infrastructure-expert

infrastructure-expert is an agent for coding agents from nexus-substrate/nexus-agents. It costs 28 tokens per session (2,905 once invoked), scanned A, original, MIT.

An infrastructure specialist for physical servers, hardware management, networking, and remote management systems such as iDRAC, iLO, IPMI, and Redfish.

In plain words
What is it for?
Use it for bare-metal operations, out-of-band access, hardware health checks, network equipment, storage systems, and server lifecycle work.
Why use it?
It helps account for real hardware limits and the risks of actions such as rebooting servers or updating firmware remotely.

Agent

Part of the nexus-agents plugin — 33 skills, 16 agents, 1 hook shipped together

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.

agentmods
npx agentmods add agents/nexus-substrate/nexus-agents/infrastructure-expert
Clone the repo
git clone --depth 1 https://github.com/nexus-substrate/nexus-agents

Or install nexus-agents, the plugin that ships this one along with the rest of its 33 skills, 16 agents, 1 hook.

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 infrastructure-expert

README.md
[![agentmods](https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/infrastructure-expert.svg)](https://agentmods.dev/agents/nexus-substrate/nexus-agents/infrastructure-expert)
Your own site
<a href="https://agentmods.dev/agents/nexus-substrate/nexus-agents/infrastructure-expert"><img src="https://agentmods.dev/badge/agents/nexus-substrate/nexus-agents/infrastructure-expert.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,905 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
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 $0.00028 $0.02905
Opus 5 $0.00014 $0.01452
Sonnet 5 $0.00006 $0.00581
Haiku 4.5 $0.00003 $0.00291

Measured 5d ago against content hash f2d2fea51155, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infrastructure-expert scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

2. **Connectivity check**: \`curl\` each service endpoint (e.g., CredHub :8844/info, UAA :8443/info)
agents/infrastructure-expert.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Infrastructure Expert

You are an infrastructure expert specializing in physical server management, bare metal operations, and hardware lifecycle automation.

Core Principles

  1. Physical hardware has real-world constraints — respect boot times, power cycles, and failure modes
  2. Always maintain multiple access paths — never lock yourself out of a system
  3. Monitor hardware health proactively — sensors, SEL, SMART data predict failures before they happen
  4. Treat every remote action as potentially destructive — verify before power cycling or firmware updating
  5. Document the physical topology — IP addresses, rack locations, serial numbers, OOB interfaces

Hardware Boot Time Reference

Hardware Type Expected Boot/POST Time OOB Management
Enterprise server (128GB+ RAM) 10-15 minutes (memory training) iDRAC, iLO, IPMI, Redfish
Enterprise server (32-64GB RAM) 5-10 minutes iDRAC, iLO, IPMI, Redfish
Desktop/workstation 1-3 minutes Rarely available
Raspberry Pi / SBC 30-60 seconds None — no OOB
Network switches/routers 2-5 minutes Serial console, SSH
NAS/storage appliances 3-8 minutes Web UI, SSH

CRITICAL: After issuing a power cycle or reboot to a high-RAM server, wait the full expected boot time before diagnosing "unresponsive." Memory training during POST is normal and cannot be skipped.

Access Strategy Hierarchy

Always maintain and verify multiple access paths. Never modify all paths simultaneously.

  1. SSH (key-based) — Primary access, fastest, most scriptable
  2. SSH (password) — Backup, always maintain as fallback even when keys are configured
  3. Tailscale/VPN SSH — Network-independent backup path, works across NAT
  4. OOB Console (iDRAC/iLO/IPMI) — When OS is unreachable, use for KVM, SOL, power control
  5. Serial console — For network switches, embedded devices, boot-time debugging
  6. Physical access — Last resort (keyboard/monitor/crash cart)

Read the full file on GitHub · 255 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. 5d ago First seen · 255 lines · 28 tokens per session scan A f2d2fea51155

Subscribe to this mod's changes

infrastructure-expert is an agent published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 2,905 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

antenna-engineer

Reasons from gain–directivity–efficiency, Chu–Harrington bandwidth limits, and array factor through HFSS/CST/FEKO synthesis, IEEE 149-2021 NF/FF/CATR metrology, CTIA TRP/TIS/ECC OTA, and Friis link budgets while treating ground-plane truncation, active impedance in arrays, range ripple, and S₁₁≠pattern conflation as…

K-Dense-AI/scientific-agents · 97 tokens

fabricator

3D printing and additive manufacturing specialist covering FDM, SLA, and SLS processes from model preparation through troubleshooting.

pjt222/agent-almanac · 25 tokens

cocotb-reviewer

RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).

babyworm/rtl-agent-team · 51 tokens

labview-class-generator

Creates LabVIEW classes end to end — settles the data model, writes each .lvclass with its private data control through NI's own project provider VIs, links inheritance, creates INTERFACES and links a class to the ones it implements, binds .ctl typedef fields so they point at the file rather than carrying a de-linked…

Zuehlke/labview-mcp · 404 tokens

persona-high

Simulated senior IC designer with full datasheet / PDK / corner fluency. Specifies CRC polynomials, bit-period cycles, opcode hex, GF180MCU 5V corners. Pushes back hard when the AI hand-waves and demands datasheet-section traceability. Drives the IC Expert Agent (plain-language register) during Phase-1 training to…

vibeic/vibe-ic · 111 tokens