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 barry-ran/QuickDesk --skill sys-infogit clone --depth 1 https://github.com/barry-ran/QuickDeskWrote 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/barry-ran/quickdesk/sys-info)<a href="https://agentmods.dev/skills/barry-ran/quickdesk/sys-info"><img src="https://agentmods.dev/badge/skills/barry-ran/quickdesk/sys-info/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/barry-ran/quickdesk/sys-info"><img src="https://agentmods.dev/badge/skills/barry-ran/quickdesk/sys-info.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.00545 |
| Opus 5.5 | $0.00021 | $0.00218 |
| Sonnet 5.5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
sys-info 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 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.
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
sys-info
Query system health and running processes on a remote host connected through QuickDesk.
Tools
get_system_info
Retrieve OS version, CPU model and usage, memory and swap totals/used, disk usage, hostname, and uptime. Takes no parameters.
Returns:
{
"os": "Ubuntu 22.04",
"kernel": "5.15.0",
"hostname": "prod-server-01",
"cpu": { "model": "AMD EPYC 7763", "cores": 8, "usage_percent": "12.3" },
"memory": { "total_mb": 16384, "used_mb": 8200, "usage_percent": "50.0" },
"swap": { "total_mb": 4096, "used_mb": 128 },
"disks": [{ "mount": "/", "total_gb": 500.0, "available_gb": 320.5, "fs": "ext4" }],
"uptime": "14h 32m"
}
list_processes
List running processes with resource usage, sorted and limited.
- sort_by (string, optional) — sort by
"cpu","memory", or"name"(default:"cpu") - limit (integer, optional) — max number of processes to return (default: 50)
Returns:
{
"total_processes": 312,
"showing": 5,
"sort_by": "cpu",
"processes": [
{ "pid": 1234, "name": "node", "cpu_percent": "45.2", "memory_mb": 512 }
]
}
Workflow
- Call
get_system_infoto get an overview of the remote machine's health. - If CPU or memory usage is high, call
list_processessorted by"cpu"or"memory"to identify the top consumers. - Use
limitto control result size when only the top offenders are needed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 63 lines · 53 tokens per session scan A 7759e263233a
sys-info is a skill published in the GitHub repository barry-ran/QuickDesk (530 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 545 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
cis-aws-compute-5.3
Disable SSH and RDP ports for Lightsail instances when not needed.
cis-aws-compute-5.5
Ensure RDP is restricted to only IP address that should have this access.
cis-aws-foundations-6.2
Ensure no Network ACLs allow ingress from 0.0.0.0/0 to remote server administration ports.
cis-aws-foundations-6.3
Ensure no security groups allow ingress from 0.0.0.0/0 to remote server administration ports.
cis-aws-foundations-6.4
Ensure no security groups allow ingress from ::/0 to remote server administration ports.
cis-aws-compute-5.12
Change the auto-generated password for Windows based instances.