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 instructions/hermeticormus/linux-sysadmin-skills/claude-mdgit clone --depth 1 https://github.com/HermeticOrmus/linux-sysadmin-skillsWrote 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/instructions/hermeticormus/linux-sysadmin-skills/claude-md)<a href="https://agentmods.dev/instructions/hermeticormus/linux-sysadmin-skills/claude-md"><img src="https://agentmods.dev/badge/instructions/hermeticormus/linux-sysadmin-skills/claude-md.svg" alt="Measured on agentmods" 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 | $0.00432 | $0.00432 |
| Opus 5 | $0.00216 | $0.00216 |
| Sonnet 5 | $0.00086 | $0.00086 |
| Haiku 4.5 | $0.00043 | $0.00043 |
Grade A, and why
linux-sysadmin-skills CLAUDE.md 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 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.
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.
How it starts
The opening of the file, as written. The whole thing — 32 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
A toolkit of five Linux system administration workflows for Debian/Ubuntu-family machines (apt, systemd, journalctl). Each workflow is a checklist-driven, step-by-step procedure Claude runs interactively with you. Merge with project-specific instructions as needed.
These target Debian and Ubuntu derivatives. The package commands assume apt; the service and log commands assume systemd and journalctl.
Safety rule: destructive operations are confirmed before they run. Anything that removes packages, edits firewall or SSH config, changes kernel parameters, kills processes, or clears caches is explained first, including how it could lock you out, and waits for your go-ahead. Read-only inspection runs without prompting.
1. Security
Audit and harden the system. Covers user and access control, SSH hardening, firewall (UFW), updates and patches, services and ports, file permissions, logs and monitoring, application and network security, and backup. Each change is explained with its security benefit and its lock-out risk before it runs.
2. Performance
Analyze and optimize performance. Assesses CPU, memory, disk, network, and process state, identifies the bottleneck, then applies targeted tuning (kernel parameters, service trimming, resource limits) with before-and-after measurement.
3. Diagnose
Diagnose a specific failing service or system issue. A systematic loop: describe the problem, gather evidence from journalctl and systemctl status, find patterns, check recent changes, form and test a hypothesis, apply the fix, verify resolution.
4. Monitor
Check overall system health on demand. A read-only sweep of CPU, memory, disk, network, processes, critical services, temperatures, and recent log errors, ending in a health summary that flags concerns.
5. Maintain
A routine maintenance pass. Updates and upgrades packages, removes unused packages, cleans cache, scans logs for errors, checks disk space, verifies critical services, and confirms backups. Destructive steps ask first.
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.
- 5d ago First seen · 32 lines · 432 tokens per session scan A 54c5880b0242
linux-sysadmin-skills CLAUDE.md is an instructions file published in the GitHub repository HermeticOrmus/linux-sysadmin-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 432 tokens to every session, about $0.0022 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 instructions, from other repositories
RuView AGENTS.md
AGENTS.md instructions for ruvnet/RuView, covering ruview repository instructions for codex, operating contract, repository map, ruview contributor harness and homecore metaharness.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
nvidia_gpu_exporter AGENTS.md
AGENTS.md instructions for utkuozdemir/nvidia_gpu_exporter, covering nvidiagpuexporter — agent guide, what this repo is, the three collection backends, code map and the capture corpus and how testing works.
nvidia_gpu_exporter copilot-instructions.md
Copilot instructions for utkuozdemir/nvidia_gpu_exporter: Read AGENTS.md in the repository root first. It is the project guide, and everything below is only the short version for when you have not opened it.
glances CLAUDE.md
Claude Code instructions for nicolargo/glances, covering claude.md — glances maintainer context, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.