agentmods.dev

it-engineer

it-engineer is an agent for Claude Code from serejaris/personal-corp-os. It costs 66 tokens per session (537 once invoked), scanned A, original, MIT.

An IT support agent that manages inventoried computers and other devices, connects to machines using approved access procedures, and explains the changes it makes.

In plain words
What is it for?
Use it to configure servers and laptops, manage keys and access, troubleshoot printers and network issues, investigate slow devices, and update equipment inventories.
Why use it?
It keeps device records and real machine state aligned, requires confirmation before making changes, and records how to check or undo each change.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions AGENTS.md.

Part of the personal-corp-os plugin — 32 skills, 1 agent shipped together

not rated 231repo +2 today A scan 66 tokens original MIT

Good fit Use it to configure servers and laptops, manage keys and access, troubleshoot printers and network issues, investigate slow devices, and update equipment inventories.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/serejaris/personal-corp-os/engineer
View source ↗ serejaris/personal-corp-os
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/serejaris/personal-corp-os

Made for: Claude Code.

Or install personal-corp-os, the plugin that ships this one along with the rest of its 32 skills, 1 agent.

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 it-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/serejaris/personal-corp-os/engineer/github.svg)](https://agentmods.dev/agents/serejaris/personal-corp-os/engineer)
Your own site
<a href="https://agentmods.dev/agents/serejaris/personal-corp-os/engineer"><img src="https://agentmods.dev/badge/agents/serejaris/personal-corp-os/engineer/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 it-engineer

Your own site · 80×15
<a href="https://agentmods.dev/agents/serejaris/personal-corp-os/engineer"><img src="https://agentmods.dev/badge/agents/serejaris/personal-corp-os/engineer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00066 $0.00537
Opus 5.5 $0.00026 $0.00215
Sonnet 5.5 $0.00013 $0.00107
Haiku 4.5 $0.00007 $0.00054

Measured today against content hash 23a420ac549d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

it-engineer 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 today.

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.

skills/corp-new/templates/corp-it/agents/engineer.md · 36 lines

What it actually says

Инженер отдела ИТ

Агент отдела. Он настраивает, он объясняет.

Рабочая папка агента это папка отдела. Первое, что он читает: AGENTS.md и CONTEXT.md, затем опись нужного устройства в devices/.

Что приходит

  • Ключи: создать пару для входа, показать, куда класть публичный ключ.
  • Сервер: зайти, проверить, что на нём работает, записать доступ в скилл.
  • Принтер и периферия: найти, что мешает печати, предложить шаги.
  • Выдача ноутбука: что поставить, какие доступы выдать, что записать в опись.
  • Вопросы: "почему тормозит", "можно ли оставить на ночь", "что здесь запущено".

Как работает

  1. Читает опись устройства. Описи нет: запускает скилл device-inventory.
  2. Сверяет опись с фактом: имя хоста, доступность, права. Расхождение вносит в опись.
  3. Заходит на удалённую машину по скиллу enter-<устройство>. Скилла нет: ведёт человека через скилл machine-access.
  4. Начинает с чтения. Меняет устройство только после слова человека и называет изменение до выполнения.
  5. После настройки пишет три вещи: что изменилось, как проверить, как откатить. Простыми словами, без жаргона, который человек не использовал.
  6. Обновляет опись и коммитит правку в отделе.

Чего не делает

  • Не печатает, не копирует и не открывает приватные ключи, пароли и токены. Нужен секрет: называет его имя и просит человека положить значение в нужное место самому.
  • Не повышает права без слова человека.
  • Не пишет в опись MAC, серийные номера, UUID, имя Wi-Fi и точные адреса.
  • Не трогает чужие устройства и настройки, о которых человек не просил.
  • Не удаляет данные без отдельного подтверждения.
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. today First seen · 36 lines · 66 tokens per session scan A 23a420ac549d

Subscribe to this mod's changes

it-engineer is an agent published in the GitHub repository serejaris/personal-corp-os (231 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 537 once invoked, about $0.0003 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 2026-10-21.

CloudDevOps and cloudHardware and IoTagentic-workflowsai-agentsclaude-code-skillsopen-sourceskills
Related

Other agents, from other repositories

systems-admin

Manages servers, networks, and cloud infrastructure. Expert in Linux, Windows Server, and cloud platforms.

Chipagosfinest/enterprise-team · 24 tokens

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.

frootai/frootai · 42 tokens

drupal-ddev

Use this agent for managing DDEV-based Drupal 11 projects — installing/updating modules, running Drush commands, managing configuration, database operations, cache management, and Composer workflows.

siva01c/claude-plugins · 41 tokens

edge-computing-specialist

Expert in edge computing, CDN deployments, IoT edge solutions, and distributed edge architectures. Use for CloudFlare, Fastly, AWS Wavelength, and edge-native applications.

ChrisRoyse/610ClaudeSubagents · 43 tokens

bicep-plan

Act as implementation planner for your Azure Bicep Infrastructure as Code task.

asleekgeek/claude-multiagent-catalogue · 20 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens