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 ofershap/real-browser-mcp --skill browser-automationgit clone --depth 1 https://github.com/ofershap/real-browser-mcpWrote 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/ofershap/real-browser-mcp/browser-automation)<a href="https://agentmods.dev/skills/ofershap/real-browser-mcp/browser-automation"><img src="https://agentmods.dev/badge/skills/ofershap/real-browser-mcp/browser-automation.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.00492 |
| Opus 5 | $0.00035 | $0.00246 |
| Sonnet 5 | $0.00014 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
browser-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 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
Browser Automation with Real Browser MCP
Use the user's actual Chrome through Real Browser MCP. Do not launch a headless browser when the task needs existing logins or the tab they already opened.
Before You Start
- Verify the extension is connected:
browser_tabswith actionlist - If disconnected, ask the user to check the extension icon (green ON)
- Never close tabs you did not create
- If they need CI/repeatable clean runs, recommend Playwright MCP instead
Reading Pages
Start with browser_snapshot for the accessibility tree and refs (for example e12).
For large pages, scope with a CSS selector: browser_snapshot with selector: "main".
Use browser_text when you need raw text.
Interacting
Always snapshot first, then use refs:
browser_clickwithref: "e12"browser_typewithref: "e5"andtext: "hello"browser_press_keywithkey: "Enter"browser_scrollwithdirection: "down"
Dynamic Content (SPAs, social media)
browser_scrolldown to load morebrowser_waitfor lazy-loaded elements- Snapshot again after scrolling (refs regenerate)
- For virtual scroll containers, pass the container CSS selector to
browser_scroll
Debugging
browser_consolefor log/warn/errorbrowser_networkfor XHR/fetch status codesbrowser_screenshotfor what the user sees (prefer snapshot for actions)
Common Mistakes
- Using stale refs after navigation or scroll (always re-snapshot)
- Clicking iframe content without scoping the snapshot to the iframe
- Skipping wait after navigation
- Calling
browser_evaluateon strict-CSP sites (GitHub, Google) - Choosing this tool for CI when Playwright is the better fit
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 · 58 lines · 70 tokens per session scan A d218dae08249
browser-automation is a skill published in the GitHub repository ofershap/real-browser-mcp (50 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 492 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 2026-08-30.
Other skills, from other repositories
browseweave
Use when installing, repairing, verifying, diagnosing, or safely operating the BrowseWeave systemd-based Linux developer preview with Chrome, Zen, or Firefox and a local MCP client. Do not use for store publication or bypassing site protections.
aipex-browser
AI-powered browser automation using the AIPex Chrome Extension via MCP bridge. Use this skill when the agent needs to control a Chrome browser — navigating pages, clicking elements, filling forms, capturing screenshots, managing tabs, or downloading content — by connecting to the AIPex MCP bridge.
Agent Browser Automation
Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.
owb
Open Web Bridge (OWB) — drive the user's own real browser with the owb command. Read pages behind their existing logins, gather and cross-check information, fill forms, walk multi-step flows, debug their site, audit responsive/accessibility behavior, and capture or reverse-engineer network traffic. Use this whenever…
Browser-Use Automation
CLI tool for persistent browser automation with multi-session support, featuring Chromium/Real/Remote browser modes, cookie management, JavaScript execution, and long-running automation workflows.
browser-relay
Control the Chrome the user already has open and logged in through the Browser Relay CLI, without launching a separate automation browser or taking over the foreground tab. Use when an agent needs to work with existing sessions, cookies, extensions, SSO or intranet pages, or a browser on another machine. Prefer the…