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/yongquantan/dependency-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/yongquantan/dependency-guard/plugin)<a href="https://agentmods.dev/plugins/yongquantan/dependency-guard/plugin"><img src="https://agentmods.dev/badge/plugins/yongquantan/dependency-guard/plugin/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/yongquantan/dependency-guard/plugin"><img src="https://agentmods.dev/badge/plugins/yongquantan/dependency-guard/plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
dependency-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 1mo 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.
What it actually says
{
"name": "dependency-guard",
"description": "A dependency security plugin for Claude Code. DepGuard intercepts package installs, checks reputation with Socket.dev, runs installs in a Modal sandbox, and blocks suspicious behavior before it reaches your machine.",
"version": "0.1.0",
"author": {
"name": "Yong Quan",
"email": "[email protected]"
},
"homepage": "https://github.com/yongquantan/dependency-guard",
"repository": "https://github.com/yongquantan/dependency-guard",
"license": "MIT",
"keywords": ["security", "supply-chain", "dependencies", "claude-code", "plugin", "hooks", "guardrails", "modal", "socket.dev"],
"userConfig": {
"socket_api_token": {
"title": "Socket.dev API Token",
"description": "For reputation checks. Free at https://socket.dev",
"type": "string",
"sensitive": true
},
"modal_token_id": {
"title": "Modal Token ID",
"description": "For sandbox analysis. Run 'modal token new' at https://modal.com",
"type": "string",
"sensitive": true
},
"modal_token_secret": {
"title": "Modal Token Secret",
"description": "From the same 'modal token new' command",
"type": "string",
"sensitive": true
}
}
}
What it installs
The manifest is a name and a version. 1 skill, 1 command, 2 hooks travel with it, and installing the plugin installs all of them — 0 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.
- 1mo ago First seen · 34 lines scan A a61459ab5519
dependency-guard is a plugin published in the GitHub repository yongquantan/dependency-guard (7 stars, last pushed 6mo 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 2026-08-31.
Other plugins, from other repositories
yoink
A plugin to clone dependencies you don't trust. No more supply chain attacks.
autopilot
A collection of five plugins: summarizer, task-notifier, autopilot, writer-skill, and npm-toolkit.
writer-skill
A writing package with styles for blog posts, technical documentation, and professional technology blogs, plus a tool for reviewing technical articles.
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…
planwright
Autopilot for spec-driven development. The human signs off and merges; planwright flies the spec. Scales to a multi-spec fleet: an agentic software factory on Claude Code primitives.
app-dev-team
An autonomous app development studio for Claude Code. 30 role agents (CEO/CPO/CTO, chief-of-staff, product-manager/validator/researcher, tech-lead/tech-manager, iOS/Android/backend/web devs, monetization, ux-architect/product-designer, code review, QA, test-automation, verification, release-auditor/manager, security…