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 bug-ops/zeph --skill os-automationgit clone --depth 1 https://github.com/bug-ops/zephWrote 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/bug-ops/zeph/os-automation)<a href="https://agentmods.dev/skills/bug-ops/zeph/os-automation"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/os-automation/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/bug-ops/zeph/os-automation"><img src="https://agentmods.dev/badge/skills/bug-ops/zeph/os-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Privilege Escalation · line 73 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Rogue Agent · line 137 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 140 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 143 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00128 | $0.01520 |
| Opus 5.5 | $0.00051 | $0.00608 |
| Sonnet 5.5 | $0.00026 | $0.00304 |
| Haiku 4.5 | $0.00013 | $0.00152 |
Grade B, and why
os-automation 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.
5. **networksetup (macOS) requires sudo for some operations** — warn the user before running commands that may require elevated privileges. Never attempt `sudo` without the user's knowledge. How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OS Automation
Automate OS-level actions using platform-native utilities.
Before running commands, detect the OS and load the matching reference for platform-specific syntax:
- macOS —
references/macos.md(osascript, pbcopy/pbpaste, screencapture, networksetup, open, launchctl) - Linux —
references/linux.md(notify-send, xclip/wl-copy, scrot/grim, xdg-open, amixer/pactl, nmcli) - Windows —
references/windows.md(PowerShell: Set-Clipboard, BurntToast, schtasks, netsh)
OS detection:
uname -s 2>/dev/null || echo Windows
Capability Matrix
| Task | macOS | Linux | Windows |
|---|---|---|---|
| Desktop notification | osascript |
notify-send |
PowerShell / BurntToast |
| Clipboard read | pbpaste |
xclip / wl-paste |
Get-Clipboard |
| Clipboard write | pbcopy |
xclip / wl-copy |
Set-Clipboard |
| Screenshot | screencapture |
scrot / grim |
snippingtool / PowerShell |
| Open file / URL | open |
xdg-open |
Start-Process |
| Launch app | open -a "App" |
gtk-launch / app name |
Start-Process |
| Volume control | osascript |
amixer / pactl |
PowerShell / nircmd |
| WiFi status | networksetup |
nmcli / iwconfig |
netsh wlan |
| Scheduled tasks | crontab / launchctl |
crontab / systemd timer |
schtasks / Register-ScheduledTask |
| Display brightness | brightness (brew) |
brightnessctl / xrandr |
PowerShell / WMI |
| Text-to-speech | say |
espeak / festival |
Add-Type / SAPI |
| System sleep | pmset sleepnow |
systemctl suspend |
rundll32 powrprof.dll,SetSuspendState |
Workflow
- Detect OS first — always.
- Load the matching reference file for exact command syntax.
- For read-only actions (clipboard read, WiFi status, screenshots to file), proceed directly.
- For write or side-effect actions (volume change, notification, scheduled task), show what will be done and confirm with the user.
- After execution, verify the result where possible (check clipboard content, confirm notification sent, verify cron entry exists).
What ships with it
3 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 · 152 lines · 128 tokens per session scan B 0eb6d377cbd8
os-automation is a skill published in the GitHub repository bug-ops/zeph (65 stars, last pushed today), licensed MIT. It adds 128 tokens to every session and 1,520 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
simplicio-compress
Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is…
simplicio-prism
Route broad or ambiguous work across Simplicio Mapper, Fast, Dev CLI, Loop, and Runtime. Use when a request spans components, requires choosing the correct capability, needs an end-to-end workflow, or the agent is unsure which Simplicio skill to invoke. Prism classifies and composes; it does not execute mutations…
google-calendar
Read schedules, check availability, and create or update Google Calendar events when the user asks to work with their calendar.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
himalaya
Himalaya v2 CLI for reading and managing email through IMAP, JMAP, Gmail, Microsoft Graph, Maildir, M2dir, and SMTP send operations.
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.