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 LayeroInfra/layero-claudenpx agentmods add plugins/layeroinfra/layero-claude/layerogit clone --depth 1 https://github.com/LayeroInfra/layero-claudeGrade A, and why
layero 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": "layero",
"description": "Собрать лендинг прямо в чате Claude Code и задеплоить его на Layero — хостинг с серверами и CDN в России.",
"version": "1.0.0",
"author": {
"name": "Layero",
"url": "https://layero.ru"
},
"homepage": "https://docs.layero.ru/plugin/intro",
"repository": "https://github.com/LayeroInfra/layero-claude",
"license": "MIT",
"keywords": [
"deploy",
"deployment",
"hosting",
"cdn",
"landing-page",
"static-site",
"russia",
"mcp"
]
}
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 e6c5a47bbd1d
layero is a plugin published in the GitHub repository LayeroInfra/layero-claude (0 stars, last pushed 26d 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
openpouch
Agent-native hosting: deploy any app or static site to a live URL in one command — no account, no CAPTCHA. Bundles the openpouch MCP tools and a deploy skill with verify + self-repair workflows.
saas-builder
Build a complete, professional digital product end to end — discovery, architecture, secure backend, auth, payments, performance, accessibility, SEO, and deploy — not generic AI output. A router skill asks 2-3 questions (English or Spanish), then activates the right specialist across the whole build lifecycle.…
waitlister
Create product-launch waitlists and publish hosted landing pages without leaving Claude.
sealos-skills
Plugin marketplace listing 1 plugin: sealos.
sealos-skills
Deploy local or GitHub projects to Sealos Cloud, connect cloud databases and S3 object storage, generate Dockerfiles and Sealos templates, assess cloud-native readiness, and build Sealos Desktop apps.
production-readiness-plugins
Plugin marketplace listing 1 plugin: production-readiness.