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.
/plugin marketplace add sembraniteam/claude-pluginsnpx agentmods add plugins/sembraniteam/claude-plugins/architecture-designergit clone --depth 1 https://github.com/sembraniteam/claude-pluginsGrade A, and why
architecture-designer 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.
What it actually says
{
"name": "architecture-designer",
"version": "0.17.2",
"description": "Guided architecture and infrastructure design workflow — from requirements gathering to code implementation — with interactive Mermaid diagrams, browser preview, and structured documentation.",
"author": {
"name": "Ahmad Rifa'i",
"email": "[email protected]"
},
"license": "MIT",
"keywords": [
"architecture",
"design",
"infrastructure",
"mermaid",
"diagrams",
"requirements",
"database",
"implementation",
"planning",
"c4",
"review",
"drift",
"remediation",
"mcp",
"web3",
"blockchain"
]
}
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 · 29 lines scan A dfcec0f2b9ab
architecture-designer is a plugin published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 29d 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
observability
Elastic Observability skills - OpenTelemetry instrumentation and migration (.NET, Java, Python), LLM observability, log search, SLOs, and service health.
sap-btp-build-work-zone-advanced
Develops and administers SAP Build Work Zone, advanced edition digital workplace solutions. Use when creating workspaces, workpages, and collaborative sites, developing UI Integration Cards in SAP Business Application Studio, building content packages and workspace templates, integrating with Microsoft…
volcengine-identity-access-control
Design and establish Volcengine landing zones, organizations, identity, account factories, and governance baselines.
helm-add-gwapi-route
Add or modernize Gateway API Route templates (HTTPRoute/GRPCRoute/TLSRoute/TCPRoute/UDPRoute) in a Helm chart. Supports both adding routes to charts that lack them and updating existing routes to current Gateway API v1.5 best practices (named rules, typed filters, current apiVersion, optional BackendTLSPolicy).
cybrix-deploy
Deploy the current static site to a live HTTPS URL via Cybrix. Detects Next.js export, Astro, Vite, Hugo, Eleventy, and plain HTML. Returns a live URL on .cbrx.cc in under 60 seconds.
homespun
Build your own software. Your AI deploys a real multi-user app with its own link, magic-link sign-in, a shared database and per-role permissions, and keeps access afterwards so it can keep operating and improving it. Bundles the homespun agent skill, which drives the homespun CLI.