A local security add-on that checks prompts, supported tool activity, outputs, and changed files for leaked secrets, with optional filtering for personal information. It can block or mask detected leaks and adds Git and continuous-integration checks.

Use it to protect coding-agent sessions, scan working-tree changes, add commit or CI safeguards, and optionally filter personal information.

It helps prevent passwords, tokens, and other sensitive data from leaving a development session or entering a repository, without sending the checks to a remote service by default.

agent-guard — Plugin by JeongJaeSoon

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add JeongJaeSoon/agent-guard

agentmods

npx agentmods add plugins/jeongjaesoon/agent-guard/agent-guard

Clone the repo

git clone --depth 1 https://github.com/JeongJaeSoon/agent-guard

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

agent-guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/agent-guard/.claude-plugin/plugin.json · 20 lines

What it actually says

{
  "name": "agent-guard",
  "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.",
  "version": "3.0.1",
  "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": [
    "secrets",
    "gitleaks",
    "hooks",
    "security",
    "privacy"
  ]
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 20 lines scan A c080c99e31c4

Subscribe to this mod's changes

agent-guard is a plugin published in the GitHub repository JeongJaeSoon/agent-guard (24 stars, last pushed 2d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Git and workflow Security ai-agents claude-code claude-code-plugin codex devsecops github-actions

agent-guard

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

shipproof

web-app-security

deploybot

websec-plugins

usap

fettle