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 Panchangam18/background-computer-use --skill safarigit clone --depth 1 https://github.com/Panchangam18/background-computer-useWrote 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/panchangam18/background-computer-use/safari)<a href="https://agentmods.dev/skills/panchangam18/background-computer-use/safari"><img src="https://agentmods.dev/badge/skills/panchangam18/background-computer-use/safari.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 | $0.00038 | $0.00368 |
| Opus 5 | $0.00019 | $0.00184 |
| Sonnet 5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
safari 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 8d 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
Driving Safari with background computer use
Safari's accessibility coverage is good overall, but its address bar and web content areas have two quirks that bite naive automation.
- Always call
get_app_state app="Safari"before interacting. - To navigate to a URL, call
set_value app="Safari" element_index=<smart-search-field> value="https://…".- The smart search field's ID is
WEB_BROWSER_ADDRESS_AND_SEARCH_FIELD. set_valuesubmits by default; don't also post a separateReturn.- Internally this uses a typing fallback, because Safari silently
ignores
AXValuewrites on the URL bar.
- The smart search field's ID is
- To scroll the page, call
scroll app="Safari" element_index=<scroll-area> direction="down". The tool tries a native AX page-scroll first, then posts wheel events to the correct WKWebView helper pid, then falls back toPageDown/PageUpkeystrokes if nothing moved. click(element_index=<link>)works on in-page links viaAXPresseven when the Safari window is occluded.- Tab switches:
click(element_index=<tab>)on anAXTabButton. Close withperform_secondary_action(action="close tab")rather than hit-testing the tiny close glyph.
Detailed notes live in server/app-hints/Safari.md; they are injected as
<app_hints> on every get_app_state call for Safari.
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.
- 8d ago First seen · 31 lines · 38 tokens per session scan A b181fe589dd1
safari is a skill published in the GitHub repository Panchangam18/background-computer-use (5 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 368 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
axstream
Fast deterministic macOS UI automation via replayable macros. Use BEFORE driving any macOS app's UI by hand (clicking/typing via computer-use or screenshots) — if a macro exists, replay finishes the task in seconds with no per-step reasoning; after doing a UI task manually, save it as a macro so the next run is fast.…
open-computer-use
Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.
macos-harness
Control a whole Mac from one persistent Python session with screenshots, PID-targeted input, an animated virtual pointer, targeted Apple Accessibility, Apple Events, Browser Harness CDP, and filesystem access. Use for native, Electron, browser, dialog, file, or cross-app tasks without moving the physical cursor or…
kwin-desktop-automation
Use when the user asks to launch, click, type, screenshot, or otherwise drive a Linux KDE Plasma / Wayland desktop app through the kwin-mcp MCP server. Trigger when kwin-mcp tools are available and the task involves desktop GUI automation, end-to-end GUI testing, kiosk / embedded device control, or live KDE Plasma…
computer-use
A set of rules for controlling Windows desktop applications through screen observation and simulated mouse and keyboard actions. It also describes how to find and launch installed applications and verify the results.
web-navigator
A browser-automation routing guide for web tasks. It directs navigation, page inspection, and actions such as clicking or filling forms to the appropriate browser tool.