Agent Guard

Local-by-default, no-telemetry hooks block or mask secret leaks in Claude Code and Codex, with opt-in PII filtering and Git/CI backstops.

agent-guard-contributors/agent-guard · v3.5.4 · Development & Workflow

Agent Guard contributorsreview

Install Source Claim this plugin

74 Follow0

Trust Score

Security

Surfaces

What is Agent Guard?

Agent Guard is a published development & workflow plugin for AI coding agents in the claude-code ecosystem, developed by Agent Guard contributors and distributed through the HOL AI plugin registry. Local-by-default, no-telemetry hooks block or mask secret leaks in Claude Code and Codex, with opt-in PII filtering and Git/CI backstops.

Canonical slug: agent-guard-contributors/agent-guard
Version: v3.5.4 · updated Sep 28, 2026
Open data: entity.json (JSON-LD)

Trust & Reputation

HOL Trust Score

Factor Analysis

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

Installability

76pts

Maintenance

55pts

MCP Posture

100pts

Plugin Security

71pts

Provenance

70pts

Publisher Quality

75pts

Registry Snapshot

Repository: https://github.com/JeongJaeSoon/agent-guard
Homepage: https://github.com/JeongJaeSoon/agent-guard
Canonical profile: https://hol.org/registry/plugins/agent-guard-contributors%2Fagent-guard
Publisher verification: No
Marketplace source: Unknown
Scanner: Broker fallback
Safety label: review
Digest verified: Yes

4 bundled skills — copy or download SKILL.mdOpen skills

Trust & reputation

Trust & Reputation

HOL Trust Score

Factor Analysis

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

Installability

76pts

Maintenance

55pts

MCP Posture

100pts

Plugin Security

71pts

Provenance

70pts

Publisher Quality

75pts

Provenance

Plugin root: plugins/agent-guard
Source repo: https://github.com/JeongJaeSoon/agent-guard
Source commit: 5771d8e84265…
Publisher verified: No
Owner verified: Not owner verified

Continuous scanner CI detected

No action is required. This plugin receives the full trust score.

Verified badge not detected

Add the HOL verified badge to the repository README to score +2% trust. Plugin owners can open that pull request from Guard Plugins.

Security Posture

review

Safety label

Security score

High findings

Provider: registry-broker-fallback
Grade: C · review
Version: Unknown

cisco-skill-scanner: unknown

Findings

mediumpublishabilitypublishability.link.missing.privacyPolicyURL

privacyPolicyURL should be present for marketplace readiness.

mediumpublishabilitypublishability.link.missing.termsOfServiceURL

termsOfServiceURL should be present for marketplace readiness.

lowoperational-securitysupply-chain.lockfile-missing

Repository snapshot does not include a lockfile.

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

infoskill-securityskill-scan.unavailable

Cisco skill scanner timed out after 60000 ms

Agent Guard — Frequently asked questions

What is Agent Guard?: Agent Guard is an AI plugin in the HOL registry. Local-by-default, no-telemetry hooks block or mask secret leaks in Claude Code and Codex, with opt-in PII filtering and Git/CI backstops.
How do I install Agent Guard?: Install Agent Guard in your harness: Codex — codex plugin marketplace add JeongJaeSoon/agent-guard; Claude Code — /plugin marketplace add JeongJaeSoon/agent-guard; Any agent — npx skills add JeongJaeSoon/agent-guard. Full step-by-step guidance is on the HOL plugin page.
How do I install Agent Guard in Codex?: To install Agent Guard in Codex, start with codex plugin marketplace add JeongJaeSoon/agent-guard. The complete step-by-step install guide for Codex is on the HOL plugin page.
How do I install Agent Guard in Claude Code?: To install Agent Guard in Claude Code, start with /plugin marketplace add JeongJaeSoon/agent-guard. The complete step-by-step install guide for Claude Code is on the HOL plugin page.
Is Agent Guard free?: Pricing for Agent Guard is published on its HOL plugin page when the maker schedules a launch.
Who publishes Agent Guard?: Agent Guard is published by Agent Guard contributors and listed on HOL.
Is Agent Guard available now?: Agent Guard availability is listed on its HOL plugin page.

Install Guidance

Install in Claude Code

Install through the Claude Code plugin marketplace.

