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 agentmods add skills/bug-ops/zeph/os-automationnpx 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.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 | $0.00128 | $0.01520 |
| Opus 5 | $0.00064 | $0.00760 |
| Sonnet 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 4d 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.
- 4d 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 (57 stars, last pushed 9d ago), licensed MIT. It adds 128 tokens to every session and 1,520 once invoked, about $0.0006 per session on Opus 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
free-model-manager
Free AI model management - discover, download, and manage free/open-source AI models from Ollama, HuggingFace, and other sources.
release-notes
Draft concise release notes.
lynkr
Universal LLM gateway with intelligent routing, Graphify code intelligence, Distill compression, routing telemetry, Code Mode, and 12+ provider support. 60-80% cost reduction for Claude Code, Cursor, and Codex.
文档协作
引导用户通过结构化的文档共同编写工作流程。当用户想撰写文档、提案、技术规范、决策文档或类似结构化内容时使用。该工作流程帮助用户高效传递上下文，通过迭代优化内容，并验证文档对读者有效。当用户提到写文档、创建提案、起草规范或类似文档任务时触发。.
openmaic-classroom
将 RAG 检索结果、文档块或知识图谱概念转换为 OpenMAIC 互动课程。当用户要求将知识库内容、检索到的文档片段、上传的文档、或知识图谱中的概念批量转换为教学课件/互动课堂时使用此技能。支持纯需求生成、基于 PDF 内容的课程生成、和基于概念图遍历的批量课堂生成。.
weknora-shared
Use when driving a WeKnora RAG server through the weknora CLI as an agent — authenticating, managing knowledge bases / documents / sessions / agents, running search or chat, or interpreting the CLI's JSON envelopes and exit codes. Read this before any other weknora- skill.