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.
npx agentmods add rules/hermeticormus/linux-sysadmin-skills/linux-sysadmingit clone --depth 1 https://github.com/HermeticOrmus/linux-sysadmin-skillsWhat 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 | $0.00033 | $0.00404 |
| Opus 5 | $0.00016 | $0.00202 |
| Sonnet 5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00040 |
Grade A, and why
linux-sysadmin 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 yesterday.
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.
What it actually says
Linux sysadmin workflows
Five checklist-driven system administration workflows for Debian/Ubuntu-family machines. Package operations use apt; service and log operations use systemd and journalctl.
Safety rule: confirm before any destructive operation. Removing packages, editing SSH or firewall config, changing kernel parameters, killing processes, and clearing caches are explained first (including lock-out risk) and wait for approval. Read-only inspection runs without prompting.
1. Security
Audit and harden: user and access control, SSH hardening, firewall (UFW), updates and patches, services and open ports, file permissions (including SUID/SGID), logs, application and network security, backups. Explain each change's security benefit and lock-out risk before applying.
2. Performance
Assess CPU, memory, disk, network, and processes. Identify the bottleneck before tuning. Apply targeted changes (kernel parameters in /etc/sysctl.conf, service trimming, resource limits) and measure before and after.
3. Diagnose
Hypothesis-driven loop for a failing service or issue: describe the problem, gather evidence (journalctl -xe, systemctl status <service>), find patterns, check recent changes, form and test a hypothesis, apply the fix, verify resolution.
4. Monitor
Read-only health sweep: CPU, memory, disk, network, processes, critical services, temperatures, recent log errors. End with a summary that flags concerns. Make no changes.
5. Maintain
Routine pass: apt update && apt upgrade, apt autoremove, clean cache, scan logs (journalctl -p 3 -b), check disk (df -h), verify critical services, confirm backups. Ask before destructive steps.
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.
- yesterday First seen · 31 lines · 33 tokens per session scan A 5cab2548bc78
linux-sysadmin is a cursor rule published in the GitHub repository HermeticOrmus/linux-sysadmin-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 404 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other cursor rules, from other repositories
config-and-mcp
Any KAFKAXYZ env maps to kafka.x.y.z for AdminClient. Precedence: classpath props < external file < env.
commit-sponsors
Every git commit message must acknowledge BetterDesk supporters.
security-threat-and-stability
Maximum security scrutiny on issues/PRs and stability-first code changes.
codinfy-agent-monitor
Codinfy Agent Monitor rules for /codinfy and MCP monitoring.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.