agentmods.dev

qa-script-executor

A testing workflow that follows written test scripts in a web browser using Chrome DevTools. It supports desktop and mobile screen settings and adds technical testing hints.

In plain words
What is it for?
Use it to run browser checks such as navigating pages, clicking controls, entering data, and verifying web experiences from scripts in a scripts/ folder.
Why use it?
It turns informal test instructions into a repeatable process, making it easier to check each step and notice failures.

Cursor rule for Cursor

2 5mo ago A scan 0 tokens original MIT
View the source file azam-sdet/10xquality
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.

agentmods
npx agentmods add rules/azam-sdet/10xquality/qa-script-executor
Clone the repo
git clone --depth 1 https://github.com/azam-sdet/10xquality

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 1,196 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01196
Opus 5 $0.00000 $0.00598
Sonnet 5 $0.00000 $0.00239
Haiku 4.5 $0.00000 $0.00120

Measured yesterday against content hash e57b44599566, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qa-script-executor 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 yesterday.

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.

.cursor/rules/qa-script-executor.mdc · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Script Executor Agent

You are an elite QA automation engineer. When the user asks you to execute a test script from the scripts/ folder, follow this protocol precisely.

Execution Protocol

Phase 1: Read & Parse the Test Script

  1. Read the test script file completely
  2. Extract: Goal, View Mode, Pre-requisites, Auth details, Steps
  3. Count total steps and announce the test plan

Phase 2: Browser Setup

  1. Use chrome-devtools MCP server for all browser automation
  2. If view mode is "mobile", call emulate with mobile viewport (width: 375, height: 812, isMobile: true, hasTouch: true)
  3. If view mode is "desktop", use default viewport or call emulate with desktop viewport (width: 1440, height: 900)

Phase 3: Execute Each Step

For every step in the script:

  1. Announce which step you are executing (e.g., "Step 1/8: Navigate to login page")
  2. Take a snapshot before acting (take_snapshot via chrome-devtools) to understand the current page state
  3. Execute the action using the appropriate Chrome DevTools MCP tool:
    • Navigation: navigate_page with {"type": "url", "url": "..."}
    • Click: click with {"uid": "..."} (uid from snapshot)
    • Type/Fill: fill with {"uid": "...", "value": "..."}
    • Keyboard: press_key with key name
    • Hover: hover with {"uid": "..."}
    • Wait: wait_for for dynamic content
    • Screenshot: take_screenshot for visual verification
  4. Verify the action succeeded by taking another snapshot or screenshot
  5. Record the result: PASS or FAIL with details

Phase 4: Enhance the Original Script

After each step executes successfully, update the original test script file in-place by appending technical hints:

Enhancement format:

Original: "Click on login button"
Enhanced: "Click on login button (hint: link element with text 'Login', uid: _7)"

Rules for hints:

  • Add hints in parentheses after the original step text
  • Include element type, visible text, and uid from the snapshot
  • Include CSS selectors or aria labels when available
  • Never remove or modify the original step description
  • Hints make future executions faster and more reliable

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 0 tokens per session scan A e57b44599566

Subscribe to this mod's changes

qa-script-executor is a cursor rule published in the GitHub repository azam-sdet/10xquality (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,196 tokens. 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.

Browser automationMobileTesting
Related

Other cursor rules, from other repositories

abn-experiment-framework

The DuckDuckGo browser includes a comprehensive A/B/N experiment framework that enables data-driven feature testing across iOS and macOS platforms. This framework allows you to safely experiment with new ideas while maintaining control groups and measuring impact.

duckduckgo/apple-browsers · 0 tokens

browserserviceskit-integration

BrowserServicesKit is the core shared library providing essential browser functionality to both iOS and macOS DuckDuckGo applications. It ensures consistent behavior and code reuse across platforms while maintaining privacy as the primary focus.

duckduckgo/apple-browsers · 0 tokens

phantom-wallet

Phantom Connect SDK integration rules for frontend Solana apps (React, React Native, browser).

helius-labs/core-ai · 0 tokens

general

This is the DuckDuckGo browser for iOS and macOS, built with privacy-first principles, modern Swift patterns, and cross-platform architecture.

duckduckgo/apple-browsers · 1,808 tokens

testing

This guide covers testing practices and patterns for the DuckDuckGo browser on iOS and macOS platforms.

duckduckgo/apple-browsers · 0 tokens

react-native-polyfills

Required polyfills and configuration for MetaMask Connect SDK in React Native — import order, Buffer, window, Event/CustomEvent, metro config, and persistence.

MetaMask/metamask-connect-cursor-plugin · 1,177 tokens