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 pulumi/agent-skillsnpx agentmods add plugins/pulumi/agent-skills/migrationgit clone --depth 1 https://github.com/pulumi/agent-skillsGrade A, and why
migration 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": "pulumi-migration",
"version": "1.0.0",
"description": "Convert and import infrastructure from Terraform, CDK, ARM, and CloudFormation to Pulumi",
"author": {
"name": "Pulumi",
"url": "https://github.com/pulumi"
},
"homepage": "https://www.pulumi.com/docs/",
"repository": "https://github.com/pulumi/agent-skills",
"license": "Apache-2.0",
"keywords": [
"pulumi",
"terraform",
"cdk",
"arm",
"migration",
"import"
]
}
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 · 21 lines scan A 60269b043f26
migration is a plugin published in the GitHub repository pulumi/agent-skills (67 stars, last pushed 3d ago), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
vidanov-skills
AWS architecture diagram generation skill with verified icons and reference templates.
arn-marketplace
The compound-engineering harness for Claude Code — durable artifacts hand off from discovery through deployment. Spark (idea), Code (build), Infra (ship).
terraform-lsp
Claude Code plugin for Terraform development with terraform-ls LSP integration, 17 automated hooks for security scanning (trivy, checkov), linting (tflint), formatting, and Terragrunt support.
terraform-lsp-claude-code
Terraform language server plugin for Claude Code - provides code intelligence for infrastructure as code.
terraform-lsp
Terraform language server (terraform-ls) for code intelligence, go-to-definition, find-references, and hover docs in Terraform files (.tf, .tfvars, .tftest.hcl).
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.