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 AIOSAI/AIPass --skill system_statusgit clone --depth 1 https://github.com/AIOSAI/AIPassWrote 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/aiosai/aipass/system_status)<a href="https://agentmods.dev/skills/aiosai/aipass/system_status"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/system_status/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/aiosai/aipass/system_status"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/system_status.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 | $0.00018 | $0.01574 |
| Opus 5.5 | $0.00007 | $0.00630 |
| Sonnet 5.5 | $0.00004 | $0.00315 |
| Haiku 4.5 | $0.00002 | $0.00157 |
Grade A, and why
system_status 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 6d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Status Skill
Check system health metrics without leaving your workflow. Returns structured data about disk usage, memory, running processes, and system uptime.
Available Actions
| Action | Description |
|---|---|
disk |
Disk usage for the root filesystem |
memory |
Memory and swap usage (psutil, portable) |
uptime |
System uptime from psutil's boot time |
processes |
Count of processes (every pid the host lists) |
battery |
Charge, mains, state, time left (none is an answer) |
summary |
All of the above combined into one report |
Published Function: machine_vitals()
An in-process read for callers that want data, not text - the host API's
/v1/machine route proxies it verbatim and BAUD's phone draws it (FPLAN-0561).
from aipass.skills.lib.system_status import handler
vitals = handler.machine_vitals()
{"ok": True, "schema": 2, "sampled_at": ...}plus nine sections:cpu,load,memory,swap,temp,fan,network,processes,battery(schema 1 had the first eight). Each carriesavailable,reason,sentence,detailbeside its values. Never raises for a reading; a value the host cannot give isNone, never a zero.- Whole-function refusal:
{"ok": False, "reason", "detail"}withpsutil_missingorswitched_off(the off-switch is consulted, and an unreadable switch state fails closed). - Reason codes (closed set, one sentence each in
REASONS):platform,no_sensor,no_allowlisted_sensor,read_failed,warming,no_range,switched_off,psutil_missing. cpucarriespercentandwindow_s, pluscores(busy percent per logical CPU, in index order),logicalandphysical(the counts) andmhz/mhz_max(frequency now and its ceiling). Onecpu_times(percpu=True)sample per read: the headline is summed from the same per-CPU deltas as the cores, so the two agree.percentandcoresareNonewhile warming (and when the CPU count changed between samples); the counts and frequency are instant readings and are published even then. No frequency on a host isNone, never0.- CPU temperature and fans come from allowlists keyed by chip and label
(
coretemp/Package id 0;applesmcfans). The fan range is a read-only Linux sysfs read offanN_min/fanN_max. batterycarriespercent,plugged,state(charging,discharging,fullorunknown),seconds_left,lowandcritical. A host whosepsutil.sensors_battery()answersNoneisno_sensor; a psutil without the function isplatform.seconds_leftisNoneon psutil'sPOWER_TIME_UNLIMITED/POWER_TIME_UNKNOWN, anddetailnames which.stateis the kernel's/sys/class/power_supply/BAT*/statusword on Linux when it is one of the three (any other word isunknown), else derived frompluggedandpercent.low/criticalare UPower'sPercentageLow/PercentageCriticalfrom/etc/UPower/UPower.confon Linux (UPower's 20 / 5 when the file leaves a key out); no file, or a time-based policy, isNone- a face tones only against a line the host published.
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.
- 6d ago Changed · +21 lines 407feef5a059
- 10d ago Changed · +15 lines · +2 tokens per session 747d6ea8a7de
- 1mo ago Changed · +8 lines 6ba9f0f71735
- 1mo ago Changed · +33 lines cb4e47e90646
- 1mo ago First seen · 59 lines · 16 tokens per session scan A 48d784ab4c8b
system_status is a skill published in the GitHub repository AIOSAI/AIPass (301 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 1,574 once invoked, about $0.0001 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
heartbeat
Lightweight system health monitoring skill.
system-info
Get system information including CPU usage, memory, disk space, battery status, and network info. Read-only and safe to use.
System Healthcheck
Run a lightweight, non-destructive system healthcheck — disk usage, memory, CPU load, process count, hostname — and store a structured snapshot in session memory. Use when the user says "run a healthcheck", "check system health", "how's the server doing", "is everything ok", or asks for a status/diagnostics snapshot…
system-info
Get system information including CPU usage, memory, disk space, battery status, and network info. Read-only and safe to use.
performance-analysis
Comprehensive performance analysis, bottleneck detection, and optimization recommendations for Claude Flow swarms.
aws-collector-tool
AWS infrastructure information collection tool. Retrieves ECS status, CloudWatch logs, and metrics. Use when: Use when: checking ECS operation, investigating error logs in CloudWatch, retrieving metrics, or monitoring AWS resources.