browser-control

browser-control is a skill for Claude Code, Codex from NakaokaRei/SwiftAutoGUI. It costs 72 tokens per session (1,861 once invoked), scanned A, original, MIT.

A browser-automation guide for controlling web pages in an already running Chromium session through the Chrome DevTools Protocol, a debugging interface for browsers. It uses sagui browser commands and does not control native macOS apps.

In plain words
What is it for?
Use it to list tabs, inspect page elements, navigate, click, type, send keys, scroll, and complete browser goals through an existing remote-debugging session.
Why use it?
It gives developers a browser-only way to inspect pages and carry out web tasks without mixing in desktop automation. It also defines checks for the operating system, installed command, browser tabs, and debugging connection.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Claude Code.

Part of the swift-auto-gui plugin — 2 skills shipped together

Good fit Use it to list tabs, inspect page elements, navigate, click, type, send keys, scroll, and complete browser goals through an existing remote-debugging session.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nakaokarei/swiftautogui/browser-control
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 NakaokaRei/SwiftAutoGUI --skill browser-control
Clone the repo
git clone --depth 1 https://github.com/NakaokaRei/SwiftAutoGUI

Made for: Claude Code, Codex.

Or install swift-auto-gui, the plugin that ships this one along with the rest of its 2 skills.

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 browser-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/browser-control/github.svg)](https://agentmods.dev/skills/nakaokarei/swiftautogui/browser-control)
Your own site
<a href="https://agentmods.dev/skills/nakaokarei/swiftautogui/browser-control"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/browser-control/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.

agentmods 80×15 button for browser-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/nakaokarei/swiftautogui/browser-control"><img src="https://agentmods.dev/badge/skills/nakaokarei/swiftautogui/browser-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,861 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00072 $0.01861
Opus 5 $0.00036 $0.00931
Sonnet 5 $0.00014 $0.00372
Haiku 4.5 $0.00007 $0.00186

Measured 9d ago against content hash d9ae3d530817, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

browser-control 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 9d 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.

plugins/swift-auto-gui/skills/browser-control/SKILL.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

browser-control

Use sagui browser to inspect and automate Chromium pages through the Chrome DevTools Protocol (CDP). Treat this as a browser-only environment: it never falls back to native macOS automation.

Preflight

Run these checks before browser automation:

uname -s
command -v sagui
sagui browser --help

Stop if the platform is not macOS. If sagui is missing, or the installed version has no browser command, ask before installing or upgrading it:

brew update
brew install NakaokaRei/tap/sagui
# Use this instead when sagui is already installed:
brew upgrade NakaokaRei/tap/sagui

Do not claim that Accessibility or Screen Recording permission is required for browser-only CDP actions. Those permissions apply to native sagui commands, not sagui browser.

Connect to Chromium

List tabs on the default loopback endpoint:

sagui browser tabs

If no debugging endpoint is available, ask the user to start a dedicated Chromium profile, or obtain approval before launching it:

"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" \
  --remote-debugging-address=127.0.0.1 \
  --remote-debugging-port=9222 \
  --user-data-dir=/tmp/swift-auto-gui-browser-profile

Keep the endpoint on loopback. Do not expose or connect CDP to a LAN or public address. The browser session does not launch Chromium, manage profiles, bypass login, solve CAPTCHA, or handle 2FA.

Use the target ID printed by sagui browser tabs when a specific tab matters. Re-list tabs after a tab closes, opens, or navigates unexpectedly because target IDs and page observations may become stale.

Choose the domain allowlist

Build the narrowest allowlist that satisfies the user's stated goal:

  • github.com permits exactly github.com.
  • '*.github.com' permits subdomains but not the parent domain; quote wildcards in the shell.
  • Repeat --domain for multiple hosts.
  • Never use a global wildcard, a public suffix such as com, or unrelated domains.
  • Ask before adding a domain that is not clearly implied by the goal.

Read the full file on GitHub · 209 lines

Files

What ships with it

1 file 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.

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. 9d ago First seen · 209 lines · 72 tokens per session scan A d9ae3d530817

Subscribe to this mod's changes

browser-control is a skill published in the GitHub repository NakaokaRei/SwiftAutoGUI (92 stars, last pushed 17d ago), licensed MIT. It adds 72 tokens to every session and 1,861 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

computer-use-macos

Top-level macOS computer-use skill with a bundled standalone runtime that bootstraps itself without any local Claude installation, private native modules, or extracted app assets.

wimi321/macos-computer-use-skill · 37 tokens

peekaboo

Use Peekaboo for macOS desktop automation, screenshots, visual UI maps, native accessibility inspection, app/window/menu/dialog control, native app and browser chrome control, browser-page MCP tooling, MCP diagnostics, and Peekaboo repo validation. Use when Codex needs current macOS UI state, direct desktop control…

openclaw/Peekaboo · 82 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

use-peek

Use the peek CLI to inspect, debug, and interact with native macOS app windows. Use when the user asks to debug a macOS app, inspect UI elements, take screenshots, click buttons, or automate interactions with native apps.

alexmx/peek · 51 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