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/panchangam18/background-computer-use/chromenpx skills add Panchangam18/background-computer-use --skill chromegit 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/chrome)<a href="https://agentmods.dev/skills/panchangam18/background-computer-use/chrome"><img src="https://agentmods.dev/badge/skills/panchangam18/background-computer-use/chrome.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 | $0.00062 | $0.00480 |
| Opus 5 | $0.00031 | $0.00240 |
| Sonnet 5 | $0.00012 | $0.00096 |
| Haiku 4.5 | $0.00006 | $0.00048 |
Grade A, and why
chrome 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 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.
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 Chrome with background computer use
Chrome is Chromium-based and cooperates well with background automation once
the server enables AXManualAccessibility (which happens automatically on
the first get_app_state).
- Call
get_app_state app="Google Chrome"before interacting. The webpage DOM is exposed as accessibility nodes under a singleHTML contentelement. - URL navigation: set the
Address and search bartext field.set_value app="Google Chrome" element_index=<N> value="https://…"works and submits by default. - Clicks on in-page links and buttons: use
click(element_index=...). Chrome honorsAXPresson Chromium AX nodes even when the window isn't key, so clicks don't steal focus. - Typing into form fields:
set_valueauto-falls-back to a typing path when the AX write is rejected (which is typical for Chromium controls). Focus stays with whichever app you had foremost. - Scrolling:
scroll app="Google Chrome" element_index=<HTML content> direction="down"works via AppleScriptexecute ... javascript. It finds the nearest scrollable ancestor at the viewport center (so it picks the right sub-scroller in app-style pages like Gmail, LinkedIn, or Notion, not justwindow).
Known limitation:
scrollfor Chrome always scrolls a window-level or sub-scroller picked by the "viewport-center ancestor" heuristic. If you need to scroll a specific sub-region that isn't at the viewport center, click into it first to re-center the heuristic, or usepress_key key="PageDown"with the understanding that it will focus Chrome.
Detailed notes live in server/app-hints/Chrome.md; they are injected as
<app_hints> on every get_app_state call for Chrome.
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 · 39 lines · 62 tokens per session scan A b4ccfa9c2ee9
chrome is a skill published in the GitHub repository Panchangam18/background-computer-use (5 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 480 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 2026-08-31.
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…
web-navigator
Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.
design-pipeline
Figma 디자인을 shadcn/ui 코드로 만들고 실제 브라우저 검증(Playwright+axe-core+3뷰포트)을 통과해야만 완료로 표시하는 파이프라인. "Figma", "디자인 코드로", "컴포넌트 만들어", "shadcn" 등 UI 생성 요청 시 사용.