project-instructions

project-instructions is a cursor rule for Cursor from azam-sdet/10xquality. It costs 547 tokens per session, scanned A, original, MIT.

Project-level rules for a browser-based UI test automation framework. The framework uses natural-language test scripts, Chrome DevTools MCP for browser control, and Playwright with Cucumber for behavior-driven tests.

In plain words
What is it for?
Use it as the main guidance when working with the recorder, test scripts, browser execution, BDD conversion, project files, or generated test reports.
Why use it?
It gives the project a shared structure for recording, running, converting, and reporting tests, so these activities follow the same conventions.

Cursor rule for Cursor

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/project-instructions
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 project-instructions

README.md
[![agentmods](https://agentmods.dev/badge/rules/azam-sdet/10xquality/project-instructions.svg)](https://agentmods.dev/rules/azam-sdet/10xquality/project-instructions)
Your own site
<a href="https://agentmods.dev/rules/azam-sdet/10xquality/project-instructions"><img src="https://agentmods.dev/badge/rules/azam-sdet/10xquality/project-instructions.svg" alt="Measured on agentmods" height="20"></a>
Per session 547 This file is loaded in full into every session.
When invoked 547 The same file — it is already loaded in full.
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 $0.00547 $0.00547
Opus 5 $0.00273 $0.00273
Sonnet 5 $0.00109 $0.00109
Haiku 4.5 $0.00055 $0.00055

Measured 4d ago against content hash d29a274af8e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

project-instructions 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.

.cursor/rules/project-instructions.mdc · 51 lines

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.

10x Quality — AI-Powered UI Test Automation Framework

This is a QA test automation framework powered by Cursor AI and Chrome DevTools MCP. Test scripts are written in natural language and executed by the AI agent using browser automation.

Project Structure

.
├── .cursor/rules/
│   ├── qa-script-executor.mdc              # Execute test scripts via Chrome DevTools MCP
│   ├── qa-recorder.mdc                     # Record manual browser interactions as test scripts
│   ├── script-to-bdd-converter.mdc        # Convert recorded scripts to Playwright+Cucumber tests
│   └── playwright-cucumber-conventions.mdc # BDD framework conventions + locator strategies
├── src/recorder/
│   ├── inject-recorder.js                  # Recorder script injected into browser
│   └── retrieve-events.js                  # Script to collect recorded events
├── scripts/
│   ├── template.md                         # Test script template
│   └── *.md                                # Test scripts (natural language)
├── reports/
│   └── test-report-*.md                    # Generated test reports
└── .mcp.json                               # MCP server configuration

Three Ways to Create & Run Tests

1. Write manually (AI-powered execution)

Write a test script in scripts/ using natural language, then ask: "Please execute the test script at scripts/my-test.md"

2. Record from browser → Natural language script

Ask: "Record a test for https://example.com" — interact with the browser manually. The agent captures every click, type, and navigation with rich metadata (locators, labels, ambiguity counts), then generates a natural language script.

3. Record → Convert to Playwright + Cucumber BDD (recommended for CI/CD)

After recording, ask: "Convert scripts/my-test.md to Playwright + Cucumber tests." The converter uses the recorded metadata (field labels, data-test attributes, DOM context) to generate Page Objects with reliable, unambiguous locators that work on the first run.

Read the full file on GitHub · 51 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. 4d ago First seen · 51 lines · 547 tokens per session scan A d29a274af8e3

Subscribe to this mod's changes

project-instructions is a cursor rule published in the GitHub repository azam-sdet/10xquality (2 stars, last pushed 5mo ago), licensed MIT. It adds 547 tokens to every session, about $0.0027 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.