AgentAvow Trust icon

AgentAvow Trust

agentavow/agentavow-trust · v0.1.45 · Development & Workflow

Checks your MCP servers at session start and stops a codex mcp add or package install that reads Do not connect, with the reason and a signed 0-100 trust score.

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 AgentAvow Trust a fit?

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

Works with

  • MCP
  • Codex
  • Claude Code
  • 1 skill
  • 1 MCP server
  • Runs hooks on agent events

Before you install

Sign-in
Asks you to sign in when you install it
Declared access
Read
License
MIT

Check before relying on it

  • Some security checks did not finish: Cisco skill scan and Cisco MCP scan. See the evidence
  • The publisher has not verified ownership on HOL.

What is AgentAvow Trust?

AgentAvow Trust is a published development & workflow plugin for AI coding agents that works with MCP, Codex and Claude Code, developed by AgentAvow and distributed through the HOL AI plugin registry. Checks your MCP servers at session start and stops a `codex mcp add` or package install that reads Do not connect, with the reason and a signed 0-100 trust score.

Canonical slug
agentavow/agentavow-trust
Version
v0.1.45 · updated Nov 18, 2026

Registry snapshot

Owner verification
Not verified
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

80

HOL Trust Score

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

Installability
100/100
Maintenance
65/100
MCP server setup
100/100
Plugin Security
98/100
Provenance
70/100
Publisher Quality
75/100

Provenance

Plugin root
.
Source repo
https://github.com/AgentAvow/agentavow-codex-plugin
Source commit
5a884e33d49f…
Publisher verified
No
Owner verified
Not owner verified
Agent Plugins 1.0
Not detected

Continuous scanner CI not detected

This plugin remains listed. Its overall trust score is reduced by 10% because security checks are not maintained in the source repository's CI.

Optional: maintain the scanner in the source repository's CI to receive the full trust score. Listing does not require that change.

README badge not detected

Plugin owners can add the HOL badge to the repository README from Guard Plugins. Distribution, not security evidence. It adds a 2% engagement adjustment to the overall trust score and never changes the security result.

Partial scan
Security result
98
Score from finished checks
0
High findings

Some checks did not finish: Cisco skill scan and Cisco MCP 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-u2SAtT / cisco-skill-scanner: failedcodex:hol-plugin-scanner-u2SAtT / cisco-mcp-scanner: unavailable

[claude:.] Claude Plugin

18/18

5 checks

[claude:.] Security

24/24

6 checks

[claude:.] Operational Security

N/A

5 checks · not applicable

[claude:.] Code Quality

10/10

2 checks

[codex:.] Manifest Validation

28/31

9 checks

[codex:.] Security

24/24

9 checks

[codex:.] Operational Security

N/A

5 checks · not applicable

[codex:.] Best Practices

12/12

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

infomanifest-validationPLUGIN_JSON_INTERFACE_ASSET_SCREENSHOTS

The interface field "screenshots" must use HTTPS or point to a safe in-repo asset.

Update "screenshots" to use HTTPS or an existing relative asset path.

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

    Find the marketplace and plugin names

    The install id is <plugin-entry>@<marketplace-name>, and the marketplace name is declared inside the manifest — it can differ from the repository name. List registered marketplaces to read both names.

    shell
  3. 3

    Install the plugin

    Substitute the plugin entry name and the marketplace name shown by the previous step.

    claude code

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-W46, 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.

