001-ui-automation-conventions

001-ui-automation-conventions is a cursor rule for Cursor from azam-sdet/10xquality. It costs 1,129 tokens per session, scanned A, original, MIT.

A set of rules for automating a browser through the Chrome DevTools MCP server, a tool that lets an agent inspect and control Chrome. It requires taking a fresh page snapshot before each interaction and using the element identifier from that snapshot.

In plain words
What is it for?
Use it when navigating pages, clicking, entering data, reloading, or otherwise running browser tests through Chrome DevTools.
Why use it?
It prevents actions from targeting guessed or outdated elements after the page changes, which makes browser tests easier to repeat and debug.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Good fit Use it when navigating pages, clicking, entering data, reloading, or otherwise running browser tests through Chrome DevTools.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/azam-sdet/10xquality/001-ui-automation-conventions
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.

Clone the repo
git clone --depth 1 https://github.com/azam-sdet/10xquality

Made for: Cursor.

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 001-ui-automation-conventions

README.md
[![agentmods](https://agentmods.dev/badge/rules/azam-sdet/10xquality/001-ui-automation-conventions/github.svg)](https://agentmods.dev/rules/azam-sdet/10xquality/001-ui-automation-conventions)
Your own site
<a href="https://agentmods.dev/rules/azam-sdet/10xquality/001-ui-automation-conventions"><img src="https://agentmods.dev/badge/rules/azam-sdet/10xquality/001-ui-automation-conventions/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 001-ui-automation-conventions

Your own site · 80×15
<a href="https://agentmods.dev/rules/azam-sdet/10xquality/001-ui-automation-conventions"><img src="https://agentmods.dev/badge/rules/azam-sdet/10xquality/001-ui-automation-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,129 This file is loaded in full into every session.
When invoked 1,129 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.01129 $0.01129
Opus 5 $0.00564 $0.00564
Sonnet 5 $0.00226 $0.00226
Haiku 4.5 $0.00113 $0.00113

Measured 12d ago against content hash ce509e20d9aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

001-ui-automation-conventions 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 12d 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.

rules/001-ui-automation-conventions.mdc · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chrome DevTools MCP UI Automation Conventions

Use the chrome-devtools MCP server for all browser automation. Follow these conventions for reliable, repeatable test execution.

Snapshot-First Rule (CRITICAL)

ALWAYS take a snapshot before interacting with any element.

  • Use take_snapshot via chrome-devtools to understand the current page state
  • Use the uid from the latest snapshot — snapshots become stale after page changes
  • NEVER guess uids — always get them from a fresh snapshot
  • After navigation or clicks that trigger page changes, take a new snapshot
  • Prefer taking a snapshot over taking a screenshot for element identification
Correct flow:
1. take_snapshot
2. Parse snapshot for uid of target element
3. click { uid: "..." }
4. take_snapshot (page changed)
5. Parse next element...

MCP Tool Reference (chrome-devtools)

Action Tool Key Parameters
Navigate to URL navigate_page type: "url", url: "..."
Go back navigate_page type: "back"
Go forward navigate_page type: "forward"
Reload navigate_page type: "reload"
Take page snapshot take_snapshot verbose: true (optional), filePath: "..." (optional)
Click element click uid: "..." (required), dblClick: true (optional)
Fill input fill uid: "...", value: "..."
Press key press_key key name
Hover element hover uid: "..."
Take screenshot take_screenshot filePath: "..." (optional)
Wait for text wait_for text: ["..."], timeout: N (optional)
Set viewport emulate viewport: "<width>x<height>x<dpr>[,mobile][,touch][,landscape]"
List open pages list_pages -
Select a page select_page page identifier
Handle dialog handle_dialog `action: "accept"
Drag element drag source and target uids
Fill form fill_form multiple fields
Evaluate script evaluate_script function: "() => { ... }", args: [...] (optional)
New page new_page url: "..." (optional)
Close page close_page -
Resize page resize_page dimensions
Upload file upload_file uid: "...", file path

Read the full file on GitHub · 112 lines

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. 12d ago First seen · 112 lines · 1,129 tokens per session scan A ce509e20d9aa

Subscribe to this mod's changes

001-ui-automation-conventions is a cursor rule published in the GitHub repository azam-sdet/10xquality (2 stars, last pushed 6mo ago), licensed MIT. It adds 1,129 tokens to every session, about $0.0056 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.