safari

safari is a skill for Claude Code from Panchangam18/background-computer-use. It costs 38 tokens per session (368 once invoked), scanned A, original, MIT.

Instructions for driving Safari in the background with computer-use actions such as navigation, scrolling, clicking links, switching tabs, and closing tabs. They describe Safari-specific behavior that automation needs to handle.

In plain words
What is it for?
Use them when automating Safari without taking focus from the user, including opening URLs, scrolling web pages, activating page links, changing tabs, and closing tabs.
Why use it?
They reduce failures caused by Safari’s address bar, web page scrolling, hidden windows, and small tab-close controls. The instructions specify which kinds of interactions work reliably.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the background-computer-use plugin — 8 skills, 1 MCP server shipped together

Good fit Use them when automating Safari without taking focus from the user, including opening URLs, scrolling web pages, activating page links, changing tabs, and closing tabs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/panchangam18/background-computer-use/safari
Install

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.

Any agent
npx skills add Panchangam18/background-computer-use --skill safari
Clone the repo
git clone --depth 1 https://github.com/Panchangam18/background-computer-use

Made for: Claude Code.

Or install background-computer-use, the plugin that ships this one along with the rest of its 8 skills, 1 MCP server.

Wrote 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.

agentmods badge for safari

README.md
[![agentmods](https://agentmods.dev/badge/skills/panchangam18/background-computer-use/safari.svg)](https://agentmods.dev/skills/panchangam18/background-computer-use/safari)
Your own site
<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>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 368 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 8d ago against content hash b181fe589dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

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.

skills/safari/SKILL.md · 31 lines

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.

  1. Always call get_app_state app="Safari" before interacting.
  2. 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_value submits by default; don't also post a separate Return.
    • Internally this uses a typing fallback, because Safari silently ignores AXValue writes on the URL bar.
  3. 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 to PageDown/ PageUp keystrokes if nothing moved.
  4. click(element_index=<link>) works on in-page links via AXPress even when the Safari window is occluded.
  5. Tab switches: click(element_index=<tab>) on an AXTabButton. Close with perform_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.

Changes

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.

  1. 8d ago First seen · 31 lines · 38 tokens per session scan A b181fe589dd1

Subscribe to this mod's changes

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.

Related

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.…

milind-soni/axstream · 96 tokens

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.

iFurySt/open-codex-computer-use · 68 tokens

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…

browser-use/macos-harness · 71 tokens

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…

isac322/kwin-mcp · 135 tokens

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.

Plocr/Reasonix-computer-use · 23 tokens

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.

Plocr/Reasonix-computer-use · 30 tokens