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/azam-sdet/10xquality/project-instructionsgit clone --depth 1 https://github.com/azam-sdet/10xqualityWrote 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/azam-sdet/10xquality/project-instructions)<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>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 | $0.00547 | $0.00547 |
| Opus 5 | $0.00273 | $0.00273 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
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.
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.
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 · 547 tokens per session scan A d29a274af8e3
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.
Other cursor rules, from other repositories
workflow-discovery-guide
Apply this rule when: Starting a new E2E test and need to understand the user journey Exploring a web application interactively before writing test code Mapping out a multi-step workflow (login, checkout, form submission, etc.) Identifying what to assert at each step of a user journey Using browsernavigate…
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
browser-ops-demo
Agent rules for browser-ops-demo.
puppeteer
This guide provides opinionated, actionable best practices for writing robust, performant, and maintainable Puppeteer scripts for web scraping, automation, and testing. It emphasizes modern patterns like page.locator() and efficient resource management.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.