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/alelaguard/agentguards-pluginsWrote 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/alelaguard/agentguards-plugins/claude-directory)<a href="https://agentmods.dev/plugins/alelaguard/agentguards-plugins/claude-directory"><img src="https://agentmods.dev/badge/plugins/alelaguard/agentguards-plugins/claude-directory/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/alelaguard/agentguards-plugins/claude-directory"><img src="https://agentmods.dev/badge/plugins/alelaguard/agentguards-plugins/claude-directory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentguards 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 yesterday.
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.
What it actually says
{
"name": "agentguards",
"displayName": "AgentGuards",
"description": "LLM security guardrails for Claude Code — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization. Enforced by hooks on every prompt, shell command, fetched page and file write. Never answers a permission prompt for you: it blocks or asks, and Claude Code's own permission rules decide everything else.",
"version": "0.2.39",
"author": {
"name": "AgentGuards",
"email": "[email protected]",
"url": "https://agentguards.co"
},
"homepage": "https://agentguards.co",
"repository": "https://github.com/alelaguard/agentguards-plugins",
"license": "FSL-1.1-MIT",
"userConfig": {
"agentguards_api_key": {
"type": "string",
"title": "AgentGuards API key",
"description": "Optional fallback for the hooks when AGENTGUARDS_API_KEY is not already set. The easiest way to set your key is to run /agentguards:setup in an Agent Mode or Local Code session and let Claude save it for you. Note the Claude Desktop app never reads a shell profile, so an export will not reach it.",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 3 skills, 3 hooks travel with it, and installing the plugin installs all of them — 143 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 23 lines scan A 0f8ca8c2547b
agentguards is a plugin published in the GitHub repository alelaguard/agentguards-plugins (4 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other plugins, from other repositories
agentlint
Claude Code marketplace wrapper for AgentLint's AI-agent guardrail engine. 77 rules across 8 packs, hybrid AgentChute security feeds, circuit-breaker visibility, inline-ignore reasons.
bridgeward
Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.
sll
Three hooks, no agents. A stated test result must reproduce, a fabricated import never reaches disk, and every command's real output is recorded. Active in every project the moment it is installed.
auto-cc
Automatic tool-call review for Claude Code. A local encoder scores every proposed tool call before it runs, approving safe work and blocking dangerous calls with an explanation the agent can act on.
cybersecurity-pro
Professional cybersecurity skill: 22 domains covering IR, DFIR, DevSecOps, SOC+SOAR, GitOps, Code Security, Container/Supply Chain, Threat Modeling, Compliance Frameworks, Cloud Security & CSPM, Zero Trust Architecture, AI/ML Security, API Security, Vulnerability Management, Threat Intelligence, Cross-Domain…
deployshield
Production safety guardrails that block write/mutating operations on cloud, database, IaC, and deployment CLIs.