Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/appleweiping/weiping_wiki/chrome-automation)<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/chrome-automation"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/chrome-automation/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.
<a href="https://agentmods.dev/skills/appleweiping/weiping_wiki/chrome-automation"><img src="https://agentmods.dev/badge/skills/appleweiping/weiping_wiki/chrome-automation.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00073 | $0.05957 |
| Opus 5 | $0.00036 | $0.02978 |
| Sonnet 5 | $0.00015 | $0.01191 |
| Haiku 4.5 | $0.00007 | $0.00596 |
Grade A, and why
chrome-automation 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 10d 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.
This is a copy
95% identical to chrome-automation — 72 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 699 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chrome Browser Automation with Real-time Control
Control the user's Google Chrome browser using agent-browser connected via Chrome DevTools Protocol (CDP). All actions are visible in real-time in the user's browser window.
Local Codex/D-Drive Override
This installation lives inside D:/Research/vipin's knowledgebase/.codex/skills/chrome-automation/, not ~/.claude/skills/.
For this machine, prefer the already verified D-drive runtime before using the upstream $HOME\Documents paths:
$AB_HOME = "D:\Research\vipin's knowledgebase\.wiki-tmp\tools\agent-browser"
$AB_BIN = "$AB_HOME\bin\agent-browser-win32-x64.exe"
$CHROME_PROFILE = "D:\Research\vipin's knowledgebase\.wiki-tmp\tools\chrome-automation-profile"
$PORT = 9223
$env:AGENT_BROWSER_HOME = $AB_HOME
Verified smoke test on 2026-05-17:
Start-Process -FilePath "C:\Program Files\Google\Chrome\Application\chrome.exe" `
-ArgumentList @("--remote-debugging-port=$PORT", "--user-data-dir=$CHROME_PROFILE", "--no-first-run", "--no-default-browser-check", "about:blank")
& $AB_BIN open https://example.com --cdp $PORT --session codex-smoke
& $AB_BIN get title --cdp $PORT --session codex-smoke
& $AB_BIN get url --cdp $PORT --session codex-smoke
& $AB_BIN snapshot -i --cdp $PORT --session codex-smoke
& $AB_BIN screenshot body "D:\Research\vipin's knowledgebase\.wiki-tmp\chrome-automation-example.png" --cdp $PORT --session codex-smoke
The D-drive agent-browser-win32-x64.exe returned agent-browser 0.27.0, connected to Chrome via CDP, read Example Domain, read https://example.com/, listed Example Domain / Learn more refs, and wrote screenshots. On this Windows binary, prefer agent-browser <command> ... --cdp <port> --session <name>; putting --cdp before the command can reconnect to stale/default state. For saved screenshots, use screenshot body <path> or screenshot --full <path>; a single path argument can be interpreted as a selector. Native Rust rebuild failed only because MSVC link.exe was absent; the downloaded upstream Windows binary works.
What ships with it
12 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.
- references/commands.md 12 KB
- references/setup-mac.md 6.2 KB
- references/setup-windows.md 9.5 KB
- references/troubleshooting.md 10 KB
- scripts/auto-install-mac.sh 2.5 KB runs code
- scripts/auto-install-windows.ps1 3.8 KB runs code
- scripts/connect_chrome.sh 1.5 KB runs code
- scripts/install-scripts.md 9.2 KB
- scripts/README.md 3.0 KB
- scripts/setup.sh 1.6 KB runs code
- scripts/start-chrome-mac.sh 3.4 KB runs code
- scripts/start-chrome-windows.ps1 5.0 KB runs code
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.
- 10d ago First seen · 699 lines · 73 tokens per session scan E cc33476c3c50
chrome-automation is a skill published in the GitHub repository appleweiping/WEIPING_WIKI (122 stars, last pushed 15d ago), licensed MIT. It adds 73 tokens to every session and 5,957 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to chrome-automation, differing in 72 lines, and is treated as a copy.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…