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/asiflow/claude-nexus-hyper-agent-teamWrote 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/asiflow/claude-nexus-hyper-agent-team/infra-expert)<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.
<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>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 | $0.00421 | $0.08020 |
| Opus 5.5 | $0.00168 | $0.03208 |
| Sonnet 5.5 | $0.00084 | $0.01604 |
| Haiku 4.5 | $0.00042 | $0.00802 |
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 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.
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/*` Copies of this mod
1 near-identical copy found in the catalogue:
- infra-expert — 97% identical, 6 lines differ
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
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 · 476 lines · 421 tokens per session scan D 925e2fabba11
infra-expert is an agent published in the GitHub repository asiflow/claude-nexus-hyper-agent-team (18 stars, last pushed 5mo ago), licensed MIT. It adds 421 tokens to every session and 8,020 once invoked, about $0.0017 per session on Opus 5.5. 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.
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…
infrastructure
Cloud infrastructure, Kubernetes, orchestration, and infrastructure as code. Use for cloud platforms, containerization, service mesh, and infrastructure design.
helm-deployment
Author and maintain Helm charts, multi-env config, digest-based deploys, and rollback-safe delivery across localdev, staging, and production.
ops-proxmox
Proxmox VE infrastructure management (VMs, LXC, storage, network, backup).
beam-sre
Use this agent as the Senior Platform Engineer / BEAM SRE — the on-call defender of the Living Platform's Plane 1 BEAM cluster on GKE. You dispatch this agent for BEAM-cluster-specific operational concerns that generic infra-expert or observability-expert cannot deeply reason about: libcluster topology design, SIGTERM…
infra-expert
Use this agent as a distinguished Infrastructure/K8s/SRE authority for peer-review-level infrastructure review, incident response, and GKE/GCP platform expertise. Covers Kubernetes deep internals, GKE-specific features, Istio service mesh, Terraform/IaC, GCP platform services, networking, cost engineering, and…