Claude Code plugin docs

1
Add the marketplace
Run this inside a Claude Code session.
claude code
2
Install the plugin
Use the plugin name and the marketplace name shown by the previous command.
claude code
3
Scripted alternative
Non-interactive equivalent for scripts and CI pipelines. Add --scope project to pin the install to one repository.
shell

Plugin Manifest

{
  "name": "agent-guard",
  "version": "3.5.4",
  "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": "./",
  "interface": {
    "displayName": "Agent Guard",
    "developerName": "Agent Guard contributors",
    "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.",
    "category": "Developer Tools",
    "capabilities": [
      "Read"
    ],
    "websiteURL": "https://github.com/JeongJaeSoon/agent-guard",
    "brandColor": "#14532D",
    "composerIcon": "./assets/icon.png",
    "screenshots": []
  },
  "registryIndexVersion": 5
}

Marketplace Source

Repo URL: https://github.com/JeongJaeSoon/agent-guard
Marketplace path: Unknown
Source path: plugins/JeongJaeSoon/agent-guard
Install policy: AVAILABLE

Skills

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

skills-cli

setup-agent-guard
codex-skills/setup-agent-guard/SKILL.md
Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection. Use when Agent Guard reports degraded protection, a SessionStart warning asks for setup, plugin hooks fail or appear bypassed, or a user asks to finish or repair Agent Guard installation.
Raw SKILL.md
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
setup-shell
codex-skills/setup-shell/SKILL.md
Install or refresh Agent Guard's plugin-local shell integration. Use when the user explicitly asks to enable or update shell command masking, or when a shell-integration warning directs them to rerun setup-shell.
Raw SKILL.md
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
setup-agent-guard
skills/setup-agent-guard/SKILL.md
Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection. Use when Agent Guard reports degraded protection, a SessionStart warning asks for setup, plugin hooks fail or appear bypassed, or a user asks to finish or repair Agent Guard installation.
Raw SKILL.md
SKILL.md content is not in this snapshot. Open the raw file to copy it from the source repository.
setup-shell
skills/setup-shell/SKILL.md
Install or refresh Agent Guard's plugin-local shell integration. Use when the user explicitly asks to enable or update shell command masking, or when a shell-integration warning directs them to rerun setup-shell.
Raw SKILL.md
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

651 bytes

5708ed8013ab8941…

.codex-plugin/plugin.json

plugin-manifest

1,416 bytes

bf5a7c7970aadb12…

assets/icon.png

asset

20,564 bytes

ab66827c34bcddbf…

codex-skills/setup-agent-guard/agents/openai.yaml

file

338 bytes

25d7bf25bfdf4fcb…

codex-skills/setup-agent-guard/SKILL.md

skill

672 bytes

c3aff99b9faedba4…

codex-skills/setup-shell/agents/openai.yaml

file

212 bytes

0776c4eca9f10429…

codex-skills/setup-shell/SKILL.md

skill

502 bytes

023af838e5dbf44d…

commands/checksum.md

file

1,353 bytes

50991b6d54746d8d…

commands/verify.md

file

3,233 bytes

7892e2b49444dc65…

hooks.json

file

12,700 bytes

a3aa8bde1879123a…

hooks/hooks.json

file

13,016 bytes

c5971cef3e4cff88…

README.md

file

3,189 bytes

efce7e6b224b7b20…

SECURITY.md

file

1,775 bytes

26ac5b8ccdbf64ed…

skills/setup-agent-guard/SKILL.md

skill

10,376 bytes

3f111fc4ef4ff59a…

skills/setup-shell/SKILL.md

skill

2,023 bytes

9a3d293486fc340b…

Product

AI tools

Extensions

Resources

AI Agents

Plugins

Extensions

Best Plugins

Security

Open Source

Points

Events

Standards

Tools

Library Docs

Resources

Agent Guard

What is Agent Guard?

Trust & Reputation

Factor Analysis

Registry Snapshot

Trust & reputation

Trust & Reputation

Factor Analysis

Provenance

Security Posture

Findings

Agent Guard — Frequently asked questions

Install Guidance

Install in Claude Code

Plugin Manifest

Marketplace Source

Skills

File Inventory