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 osouthgate/agent-plus-skillsnpx agentmods add plugins/osouthgate/agent-plus-skills/vercel-remotegit clone --depth 1 https://github.com/osouthgate/agent-plus-skillsGrade A, and why
vercel-remote 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": "vercel-remote",
"description": "Read-first wrapper around the Vercel REST API — one-call project overviews (deployments, domains, env NAMES-only), name-resolved projects, --wait on async flows, --json on lists. Zero env-var-value leakage.",
"version": "0.4.0",
"author": {
"name": "Oliver Southgate",
"url": "https://github.com/osouthgate"
},
"homepage": "https://github.com/osouthgate/agent-plus-skills",
"repository": "https://github.com/osouthgate/agent-plus-skills",
"license": "MIT",
"keywords": [
"vercel",
"devops",
"observability",
"deploy",
"deployments",
"incident-triage"
],
"agent_plus_version": ">=0.7",
"refresh_handler": {
"command": "vercel-remote whoami --json",
"timeout_seconds": 10,
"identity_keys": ["username", "team"],
"failure_mode": "soft"
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 117 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.
- 2d ago First seen · 28 lines scan A dd68a282c3ca
vercel-remote is a plugin published in the GitHub repository osouthgate/agent-plus-skills (2 stars, last pushed 3mo 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
kastell
Server security auditing, hardening, and fleet management. Runtime-derived audit catalog, CIS/PCI-DSS/HIPAA compliance, production hardening workflows, and first-party MCP tools. Supports Hetzner, DigitalOcean, Vultr, Linode with Coolify, Dokploy, and bare VPS modes.
aws-skills marketplace
Plugin marketplace listing 5 plugins: aws-common, aws-iac, aws-cost-ops, serverless-eda, aws-agentic-ai.
kastell-plugin
Autonomous server security and infrastructure management. First-party MCP tools for cloud server provisioning, security auditing, hardening, backup, and fleet management across Hetzner, DigitalOcean, Vultr, and Linode.
alibabacloud-ecs-ops
Alibaba Cloud ECS 全生命周期运维管理插件,覆盖实例管理、诊断排障、磁盘快照、安全组网络及场景化运维,集成操作前成本评估能力.
alibabacloud-spec-ops
Alibaba Cloud AI Ops Plugin - Infrastructure operations workflow with intelligent planning, validation, and execution powered by MCP tooling.
github-talent-marketplace
Plugin marketplace listing 1 plugin: github-talent-mcp.