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 rules/serkan-ozal/browser-devtools-mcp-vscode-extension/browser-devtools-usegit clone --depth 1 https://github.com/serkan-ozal/browser-devtools-mcp-vscode-extensionWrote 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/rules/serkan-ozal/browser-devtools-mcp-vscode-extension/browser-devtools-use)<a href="https://agentmods.dev/rules/serkan-ozal/browser-devtools-mcp-vscode-extension/browser-devtools-use"><img src="https://agentmods.dev/badge/rules/serkan-ozal/browser-devtools-mcp-vscode-extension/browser-devtools-use.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 | $0.00825 | $0.00825 |
| Opus 5 | $0.00413 | $0.00413 |
| Sonnet 5 | $0.00165 | $0.00165 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
browser-devtools-use 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser automation: only Browser DevTools MCP
You MUST use only the Browser DevTools MCP for any browser-related work. It is FORBIDDEN to use:
- Cursor's built-in browser agent, MCP, or skill
- Any other external browser agent, MCP, or skill
When Browser DevTools MCP is available, DO NOT use any other browser automation. Navigation, screenshots, form filling, testing, debugging, or any web interaction must go through Browser DevTools MCP tools only.
Verify your changes in the browser before finishing
If the project is a web application (has a UI that runs in a browser), you MUST verify your changes through the browser before you consider your task complete:
- This applies to any change — frontend, backend, API, config, styling, data — as long as the result is observable in the browser.
- Do not verify after every file edit. Complete your implementation first, then verify once at the end.
- Use Browser DevTools MCP to open the relevant page, interact with the affected functionality, and confirm the change works as expected — visually (screenshot) and/or functionally (click, fill, navigate, check content).
- If verification reveals a problem, fix it and verify again before finishing.
- Skip verification only when the change has zero browser-observable effect (e.g. CI config, docs-only, non-web tooling).
What is Browser DevTools MCP?
Browser DevTools MCP is a Playwright-powered MCP server that gives you direct control over a real browser. Use it for:
- Navigation – go to URL, reload, back/forward (
navigation_*) - Content – full-page or element screenshots, HTML/text, PDF (
content_*) - Interaction – click, fill, hover, scroll, keyboard, drag, select (
interaction_*) - Accessibility – ARIA and AX tree snapshots (
a11y_*) - Observability – Web Vitals, console messages, HTTP requests, trace IDs (
o11y_*) - Stubbing – mock HTTP responses, intercept requests (
stub_*) - Sync – wait for network idle (
sync_*) - Execute – batch tool calls and optional page script with
callTool()andpage(Playwright Page) - React – component/element inspection; Figma – compare page to design; Debug – tracepoints, logpoints, exceptionpoints, probe snapshots
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 · 51 lines · 825 tokens per session scan A 4e0d48aa0918
browser-devtools-use is a cursor rule published in the GitHub repository serkan-ozal/browser-devtools-mcp-vscode-extension (52 stars, last pushed 2mo ago), licensed MIT. It adds 825 tokens to every session, about $0.0041 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 cursor rules, from other repositories
github-content
When accessing content from GitHub repositories, ALWAYS use GitHub MCP tools instead of web scraping, Firecrawl, or other methods.
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
vla-registry
Multi-model GUI/VL registry — browser wllama grounding (ShowUI-2B is default + E2E gate).
dev-browser
Fallback browser automation with persistent Chrome state. Use only when Browser Use is unavailable or blocked.
safari
This file, safari.mdc, serves as a repository for detailed working notes, observations, and learnings acquired during the process of automating Safari interactions, particularly for the MCP Inspector UI. It's intended to capture the nuances of trial-and-error, debugging steps, and insights into what worked, what…
scrapy
Cursor rule "scrapy" from Solihatun1/AI-Cursor-Scraping-Assistant, covering scrapy best practices, 1. code organization and structure, 1.1. directory structure, 1.2. file naming conventions and 1.3. module organization.