Loading reviews

Plugin manifest

{
  "name": "agentavow-trust",
  "version": "0.1.45",
  "description": "Checks your MCP servers and packages with AgentAvow before Codex uses them. When a session starts it checks the servers in ~/.codex/config.toml and a trusted project's .codex/config.toml. When Codex runs codex mcp add, or installs a package by name with npm, pnpm, yarn, bun, pip, uv, pipx or poetry, it checks that exact version first: Do not connect stops the step and says why, Review before you connect is a one-line note, and Safe to connect stays silent. Every answer has its reason and a signed 0-100 trust score you can verify offline. Also bundles the AgentAvow connector and the scan-before-connect skill. The hooks run only while you trust them (/hooks). Fail-open. What leaves your machine: the server URL or package name being checked, and a random install ID used only to count active installs, also sent once a day with the plugin version and app type (turn it off with AGENTAVOW_ANON_ID=off).",
  "author": {
    "name": "AgentAvow",
    "url": "https://agentavow.com"
  },
  "homepage": "https://agentavow.com/docs/codex",
  "repository": "https://github.com/AgentAvow/agentavow-codex-plugin",
  "license": "MIT",
  "keywords": [
    "security",
    "trust",
    "mcp",
    "supply-chain",
    "code-scanning",
    "attestation"
  ],
  "skills": "./",
  "hooks": "./hooks/hooks.json",
  "mcpServers": "./.registry/mcp.json",
  "commands": [
    "./commands/"
  ],
  "scripts": "./scripts/",
  "interface": {
    "displayName": "AgentAvow Trust",
    "developerName": "AgentAvow",
    "shortDescription": "Is this tool safe to connect?",
    "longDescription": "AgentAvow checks an MCP server or package before Codex adds or installs it, and answers in plain words: Safe to connect, Review before you connect, or Do not connect, with the reason. Underneath are a 0-100 trust score, backed by a signed attestation anyone can verify offline, and an adoption score. In the Codex CLI and desktop app the plugin's hooks check your servers at session start and stop a codex mcp add or package install that reads Do not connect. The bundled connector and skill answer when you ask about a tool. No account and no sign-in.",
    "category": "Developer Tools",
    "capabilities": [
      "Read"
    ],
    "websiteURL": "https://agentavow.com/docs/codex",
    "privacyPolicyURL": "https://agentavow.com/legal/privacy",
    "termsOfServiceURL": "https://agentavow.com/legal/terms",
    "defaultPrompt": [
      "Is the npm package chalk safe to install?"
    ],
    "composerIcon": "./icon.png",
    "logo": "./icon.png"
  },
  "holManifestOrigin": "repository",
  "registryIndexVersion": 9
}

Marketplace source

Repo URL
https://github.com/AgentAvow/agentavow-codex-plugin
Marketplace path
Unknown
Source path
plugins/AgentAvow/agentavow-codex-plugin
Install policy
AVAILABLE

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
  • scan-before-connect

    skills/scan-before-connect/SKILL.md

    Scan an MCP server, a package (npm, PyPI, crates, Docker, Hugging Face), or a GitHub repo with AgentAvow before it is added, installed, or connected. Use when the user asks you to add or install a new MCP server, plugin, package, or tool from a repo, or asks whether one is safe or trustworthy.

    SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.

File inventory

.claude-plugin/plugin.json

file

2,067 bytes

8dfa69a5cde728f7…

.codex-plugin/plugin.json

plugin-manifest

2,451 bytes

c5637f9a6912d82d…

.codexignore

file

128 bytes

acd1f9a9b562382a…

.mcp.json

file

125 bytes

bfc71c130d113fc8…

.registry/mcp.json

mcp-config

89 bytes

76e6d93f5ccea5c3…

commands/scan.md

file

2,191 bytes

01db28a72f8ba8fc…

hooks/hooks.json

file

975 bytes

95fd866c41b8715c…

icon.png

file

48,860 bytes

9357f95b33773732…

LICENSE

file

1,424 bytes

23a211bf2d4ed6a5…

README.md

file

21,811 bytes

c483fc7662d54683…

SECURITY.md

file

1,473 bytes

037e8982cb3b8990…

skills/scan-before-connect/SKILL.md

skill

5,509 bytes

e4a9652b5e57a166…

AgentAvow Trust — Frequently asked questions

What is AgentAvow Trust?
AgentAvow Trust is an AI plugin in the HOL registry. Checks your MCP servers at session start and stops a codex mcp add or package install that reads Do not connect, with the reason and a signed 0-100 trust score.
How do I install AgentAvow Trust?
Install AgentAvow Trust in your harness: Codex — codex plugin marketplace add AgentAvow/agentavow-codex-plugin; Claude Code — /plugin marketplace add AgentAvow/agentavow-codex-plugin; MCP — git clone https://github.com/AgentAvow/agentavow-codex-plugin. Full step-by-step guidance is on the HOL plugin page.
How do I install AgentAvow Trust in Codex?
To install AgentAvow Trust in Codex, start with codex plugin marketplace add AgentAvow/agentavow-codex-plugin. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install AgentAvow Trust in Claude Code?
To install AgentAvow Trust in Claude Code, start with /plugin marketplace add AgentAvow/agentavow-codex-plugin. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
How do I install AgentAvow Trust in MCP?
To install AgentAvow Trust in MCP, start with git clone https://github.com/AgentAvow/agentavow-codex-plugin. The complete step-by-step install guide for MCP is on the HOL plugin page.
How is the Trust Score for AgentAvow Trust computed?
AgentAvow Trust has a HOL Trust Score of 80 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/agentavow%2Fagentavow-trust/trust
Who publishes AgentAvow Trust?
AgentAvow Trust is published by AgentAvow and listed on HOL.

Directory acceptance

Listed in 1 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-W46. 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.

Reviews and similar plugins