": "https://metamynd.ai"
  },
  "homepage": "https://docs.metamynd.ai",
  "repository": "https://github.com/Metamynd/agentsafe-guard",
  "license": "MIT",
  "keywords": [
    "ai-agents",
    "governance",
    "authorization",
    "audit",
    "mcp",
    "security"
  ],
  "skills": "./",
  "interface": {
    "displayName": "MetaMynd AgentSafe Guard",
    "developerName": "MetaMynd",
    "shortDescription": "Allow, refuse or hold an agent's tool calls before they run",
    "longDescription": "Adds MetaMynd governance to a Node agent. Each tool call is checked against a mandate the agent cannot edit, and a refused call never reaches the tool.",
    "category": "Security",
    "capabilities": [
      "Read",
      "Write"
    ],
    "websiteURL": "https://metamynd.ai",
    "privacyPolicyURL": "https://metamynd.ai/en/legal/privacy-policy",
    "termsOfServiceURL": "https://metamynd.ai/en/legal/terms-of-service",
    "composerIcon": "./assets/logo.png",
    "logo": "./assets/logo.png",
    "screenshots": [
      "./assets/demo.png"
    ],
    "defaultPrompt": [
      "Add MetaMynd governance to this agent's tools"
    ]
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/Metamynd/agentsafe-guard
Marketplace path
.claude-plugin/marketplace.json
Source path
.
Install policy
Unspecified

Skills

1 SKILL.md file ship with this plugin. Preview, copy, or download each one, then install them with the Skills CLI.

Share
skills-cli

  • add-metamynd-governance

    skills/add-metamynd-governance/SKILL.md

    Add MetaMynd runtime governance to a Node agent project, so that tool calls are allowed, refused or held for a person before they run. Use when the user wants spend caps, allow-lists, human approval or an audit trail on what their AI agent can do, or asks to add AgentSafe Guard or MetaMynd to a project.

    Raw SKILL.md

File inventory

.claude-plugin/marketplace.json

file

478 bytes

f96208e34f169033…

.claude-plugin/plugin.json

file

485 bytes

aba762fb21340679…

.codex-plugin/plugin.json

plugin-manifest

1,224 bytes

868c25b13d9380ff…

assets/demo.png

asset

111,640 bytes

5b1dce7df5de3df7…

assets/logo.png

asset

790,644 bytes

33396da4a954c2f3…

LICENSE

file

1,420 bytes

0cab1b96e10a2549…

package-lock.json

file

41,799 bytes

ee9fc48babc114d6…

package.json

file

778 bytes

0a5b3cf534382c88…

README.md

file

8,256 bytes

5c7ffe64be37d303…

SECURITY.md

file

3,228 bytes

f9548bd3fc7be37d…

skills/add-metamynd-governance/SKILL.md

skill

4,479 bytes

8ebcd0b6f767f127…

tsconfig.json

file

306 bytes

6bb46ed5214e76f1…

Metamynd Runtime Governance for AI Agents — Frequently asked questions

What is Metamynd Runtime Governance for AI Agents?
Metamynd Runtime Governance for AI Agents is an AI plugin in the HOL registry. You can tell an AI agent to stay under its budget and use approved vendors. It will usually comply, but "usually" is not a control you can show an auditor. Metamynd Governance moves the decision out of the agent. Wrap a tool in three…
How do I install Metamynd Runtime Governance for AI Agents?
Install Metamynd Runtime Governance for AI Agents in your harness: Codex — codex plugin marketplace add Metamynd/agentsafe-guard; Claude Code — /plugin marketplace add Metamynd/agentsafe-guard; Any agent — npx [email protected] add Metamynd/agentsafe-guard. Full step-by-step guidance is on the HOL plugin page.
How do I install Metamynd Runtime Governance for AI Agents in HOL Guard?
To install Metamynd Runtime Governance for AI Agents in HOL Guard, start with hol-guard plugin install metamynd/agentsafe-guard --apply. The complete step-by-step install guide for HOL Guard is on the HOL plugin page.
How do I install Metamynd Runtime Governance for AI Agents in Codex?
To install Metamynd Runtime Governance for AI Agents in Codex, start with codex plugin marketplace add Metamynd/agentsafe-guard. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install Metamynd Runtime Governance for AI Agents in Claude Code?
To install Metamynd Runtime Governance for AI Agents in Claude Code, start with /plugin marketplace add Metamynd/agentsafe-guard. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
Is Metamynd Runtime Governance for AI Agents free?
Metamynd Runtime Governance for AI Agents is listed as free on HOL.
How is the Trust Score for Metamynd Runtime Governance for AI Agents computed?
Metamynd Runtime Governance for AI Agents has a HOL Trust Score of 94 out of 100. The score is a weighted sum of six components from a static scan of the source, capped for high-severity findings and adjusted by two disclosed policies. Memberships and payments are not inputs, and a scan is not a safety guarantee. Full breakdown: https://hol.org/registry/plugins/metamynd%2Fagentsafe-guard/trust
Who publishes Metamynd Runtime Governance for AI Agents?
Metamynd Runtime Governance for AI Agents is published by MetaMynd and listed on HOL.
Is Metamynd Runtime Governance for AI Agents available now?
Metamynd Runtime Governance for AI Agents is currently beta according to its latest public launch.

Directory acceptance

Listed in 0 of 5 directory lists

Read from the list each directory publishes on GitHub. Being listed means the directory accepted the plugin; it is not a HOL security rating.

Lists last read . HOL re-reads them every day.

Submitting it? Check it against each directory's rules

Install signal

HOL cannot see every install. These are separate signals from different sources, so they are not added together. Counts under each floor show as <N.

Install commands issued here
<5
HOL Guard install commands issued from this listing, last 28 days.
Opt-in install reports
<10
Machines that reported installing it through HOL Guard in week 2026-W45. Reporting is opt-in, so most installs are not counted.
HOL Guard workspaces
<5
Workspaces that approved it or include it in an approved-plugin feed, as of today.
New GitHub stars
<5
From HOL's GitHub snapshots of the repository, 2026-11-05 to 2026-11-12.

Related plugins

Ordered by Trust Score. Listings cannot pay for these positions. Check each one fits your task before switching from Metamynd Runtime Governance for AI Agents.

Alternatives in Tools & Integrations

See all Tools & Integrations plugins

More from MetaMynd

History, reviews, and similar plugins

Latest launch