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/franzos/claude-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/franzos/claude-plugins/infra)<a href="https://agentmods.dev/plugins/franzos/claude-plugins/infra"><img src="https://agentmods.dev/badge/plugins/franzos/claude-plugins/infra/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/franzos/claude-plugins/infra"><img src="https://agentmods.dev/badge/plugins/franzos/claude-plugins/infra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
infra 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": "infra",
"version": "0.1.0",
"description": "Infrastructure and operations specialists: reverse proxies and web servers (HAProxy, nginx, Caddy, Traefik), container runtimes (Docker, Podman), and the systemd service manager.",
"author": {
"name": "Franz",
"email": "[email protected]"
},
"license": "MIT"
}
What it installs
The manifest is a name and a version. 7 agents travel with it, and installing the plugin installs all of them — 609 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 · 11 lines scan A 1a371039fc91
infra is a plugin published in the GitHub repository franzos/claude-plugins (1 stars, last pushed 13d 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
sre-bot
SRE triage assistant for plain-English production health and Kubernetes questions in Slack. One pinned upstream Kubernetes MCP connector exposes the core toolset: reads execute immediately, six mutations require a fresh human approval, and unmatched tools fail closed. Kubernetes RBAC limits writes to disposable…
devops
VPS infrastructure management with strut: deploy Docker Compose stacks, backup databases, detect drift, rotate secrets, manage fleets, configure domains/SSL, and audit/migrate existing servers.
han-communication
Foundational communication plugin for the Han suite. Owns the canonical readability standard, the writing-voice profile, and the explanation standard for talking to a reader who will not implement the work, plus the readability-guidance skill that surfaces the first two into a calling skill's own context for in-voice…
han-research
Pre-planning knowledge-work skills for the Han suite: understanding a problem before anyone commits to a plan. Home of research (research an open-ended question and end at an adversarially-validated recommendation), gap-analysis (compare two artifacts and report what is missing, incomplete, or conflicting), and…
cloudflare-sandbox
Cloudflare Sandboxes SDK for secure code execution in Linux containers at edge. Use for untrusted code, Python/Node.js scripts, AI code interpreters, git operations.
markifact marketplace
Run Google Ads, Meta Ads, GA4, Shopify, and 50+ more platforms from Claude. 1000+ operations with human-in-the-loop on every write.