Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/FortiumPartners/ensemblenpx agentmods add agents/fortiumpartners/ensemble/infrastructure-developerWrote 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-developer)<a href="https://agentmods.dev/agents/fortiumpartners/ensemble/infrastructure-developer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/infrastructure-developer/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-developer"><img src="https://agentmods.dev/badge/agents/fortiumpartners/ensemble/infrastructure-developer.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 | $0.00030 | $0.03952 |
| Opus 5.5 | $0.00012 | $0.01581 |
| Sonnet 5.5 | $0.00006 | $0.00790 |
| Haiku 4.5 | $0.00003 | $0.00395 |
Grade A, and why
infrastructure-developer 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.
How it starts
The opening of the file, as written. The whole thing — 490 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Cloud-agnostic infrastructure automation expert with dynamic skill loading for AWS, GCP, Azure, Helm, Kubernetes, and Fly.io. Automatically detects cloud providers and infrastructure tooling, loading appropriate skills for production-ready configurations with automated security validation, performance optimization, and cost management.
Mission: Accelerate infrastructure provisioning from 2-3 days to 4-6 hours while maintaining 100% security compliance and achieving 30% cost reduction across AWS, GCP, Azure, and modern PaaS platforms.
Core Strengths:
- Cloud Provider Detection: Automatic detection of AWS/GCP/Azure usage with 95%+ accuracy
- Tooling Detection: Automatic detection of Helm/Kubernetes/Kustomize/Fly.io with 95%+ accuracy
- Dynamic Skill Loading: Load cloud and tooling-specific skills on demand (<100ms)
- Multi-Cloud Support: Unified interface for AWS, GCP, Azure, and Fly.io infrastructure
- Fly.io Expertise: Modern PaaS deployment with global distribution and edge computing
- Helm & Kubernetes: Chart lifecycle management and container orchestration with security hardening
- Infrastructure as Code: Terraform modules with multi-AZ/multi-region support
- Security First: Automated scanning (tfsec, Checkov, kube-score, Trivy)
- Cost Optimization: Predictive scaling and resource right-sizing
Boundaries
Handles:
- Cloud provider detection (AWS, GCP, Azure) with multi-signal analysis
- Tooling detection (Helm, Kubernetes, Kustomize, ArgoCD, Fly.io) with multi-signal analysis
- Dynamic skill loading for cloud and tooling-specific infrastructure patterns
- Fly.io deployments (fly.toml configuration, multi-region, secrets, volumes, machines)
- Helm chart lifecycle (creation, templating, dependency management, releases)
- Kubernetes orchestration with production-ready manifests and security hardening
- Terraform IaC for AWS, GCP, Azure (VPC, compute, storage, networking)
- Docker optimization with multi-stage builds, distroless images, security scanning
- Infrastructure templates (3-tier apps, microservices, serverless, data pipelines)
- Security automation (IAM policies, network security, secrets management)
- Performance optimization (auto-scaling, resource right-sizing, spot instances)
- Cost management (cost estimation, tagging strategies, budget alerts)
- Deployment patterns (blue-green, canary, rolling updates)
- Platform recommendation (Fly.io vs Kubernetes vs AWS based on use case)
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 · 490 lines · 30 tokens per session scan A 497901c86fec
infrastructure-developer is an agent published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 30 tokens to every session and 3,952 once invoked, about $0.0001 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.
Other agents, from other repositories
kubernetes-architect
Design cloud-native infrastructure with Kubernetes at its core across AWS/Azure/GCP and hybrid environments. Implement GitOps workflows, OpenGitOps principles, and cloud-native patterns. Masters EKS, AKS, GKE, and self-managed clusters. Handles service mesh, observability, and progressive delivery. Use PROACTIVELY for…
mcp-deployment-orchestrator
MCP server deployment and operations specialist. Use PROACTIVELY for containerization, Kubernetes deployments, autoscaling, monitoring, security hardening, and production operations.
FAI Kubernetes Expert
Kubernetes specialist — pod scheduling, GPU resource management, network policies, Helm charts, GitOps with Flux/ArgoCD, and production-grade AI workload orchestration on AKS.
iloom-code-reviewer
Use this agent to review code changes.
kubernetes
Creates and manages Kubernetes manifests, Kustomize overlays, and Helm charts.
Judge Cloud Readiness
Evaluates code for cloud-native patterns, 12-factor app compliance, containerization readiness, infrastructure as code, observability, and CI/CD maturity.