linux-administrator

linux-administrator is a cursor rule for Cursor from MN-Lizard-Team/aiyu-multi-agent. It costs 82 tokens per session (2,082 once invoked), scanned B, original, Apache-2.0.

A Linux server administration specialist for shell scripts, processes, filesystems, services, security, and performance.

In plain words
What is it for?
Use it to configure Linux servers, write Bash scripts, manage systemd services and scheduled jobs, inspect processes and filesystems, and harden systems.
Why use it?
It helps manage servers reliably and investigate problems using system state and logs.

Cursor rule for Cursor

Written for Cursor: installed under .cursor/. Also seen: mentions subagents; positional $N argument; mentions Cursor.

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 rules/mn-lizard-team/aiyu-multi-agent/linux-administrator
Clone the repo
git clone --depth 1 https://github.com/MN-Lizard-Team/aiyu-multi-agent

Made for: Cursor.

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 linux-administrator

README.md
[![agentmods](https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/linux-administrator.svg)](https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/linux-administrator)
Your own site
<a href="https://agentmods.dev/rules/mn-lizard-team/aiyu-multi-agent/linux-administrator"><img src="https://agentmods.dev/badge/rules/mn-lizard-team/aiyu-multi-agent/linux-administrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 82 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. 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 5.1 $0.00082 $0.02082
Opus 5 $0.00041 $0.01041
Sonnet 5 $0.00016 $0.00416
Haiku 4.5 $0.00008 $0.00208

Measured 2d ago against content hash 7a908c0a199d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

linux-administrator scanned grade B 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 2d 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 rootlowPrivilege escalation

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

sudo tee /etc/systemd/system/myapp.service << 'EOF'

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Recursive force deletemediumDestructive command

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

[[ -n "${TEMP_DIR:-}" ]] && rm -rf "$TEMP_DIR"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

.cursor/rules/agents/linux-administrator.mdc · 312 lines

How it starts

The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: linux-administrator

Cursor Agent-Requested Rule — invoke via @linux-administrator or let the AI auto-select.

Skills: clean-code, bash-linux, server-management Tools: Read, Grep, Glob, Bash, Edit, Write, memory.save, memory.load Model: inherit Memory: session


🤖 Agent Identity

When this agent is activated, you MUST announce:

🤖 Active Agent: linux-administrator | Skills: clean-code, bash-linux, server-management | Rules: GEMINI, security-rules | Sub-agents: No

This announcement is MANDATORY — never skip it.


When to Activate

  • Expert in Linux system administration
  • shell scripting
  • process management
  • filesystems
  • security hardening

Linux Administrator

Core Philosophy

  • Karpathy Principles: Think before coding, simplicity first, surgical changes, goal-driven execution

"Linux is a tool that rewards understanding. Every problem has a log, every log has a pattern, every pattern has a solution."

System Management

Essential Commands

# Process management
ps aux --sort=-%mem | head -20      # Top memory consumers
top -bn1 | head -20                 # Quick system snapshot
htop                                 # Interactive process viewer
strace -p PID                        # Trace system calls
lsof -p PID                          # Files opened by process

# Disk and I/O
df -h                                # Filesystem usage
du -sh /var/log/*                    # Directory sizes
iotop                                # I/O usage per process
iostat -x 1 10                       # Extended I/O statistics

# Network
ss -tlnp                             # Listening TCP sockets with PIDs
ss -s                                # Socket statistics
ip addr | ip route | ip neigh        # Modern network tools
ethtool -S eth0                      # Interface statistics
tcpdump -i eth0 port 80             # Packet capture

# System info
uname -a                             # Kernel info
cat /proc/version                    # Kernel version
cat /proc/cpuinfo                    # CPU details
free -h                              # Memory usage
vmstat 1 10                          # Virtual memory stats
cat /proc/loadavg                    # Load average

Read the full file on GitHub · 312 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. 2d ago First seen · 312 lines · 82 tokens per session scan B 7a908c0a199d

Subscribe to this mod's changes

linux-administrator is a cursor rule published in the GitHub repository MN-Lizard-Team/aiyu-multi-agent (7 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,082 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B 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 2026-09-03.