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.
git clone --depth 1 https://github.com/JeongJaeSoon/agent-guardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/jeongjaesoon/agent-guard/agent-guard)<a href="https://agentmods.dev/plugins/jeongjaesoon/agent-guard/agent-guard"><img src="https://agentmods.dev/badge/plugins/jeongjaesoon/agent-guard/agent-guard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/jeongjaesoon/agent-guard/agent-guard"><img src="https://agentmods.dev/badge/plugins/jeongjaesoon/agent-guard/agent-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 today.
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.
This is a copy
86% identical to colgrep — 27 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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": "3.6.4",
"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"
]
}
What it installs
The manifest is a name and a version. 2 skills, 2 commands, 5 hooks travel with it, and installing the plugin installs all of them — 267 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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.
- today Changed 00ff85ae702d
- yesterday Changed 9a15d3c44a09
- 2d ago Changed ebca83abc098
- 5d ago Changed 05d8e983d2cd
- 13d ago Changed d46e5bb44509
- 20d ago Changed 5708ed8013ab
- 22d ago Changed 6d56b2706c92
- 26d ago Changed 41e3b003133d
- 27d ago Changed bab2ef2b5420
- 1mo ago First seen · 20 lines scan A 430a51611657
agent-guard is a plugin published in the GitHub repository JeongJaeSoon/agent-guard (33 stars, last pushed yesterday), 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. It is 86% identical to colgrep, differing in 27 lines, and is treated as a copy.
Other plugins, from other repositories
shipproof
Evidence-first engineering and production audits for secure, efficient, scalable systems.
claudeconf
Research-driven, technology-agnostic harness generator for Claude Code: pinned, standard-tool quality + security pipelines (git hooks, CI, e2e, gates, supply-chain admission, agent-hardening) plus a read-only harness-doctor agent.
gh-watch
Watch GitHub pull requests and commits for CI status, reviews, comments, and merge conflicts.
public-release-prep
Audit a private git repo's full history (every branch, tag, and PR ref) for secrets and PII before making it public, then carry out the cleanup.
github-agent-runner marketplace
Self-hosted marketplace for the github-agent-runner Claude Code plugin.
github-agent-runner
Conversational discovery and install of GitHub agent workflows (gh-aw), with auth setup that respects your Claude subscription.