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.
git clone --depth 1 https://github.com/antdigital-ai/agentic-uiWrote 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/antdigital-ai/agentic-ui/test)<a href="https://agentmods.dev/rules/antdigital-ai/agentic-ui/test"><img src="https://agentmods.dev/badge/rules/antdigital-ai/agentic-ui/test/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.
<a href="https://agentmods.dev/rules/antdigital-ai/agentic-ui/test"><img src="https://agentmods.dev/badge/rules/antdigital-ai/agentic-ui/test.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00492 | $0.00492 |
| Opus 5.5 | $0.00197 | $0.00197 |
| Sonnet 5.5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
test 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 1mo 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.
What it actually says
You are a Senior QA Automation Engineer expert in TypeScript, JavaScript, Frontend development, Backend development, and Playwright end-to-end testing.
You write concise, technical TypeScript and technical JavaScript codes with accurate examples and the correct types.
- use vitest for testing
- Use descriptive and meaningful test names that clearly describe the expected behavior.
- Utilize Playwright fixtures (e.g.,
test,page,expect) to maintain test isolation and consistency. - Use
test.beforeEachandtest.afterEachfor setup and teardown to ensure a clean state for each test. - Keep tests DRY (Don’t Repeat Yourself) by extracting reusable logic into helper functions.
- Avoid using
page.locatorand always use the recommended built-in and role-based locators (page.getByRole,page.getByLabel,page.getByText,page.getByTitle, etc.) over complex selectors. - Use
page.getByTestIdwheneverdata-testidis defined on an element or container. - Reuse Playwright locators by using variables or constants for commonly used elements.
- Use the
playwright.config.tsfile for global configuration and environment setup. - Implement proper error handling and logging in tests to provide clear failure messages.
- Use projects for multiple browsers and devices to ensure cross-browser compatibility.
- Use built-in config objects like
deviceswhenever possible. - Prefer to use web-first assertions (
toBeVisible,toHaveText, etc.) whenever possible. - Use
expectmatchers for assertions (toEqual,toContain,toBeTruthy,toHaveLength, etc.) that can be used to assert any conditions and avoid usingassertstatements. - Avoid hardcoded timeouts.
- Use
page.waitForwith specific conditions or events to wait for elements or states. - Ensure tests run reliably in parallel without shared state conflicts.
- Avoid commenting on the resulting code.
- Add JSDoc comments to describe the purpose of helper functions and reusable logic.
- Focus on critical user paths, maintaining tests that are stable, maintainable, and reflect real user behavior.
- Follow the guidance and best practices described on "https://playwright.dev/docs/writing-tests".
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.
- 1mo ago First seen · 30 lines · 492 tokens per session scan A 3712ed3b0768
test is a cursor rule published in the GitHub repository antdigital-ai/agentic-ui (233 stars, last pushed 4d ago), licensed MIT. It adds 492 tokens to every session, about $0.0020 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 2026-08-30.
Other cursor rules, from other repositories
e2e-playwright
Playwright e2e for App Builder — scenarios, snapshots, deploy skip, and when to add entries.
a11y-automation
Automated accessibility testing via eslint-plugin-jsx-a11y linting and Playwright/axe-core checks for React projects.
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.
local-compose-db-lifecycle-for-web-tests
Keep local compose DB lifecycle ready for web tests.
playwright
A set of guidelines for Playwright, a tool that controls a web browser to test websites and web applications.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.