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/skillmds/skillmdWrote 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/skillmds/skillmd/cloud-devops)<a href="https://agentmods.dev/plugins/skillmds/skillmd/cloud-devops"><img src="https://agentmods.dev/badge/plugins/skillmds/skillmd/cloud-devops/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/skillmds/skillmd/cloud-devops"><img src="https://agentmods.dev/badge/plugins/skillmds/skillmd/cloud-devops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cloud-devops 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 4d 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": "cloud-devops",
"description": "Docker, Kubernetes, CI/CD and cloud (AWS/Azure/GCP) automation.",
"version": "1.0.0",
"author": {
"name": "SkillMD"
},
"homepage": "https://skillmd.com/plugins/skillmd/cloud-devops"
}
What it installs
The manifest is a name and a version. 23 skills travel with it, and installing the plugin installs all of them — 1,889 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill serenity A 135 tokens
- Skill 04-security A 36 tokens
- Skill warden-agent-builder A 106 tokens
- Skill adp A 181 tokens
- Skill fsc-data-model A 139 tokens
- Skill audit A 50 tokens
- Skill infrastructure-drift-detection A 19 tokens
- Skill aws-batch A 57 tokens
- Skill gke-basics A 4 tokens
- Skill glab A 107 tokens
- Skill preset A 22 tokens
- Skill Mintlify-design-analysis A 129 tokens
- Skill HashiCorp-design-analysis A 158 tokens
- Skill IBM-design-analysis A 135 tokens
- Skill Dokku Docker-Powered Mini-Heroku Self-Hosted PaaS A 83 tokens
- Skill dbt Cloud MCP A 4 tokens
- Skill cloud-sync C 64 tokens
- Skill docker-expert A 60 tokens
- Skill hyperframes-cli A 129 tokens
- Skill bpmn-generator A 202 tokens
- Skill surrealism A 37 tokens
- Skill AWS S3 MCP Server A 5 tokens
- Skill deck-blueprint A 27 tokens
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.
- 4d ago First seen · 10 lines scan A cb291bb6bfa6
cloud-devops is a plugin published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), 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 2026-09-19.
Other plugins, from other repositories
cc-arsenal-dev
Development skills: feature implementation, bug fixing, testing, refactoring, CI/CD generation, framework documentation injection, project planning, image generation (Nano Banana/Gemini and Codex imagegen), database migrations, Docker setup, environment setup, visual regression checks, i18n checks, release shipping…
jk
GitHub CLI-style interface for Jenkins controllers - create multibranch jobs, inspect config.xml, and manage runs, logs, artifacts, credentials, nodes, and queues.
poly
Zero-dependency lint & format orchestrator over MCP — one pure-Rust binary wrapping ruff/oxc/taplo/rumdl and more as in-process backends, plus a tree-sitter generic tier for everything else. Exposes lint/format/cache tools with structured JSON output.
deployment-engineer
Use this agent when setting up CI/CD pipelines, configuring Docker containers, deploying applications to cloud platforms, setting up Kubernetes clusters, implementing infrastructure as code, or automating deployment workflows. Examples: Context: User is setting up a new project and needs deployment automation.
ensemble-infrastructure
Infrastructure management for AWS, Kubernetes, Docker, Helm, Fly.io.
ci-incident-medic
Triages failing GitHub Actions runs, hardens Dockerfiles, pre-flights Kubernetes manifests before they reach the cluster, and drafts blameless postmortems from incident evidence.