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 metaspartan/cybara --skill mactopgit clone --depth 1 https://github.com/metaspartan/cybaraWrote 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/metaspartan/cybara/mactop)<a href="https://agentmods.dev/skills/metaspartan/cybara/mactop"><img src="https://agentmods.dev/badge/skills/metaspartan/cybara/mactop.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 5.1 | $0.00060 | $0.00957 |
| Opus 5 | $0.00030 | $0.00478 |
| Sonnet 5 | $0.00012 | $0.00191 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
mactop 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mactop Skill
Execute mactop in headless mode and parse the output for Apple Silicon hardware metrics.
Prerequisites
- mactop installed:
brew install mactop - PATH includes /usr/sbin: Required for sysctl access
Usage
Get Full Metrics
mactop --headless --count 1 --format json
Use --format toon when a compact human-readable stream is better than JSON.
Parse Key Metrics
CPU Usage:
mactop --format toon --headless --count 1 | grep "^cpu_usage:" | awk '{print $2}'
RAM (used/total GB):
mactop --format toon --headless --count 1 | grep -E "^ (Used|Total):" | awk '{printf "%.1f", $2/1073741824}'
GPU Usage:
mactop --format toon --headless --count 1 | grep "^gpu_usage:" | awk '{print $2}'
Power (total/CPU/GPU):
mactop --format toon --headless --count 1 | grep -E "^ (TotalPower|CPUPower|GPUPower):" | awk '{print $2}'
Thermal State:
mactop --format toon --headless --count 1 | grep "^thermal_state:" | awk '{print $2}'
Temperature:
mactop --format toon --headless --count 1 | grep "^ SocTemp:" | awk '{print $2}'
Chip Info:
mactop --format toon --headless --count 1 | grep "^ Name:" | awk '{print $2}'
Network I/O (bytes/sec):
mactop --format toon --headless --count 1 | grep -E "^( InBytesPerSec| OutBytesPerSec):" | awk '{print $2}'
Thunderbolt Buses:
mactop --format toon --headless --count 1 | grep "^ Name:" | awk '{print $2}'
Options
| Option | Description |
|---|---|
--count N |
Number of samples (default: 1) |
--interval MS |
Sample interval in milliseconds (default: 1000) |
TOON Format
timestamp: "2026-01-25T20:00:00-07:00"
soc_metrics:
CPUPower: 0.15
GPUPower: 0.02
TotalPower: 8.5
SocTemp: 42.3
memory:
Total: 25769803776
Used: 14852408320
Available: 10917395456
cpu_usage: 5.2
gpu_usage: 1.8
thermal_state: Normal
system_info:
Name: Apple M4 Pro
CoreCount: 12
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 First seen · 120 lines · 60 tokens per session scan A f3b62fb73b29
mactop is a skill published in the GitHub repository metaspartan/cybara (28 stars, last pushed today), licensed MIT. It adds 60 tokens to every session and 957 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
blucli
BluOS CLI (blu) for discovery, playback, grouping, and volume control of Bluesound and NAD speakers. Use when the user wants to play music, stream audio, control speakers, adjust volume, group or ungroup Bluesound players, search TuneIn radio, or manage multi-room streaming setups.
camsnap
Capture frames or clips from RTSP/ONVIF cameras. Grabs snapshots, video clips, and motion events from IP cameras, security cameras, and video streams. Use when the user wants to take a snapshot from a camera, record a clip from an RTSP stream, monitor motion on a security camera, discover ONVIF devices on the network…
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
home-assistant
This skill should be used when helping with Home Assistant setup, including creating automations, modifying dashboards, checking entity states, debugging automations, and managing the smart home configuration. Use this for queries about HA entities, YAML automation/dashboard generation, or troubleshooting HA issues.
raspberry-pi-pico2
Use when developing with Raspberry Pi Pico 2 or the Pi Debug Probe.
piper-tts-training
Train custom TTS voices for Piper (ONNX format) using fine-tuning or from-scratch approaches. Use when creating new synthetic voices, fine-tuning existing Piper checkpoints, preparing audio datasets for TTS training, or deploying voice models to devices like Raspberry Pi or Home Assistant. Covers dataset preparation…