SkyPilot is a system for running, managing, and scaling AI workloads across different computing infrastructure through one interface. AI teams use it for jobs such as machine learning, hyperparameter tuning, and inference, while infrastructure teams use it for scheduling, scaling, and orchestration.
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/skypilot-org/skypilotWrote 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/skypilot-org/skypilot/agent)<a href="https://agentmods.dev/plugins/skypilot-org/skypilot/agent"><img src="https://agentmods.dev/badge/plugins/skypilot-org/skypilot/agent/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/skypilot-org/skypilot/agent"><img src="https://agentmods.dev/badge/plugins/skypilot-org/skypilot/agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
skypilot 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.
This is a copy
86% identical to skypilot marketplace — 27 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"name": "skypilot",
"description": "SkyPilot agent skill for launching cloud VMs, Kubernetes pods, and Slurm jobs across 25+ clouds",
"version": "1.0.0",
"author": {
"name": "SkyPilot Team"
},
"homepage": "https://docs.skypilot.co/",
"repository": "https://github.com/skypilot-org/skypilot",
"license": "Apache-2.0",
"keywords": ["AI Infrastructure", "Multi-Cloud", "GPU", "Kubernetes", "Slurm", "Training", "Serving", "Cost Optimization", "SkyPilot"]
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 168 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 · 13 lines scan A 30a8967b0b3b
skypilot is a plugin published in the GitHub repository skypilot-org/skypilot (10,713 stars, last pushed today), licensed Apache-2.0. 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. It is 86% identical to skypilot marketplace, differing in 27 lines, and is treated as a copy.
Other plugins, from other repositories
lepton-cli
Operate NVIDIA DGX Cloud Lepton through the globally installed lep CLI.
gpu-server-setup
Prepare a Linux server with NVIDIA GPUs for LLM and neural-network workloads: NVIDIA driver + CUDA from the official repo, Docker Engine + NVIDIA Container Toolkit as the mandatory base, GPU passthrough into containers, staged verification gates, optional docker-compose presets for vLLM, Infinity, OpenWebUI and Ollama.
agent-sandboxing
Agent sandboxing for AI coding agents: microVM and kernel-isolated execution environments. Index skill (sandbox) routes to substrate-specific paths. Currently covers the kubernetes-sigs/agent-sandbox path on kind, GKE, and kina (Kubernetes-in-Apple-Containers), with Kata, gVisor, and Apple Container microVM substrates.
ensemble-infrastructure
Infrastructure management for AWS, Kubernetes, Docker, Helm, Fly.io.
security-hardening
System hardening and CIS Benchmark assessment for Linux and Windows hosts, containers, Kubernetes, web servers, databases, and cloud accounts, with implementation and verification steps.
open-forge
Self-host open-source apps on your own cloud, your own VPS, your own Kubernetes cluster, a PaaS, or your own laptop. Chat-friendly interface to existing tools (aws, az, hcloud, doctl, gcloud, flyctl, kubectl, helm, podman, docker, lume, tailscale, terraform, cdk, ssh, gh) — Claude runs every command; you only answer…