Repository rules describing the technology stack and coding practices for a QA automation project. The project uses a Next.js demo app, Playwright browser tests, and GitHub Actions.

Choosing compatible Node, TypeScript, Next.js, and Playwright patterns; updating the demo app; and maintaining end-to-end tests and CI.

They keep development and CI changes aligned with the project’s versions, structure, testing approach, and accessibility expectations.

tech-stack — Cursor rule for Cursor by nirarad/playwright-ai-qa-agent

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/nirarad/playwright-ai-qa-agent

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.

README.md

[![agentmods](https://agentmods.dev/badge/rules/nirarad/playwright-ai-qa-agent/tech-stack/github.svg)](https://agentmods.dev/rules/nirarad/playwright-ai-qa-agent/tech-stack)

Your own site

<a href="https://agentmods.dev/rules/nirarad/playwright-ai-qa-agent/tech-stack"><img src="https://agentmods.dev/badge/rules/nirarad/playwright-ai-qa-agent/tech-stack/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.

Your own site · 80×15

<a href="https://agentmods.dev/rules/nirarad/playwright-ai-qa-agent/tech-stack"><img src="https://agentmods.dev/badge/rules/nirarad/playwright-ai-qa-agent/tech-stack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 719 This file is loaded in full into every session.

When invoked 719 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.

Model	Per session	Once invoked
Fable 5.1	$0.00719	$0.00719
Opus 5.5	$0.00288	$0.00288
Sonnet 5.5	$0.00144	$0.00144
Haiku 4.5	$0.00072	$0.00072

Measured 2mo ago against content hash f6c2a71f59f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tech-stack 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 2mo 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/tech-stack.mdc · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Technology Stack

This repo is a portfolio-grade QA automation system:

demo-app/: Next.js demo web app used as the test target
Playwright E2E tests run in CI
An AI failure agent classifies Playwright failures and creates GitHub Issues or PRs

Runtime + Language

Node.js 20 (CI baseline)

CI: GitHub Actions should use Node 20
Local: use Node 20+ to match CI behavior

TypeScript 5.x

Use strict TypeScript where applicable
Prefer import type { ... } for type-only imports

Demo App (Target Under Test)

Next.js 14 (App Router)

Use App Router conventions: app/, page.tsx, layout.tsx, route.ts
Server Components by default; only use 'use client' for interactivity/state
Use next/image for images when relevant
Use Next.js Metadata API for SEO where applicable

Tailwind CSS

Use Tailwind utilities for styling (avoid inline styles)
Keep UI accessible (labels, aria attributes, keyboard navigation)

Storage + Auth (demo-only)

localStorage for users/session/tasks
Break Mode stored in localStorage to force predictable failures

E2E Testing

Playwright Test

Use @playwright/test
Configure reporters:
- JSON reporter to test-results/results.json
- HTML report to test-results/html-report
Configure diagnostics:
- screenshots only on failure
- trace/video on first retry (CI)

Test Targeting

Prefer data-testid for stable element targeting
Break Mode selector-change is allowed to rename data-testid to simulate locator breakage

CI/CD

GitHub Actions

Workflow runs Playwright, uploads artifacts, then runs the agent on failure
Use continue-on-error: true on the Playwright step so the agent can run
Always upload test-results/ artifacts
Fail the job after the agent runs when tests failed (so checks are red)
Mandatory CI safety policy for agent execution:
- See ci-agent-guardrails.mdc

Vercel (Demo App Hosting)

Read the full file on GitHub · 100 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.

2mo ago First seen · 100 lines · 719 tokens per session scan A f6c2a71f59f3

Subscribe to this mod's changes

tech-stack is a cursor rule published in the GitHub repository nirarad/playwright-ai-qa-agent (6 stars, last pushed 6mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0029 per session on Opus 5.5. 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.

tech-stack