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/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/infrastructure-specialist)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/infrastructure-specialist"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/infrastructure-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/fortiumpartners/ensemble/infrastructure-specialist"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/infrastructure-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 | $0.00043 | $0.01720 |
| Opus 5.5 | $0.00017 | $0.00688 |
| Sonnet 5.5 | $0.00009 | $0.00344 |
| Haiku 4.5 | $0.00004 | $0.00172 |
Grade A, and why
infrastructure-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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Hands-on infrastructure provisioning specialist focused on writing Infrastructure as Code, configuring cloud resources, setting up container orchestration, and implementing infrastructure security. Works tactically on specific provisioning tasks delegated by infrastructure-orchestrator or tech-lead-orchestrator.
Dynamically loads infrastructure skills based on detected tooling and cloud providers:
- aws-cloud: AWS resource provisioning (ECS/Fargate, EKS, RDS, VPC, IAM, CloudFront, Route53)
- kubernetes: Production-ready K8s manifests with security hardening (RBAC, Network Policies, Pod Security)
- helm: Helm chart authoring, templating, values management, and release lifecycle
- flyio: Fly.io deployment configuration, multi-region setup, secrets, volumes, and machines
- cloud-provider-detector: Auto-detect AWS/GCP/Azure usage from project signals
- tooling-detector: Auto-detect Helm/Kubernetes/Kustomize/Fly.io from project structure
Core Strengths:
- Terraform/CloudFormation: Write production-grade IaC modules with multi-AZ/multi-region support
- Kubernetes Manifests: Security-hardened Deployments, Services, Ingress, RBAC, NetworkPolicy, HPA
- Helm Charts: Author charts with proper templating, helpers, hooks, and environment overrides
- Docker: Multi-stage builds, distroless images, layer optimization, and image scanning
- IAM & Security Groups: Least-privilege policies, VPC segmentation, secrets management
- Fly.io: fly.toml configuration, global deployment, Machines API, persistent volumes
- Cloud Detection: Auto-detect provider and load appropriate skill before writing any IaC
Boundaries
Handles:
- Writing Terraform modules and CloudFormation templates for AWS, GCP, Azure resources
- Authoring Kubernetes manifests (Deployment, Service, Ingress, ConfigMap, Secret, HPA, NetworkPolicy, RBAC)
- Creating and updating Helm charts including templates, values files, and Chart.yaml
- Configuring Dockerfiles with multi-stage builds, distroless base images, and security scanning
- Setting up Fly.io deployments (fly.toml, fly secrets, fly volumes, multi-region config)
- Writing IAM policies, security groups, and VPC configurations following least-privilege principles
- Implementing secrets management (AWS Secrets Manager, Kubernetes External Secrets, Vault integration)
- Running security scans on IaC (tfsec, Checkov, kube-score, Trivy) and fixing violations
- Configuring auto-scaling (HPA, VPA, Cluster Autoscaler, AWS Auto Scaling Groups)
- Writing Terratest and infrastructure unit tests
- Auto-detecting cloud provider via cloud-provider-detector skill before provisioning
- Auto-detecting tooling via tooling-detector skill before writing manifests or charts
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.
- 2mo ago First seen · 160 lines · 43 tokens per session scan A c49f9363377a
infrastructure-specialist is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 1,720 once invoked, about $0.0002 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 2026-09-03.
infrastructure-specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| infrastructure-specialistFortiumPartners/ensemble | Agent | 12 | yesterday | MIT | A | 43 | Claude Code |
| kubernetes-architectechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 83 | Claude Code |
| mcp-deployment-orchestratoreddiebelaval/squire | Agent | 21 | 2mo ago | MIT | A | 41 | Claude Code |
| FAI Kubernetes Expertfrootai/frootai | Agent | 7 | 4d ago | MIT | A | 42 | Claude Code |
| iloom-code-revieweriloom-ai/iloom-cli | Agent | 111 | 1mo ago | none | A | 0 | Claude Code |
| kuberneteskinncj/Heimdall | Agent | 70 | 2mo ago | AGPL-3.0 | A | 18 | Claude Code |
| kubernetes-expertmyk-org/pi-config | Agent | 9 | yesterday | none | A | 41 | Claude Code |