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 skills add m3taz-ahmed/ai-globals --skill linux-systems-lordgit clone --depth 1 https://github.com/m3taz-ahmed/ai-globalsWrote 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/skills/m3taz-ahmed/ai-globals/linux-systems-lord)<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/linux-systems-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/linux-systems-lord/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.
<a href="https://agentmods.dev/skills/m3taz-ahmed/ai-globals/linux-systems-lord"><img src="https://agentmods.dev/badge/skills/m3taz-ahmed/ai-globals/linux-systems-lord.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.00864 |
| Opus 5.5 | $0.00009 | $0.00346 |
| Sonnet 5.5 | $0.00005 | $0.00173 |
| Haiku 4.5 | $0.00002 | $0.00086 |
Grade B, and why
linux-systems-lord scanned grade B 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 1mo 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 rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
15. [PROHIBIT] `kill -9` as a first resort, `chmod 777`, disabling SELinux instead of fixing contexts, tuning blind (change without measurement), or running diagnostic tools on prod without understanding their overhead. What it actually says
[SKILL] linux-systems-lord [OBJ] Debug and tune Linux from syscall to service. [RULES]
- [CMD] IDs: Linux kernel
/torvalds/linux, kernel docs/websites/kernel_doc_html, systemd/systemd/systemd, eBPF/isovalent/ebpf-docs, Cilium/cilium/cilium. - [REQ] Pillar coverage: kernel architecture, process/service management, filesystems/storage, Linux networking, eBPF, performance engineering, observability, security/hardening.
- [REQ] Query relevant ID with full question + topic (networking, systemd, ebpf, kernel, performance).
- [REQ] Distinguish user-space vs kernel-space symptoms.
- [REQ] Cite exact file paths, unit names, sysctl keys.
- [REQ] Diagnostic method: USE per resource (Utilization, Saturation, Errors) —
uptime/vmstat/iostat -xz 1/free/ss/topestablish the picture in <60s before deep dives. CPU ≠ load: runnable queue (load) can be CPU, uninterruptible I/O, or lock contention —pidstat,/proc/pressure/*(PSI) disambiguate. - [REQ] systemd discipline: services as units with
Restart=,RestartSec=, resource limits (MemoryMax=,CPUQuota=), hardening directives (NoNewPrivileges,ProtectSystem,PrivateTmp),After=/Wants=ordering explicit,journalctl -ufor logs,systemd-analyze blame/critical-chainfor boot. - [REQ] Process forensics:
/proc/<pid>/is the truth (status, maps, fd, limits),strace -f -ttfor syscall behavior,lsof/fuserfor file/socket owners,psstates (R/S/D/Z) interpreted correctly — D-state = kernel wait, usually I/O. - [REQ] Networking:
ss -tlnp/ip -s link/ip route/resolvectlbaseline; TCP states understood (TIME_WAIT vs CLOSE_WAIT diagnosis); nftables/firewalld rules audited; DNS failures checked before blaming the app; MTU/nat/offload edge cases on overlays. - [REQ] Storage:
df -h+df -i(inodes!) +lsblk+ SMART; filesystem per workload (ext4 default, xfs large files, btrfs/zfs features with ops cost);ionice/queue tuning only afteriostatshows queue depth problems. - [REQ] Memory: free vs available (cache is healthy), OOM-killer logs in
dmesg, swap/swappiness deliberate, cgroup limits vs system overcommit understood — OOM kills hit cgroup limits first. - [REQ] eBPF for truth:
bpftrace/bcc tools (execsnoop,opensnoop,biolatency,tcplife) when classic tools can't see it; perf for CPU flame graphs; kernel tracing is the last-mile tool not the first. - [REQ] Security: least privilege + capabilities (
getcap), auditd for forensics, sysctl hardening (net.ipv4., kernel.), seccomp/apparmor profiles where warranted, world-writable/SUID audits on schedule. - [REQ] Tuning discipline: sysctl changes with measured before/after + documented rationale + persistence in
/etc/sysctl.d/; never cargo-cult tuning flags from blog posts. - [PROHIBIT]
kill -9as a first resort,chmod 777, disabling SELinux instead of fixing contexts, tuning blind (change without measurement), or running diagnostic tools on prod without understanding their overhead.
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.
- 1mo ago Changed · +10 lines scan A → B 46d0a33656c6
- 1mo ago First seen · 13 lines · 23 tokens per session scan A 3db60aa8b64e
linux-systems-lord is a skill published in the GitHub repository m3taz-ahmed/ai-globals (5 stars, last pushed 5d ago), licensed MIT. It adds 23 tokens to every session and 864 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.