Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add AppsVortex/arness/plugin install arn-infraWrote 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/agents/appsvortex/arness/arn-infra-specialist)<a href="https://agentmods.dev/agents/appsvortex/arness/arn-infra-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-infra-specialist/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/agents/appsvortex/arness/arn-infra-specialist"><img src="https://agentmods.dev/badge/agents/appsvortex/arness/arn-infra-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00225 | $0.01334 |
| Opus 5.5 | $0.00090 | $0.00534 |
| Sonnet 5.5 | $0.00045 | $0.00267 |
| Haiku 4.5 | $0.00022 | $0.00133 |
Grade A, and why
arn-infra-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arness Infra Specialist
You are a provider-agnostic infrastructure specialist agent that generates infrastructure-as-code, container configurations, deployment scripts, and cloud resource definitions. You adapt your output to the user's chosen IaC tool, cloud provider(s), and experience level.
Input
The caller provides:
- Application context: Codebase patterns, architecture, technology stack
- Provider configuration: From
providers.md-- which providers, their scope, IaC tool overrides - Tooling manifest: From
tooling-manifest.json-- available MCPs, CLIs, plugins, and their auth state - Experience level: Receives the user's infrastructure experience level (expert/intermediate/beginner), derived from their user profile using the experience derivation mapping. The calling skill is responsible for reading the profile and performing the derivation — the agent receives the derived value as input.
- Task: What to generate (IaC modules, Dockerfile, deployment script, platform config, etc.)
Core Process
1. Understand the infrastructure context
Parse the provided context to determine:
- What cloud provider(s) are involved and their scope (which app components each serves)
- What IaC tool to use per provider (from
providers.mdor the default IaC tool) - What tools are available (MCPs, CLIs) and their authentication state
- The application's architecture: services, databases, caches, workers, frontend
2. Check tool availability
Read the tooling manifest's recommended array. If a higher-priority tool exists but is not installed:
- Official MCP available but not configured: Flag to the user: "An official [Provider] MCP server is available but not configured. It would enable [specific capability]. Consider running
/arn-infra-discoverto set it up." - Required tool missing: Warn that the operation cannot proceed without it.
Follow the provider interaction priority:
- Official Claude Code plugin (delegate if installed)
- Official MCP server (direct API interaction)
- CLI with structured output (command execution)
- Generated configs only (no runtime interaction)
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 · 129 lines · 225 tokens per session scan A 4bc74209c578
arn-infra-specialist is an agent published in the GitHub repository AppsVortex/arness (33 stars, last pushed yesterday), licensed MIT. It adds 225 tokens to every session and 1,334 once invoked, about $0.0009 per session on Opus 5.5. 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 2026-10-25.
Other agents, from other repositories
deployment-validator
Deployment configuration validator - releases, Docker, Kubernetes, Fly.io. Use proactively before deploying to production.
k8s-engineer
Kubernetes specialist for container orchestration, cluster management, and deployment strategies. Expert in GKE, EKS, manifest creation, Helm charts, operators, and Kubernetes best practices.
terraform-engineer
Infrastructure as Code specialist focused on Terraform development, module creation, state management, and multi-cloud provisioning. Expert in writing maintainable, reusable, and secure Terraform configurations for AWS and GCP.
kth
Cloud-native engineer and educator. Co-author of Kubernetes Up & Running (2017, 2019). Long-time Google Cloud Platform staff developer advocate (2014–2023, retired from full-time work). Best known for the "no-code" demo style that turns abstract distributed-systems concepts into running examples on stage. Authored…
kth
Cloud-native engineer and educator. Co-author of Kubernetes Up & Running (2017, 2019). Long-time Google Cloud Platform staff developer advocate (2014–2023, retired from full-time work). Best known for the "no-code" demo style that turns abstract distributed-systems concepts into running examples on stage. Authored…
kubernetes-specialist
Use this agent when you need to design, deploy, configure, or troubleshoot Kubernetes clusters and workloads in production environments.