infra-expert

infra-expert is an agent for Claude Code from asiflow/claude-nexus-hyper-agent-team. It costs 421 tokens per session (8,020 once invoked), scanned D, original, MIT.

An infrastructure and site-reliability review specialist focused on Kubernetes, Google Cloud, networking, Terraform, and service operations.

In plain words
What is it for?
Use it to review GKE or Kubernetes systems, Istio, Google Cloud services, infrastructure-as-code, network policies, access controls, and incidents.
Why use it?
It helps identify deployment, security, reliability, rollback, monitoring, and cost risks before infrastructure changes are made.

Agent for Claude Code

Written for Claude Code: ${CLAUDE_PROJECT_DIR} variable. Also seen: model in frontmatter; reads .claude/ paths; positional $N argument.

Good fit Use it to review GKE or Kubernetes systems, Istio, Google Cloud services, infrastructure-as-code, network policies, access controls, and incidents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/asiflow/claude-nexus-hyper-agent-team/infra-expert
Install

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.

Clone the repo
git clone --depth 1 https://github.com/asiflow/claude-nexus-hyper-agent-team

Made for: Claude Code.

Wrote 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.

agentmods badge for infra-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert/github.svg)](https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert)
Your own site
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert/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.

agentmods 80×15 button for infra-expert

Your own site · 80×15
<a href="https://agentmods.dev/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert"><img src="https://agentmods.dev/badge/agents/asiflow/claude-nexus-hyper-agent-team/infra-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 421 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,020 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00421 $0.08020
Opus 5 $0.00211 $0.04010
Sonnet 5 $0.00084 $0.01604
Haiku 4.5 $0.00042 $0.00802

Measured 10d ago against content hash 925e2fabba11, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade D, and why

infra-expert scanned grade D with 2 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 10d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Diagnostic: SSH to the affected node → `sudo crictl ps -a | grep <stale-name>` → if orphaned entries exist, the node needs `systemctl restart containerd` (or cordon + drain + recreate node).

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Debian/Ubuntu: `apt-get update && apt-get upgrade -y && rm -rf /var/lib/apt/lists/*`
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

agents/infra-expert.md · 476 lines

How it starts

The opening of the file, as written. The whole thing — 476 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Infra Expert — a Distinguished Infrastructure Engineer and SRE Authority. You debug GKE node pressure at 3 AM, write Terraform modules that survive team turnover, and design network policies that actually enforce zero-trust. You are the consultant who reviews Google Cloud's own reference architectures and finds gaps.

You primarily review and recommend. Infrastructure implementation goes to elite-engineer. You are the authority who ensures infrastructure decisions are correct, secure, cost-efficient, and production-hardened.


CORE AXIOMS (Non-Negotiable)

Axiom Meaning
Infrastructure is code Every infrastructure change is versioned, reviewed, tested, and reproducible. No ClickOps.
Blast radius first Before any change: what's the worst case? How do we roll back? What's the recovery time?
Least privilege everywhere Network, IAM, RBAC, secrets — default deny, explicit allow, minimal scope.
Cost is a feature Right-size everything. Committed use where predictable. Spot/preemptible where tolerant.
Observability before complexity Don't add infrastructure you can't monitor. If you can't see it breaking, you can't fix it.
Evidence-based review Every finding cites specific manifest line, Terraform resource, or GCP configuration.

CRITICAL PROJECT CONTEXT

  • GKE cluster running your project with Istio service mesh
  • Services: (Go), (Python), (Next.js), 14+ federated services
  • Data layer: Cloud SQL (PostgreSQL), Memorystore (Redis), Firestore, GCS buckets
  • Networking: Dataplane V2 (Cilium), NetworkPolicies, Cloud NAT, cert-manager, Let's Encrypt
  • IaC: Terraform for GCP resources, K8s manifests (raw YAML) for workloads
  • Recent pain points: NetworkPolicy breakage, GCS FUSE mount issues, Squid proxy fixes, sandbox pod networking

CAPABILITY DOMAINS

1. Kubernetes Deep Internals

  • Scheduler: resource requests drive scheduling, limits enforce runtime bounds, QoS classes (Guaranteed/Burstable/BestEffort)
  • Kubelet: probe execution, container lifecycle hooks, eviction thresholds, image pull policies
  • API server: admission controllers, webhook configuration, RBAC evaluation, audit logging
  • etcd: consistency model, compaction, defragmentation, backup/restore
  • CRI: container runtime behavior, image layers, pull-through caches
  • CSI: persistent volume lifecycle, StorageClass configuration, volume expansion, GCS FUSE CSI specifics
  • CNI: pod networking, IPAM, Cilium/Calico specifics, eBPF datapath

Read the full file on GitHub · 476 lines

Changes

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.

  1. 10d ago First seen · 476 lines · 421 tokens per session scan D 925e2fabba11

Subscribe to this mod's changes

infra-expert is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 3mo ago), licensed MIT. It adds 421 tokens to every session and 8,020 once invoked, about $0.0021 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

cluster-awareness

Use this agent for live GKE cluster intelligence — it knows what's ACTUALLY running in production right now by querying kubectl, not what manifests say should be running. Provides real-time pod status, service topology, port mappings, deployed versions, resource usage, health state, and drift detection. The…

asiflow/claude-nexus-hyper-agent-team-light · 457 tokens

cicd-automation-devops-troubleshooter

Expert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability. Masters log analysis, distributed tracing, Kubernetes debugging, performance optimization, and root cause analysis. Handles production outages, system reliability, and preventive monitoring. Use…

wshobson/agents · 74 tokens

cicd-automation-kubernetes-architect

Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE/OKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost…

wshobson/agents · 101 tokens

hybrid-cloud-architect

Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP/OCI and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration…

wshobson/agents · 81 tokens

cloud-infrastructure-network-engineer

Expert network engineer specializing in modern cloud networking, security architectures, and performance optimization. Masters multi-cloud connectivity, service mesh, zero-trust networking, SSL/TLS, global load balancing, and advanced troubleshooting. Handles CDN optimization, network automation, and compliance. Use…

wshobson/agents · 74 tokens

data-engineer

Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.

wshobson/agents · 54 tokens