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 instructions/m3au/playwright-bdd-cursor-template/claude-mdgit clone --depth 1 https://github.com/m3au/playwright-bdd-cursor-templateWrote 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/instructions/m3au/playwright-bdd-cursor-template/claude-md)<a href="https://agentmods.dev/instructions/m3au/playwright-bdd-cursor-template/claude-md"><img src="https://agentmods.dev/badge/instructions/m3au/playwright-bdd-cursor-template/claude-md.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 5.1 | $0.02749 | $0.02749 |
| Opus 5 | $0.01375 | $0.01375 |
| Sonnet 5 | $0.00550 | $0.00550 |
| Haiku 4.5 | $0.00275 | $0.00275 |
Grade A, and why
playwright-bdd-cursor-template CLAUDE.md 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 5d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This is the Playwright BDD Cursor Template repository - a production-ready E2E testing framework optimized for Cursor IDE's AI assistant. It provides a complete, opinionated setup for writing maintainable end-to-end tests with built-in accessibility and performance auditing.
Running Tests
Test Commands
- Run all E2E tests:
bun run test- Automatically runs
bunx bddgen(pretest) to generate test files from Gherkin features - Runs all Playwright projects (UITestingPlayground, AutomationExercise, JSONPlaceholder)
- Automatically runs
- Run specific challenge:
bun run test:uitestingplaygroundorbun run test:automationexercise - Run in UI mode:
bun run ui- Interactive test runner - Run in headed mode:
bun run headed- Visible browser - Run in debug mode:
bun run debug- Playwright Inspector - Run only failed tests:
bun run failed- Re-run last failed tests - Run unit tests:
bun test- Runs unit tests with coverage (configured viabunfig.toml)
Test Organization
Tests are organized by challenge in tests/e2e/challenges/:
tests/e2e/challenges/uitestingplayground/- UI testing challenges (23 scenarios)tests/e2e/challenges/automationexercise/- E-commerce challenges (15 scenarios)tests/e2e/challenges/jsonplaceholder/- API testing challenges (34 scenarios)
Each challenge contains:
features/- Gherkin feature files (.feature)poms/- Page Object Models (TypeScript files with BDD decorators)pages/- Page-level POMscomponents/- Reusable component POMs (UITestingPlayground only)
services/- API Object Models (JSONPlaceholder only)
Writing Tests
Tests use Playwright with BDD decorators directly on POM methods. No separate step-definition files needed.
Key Patterns:
- Page Object Models - All page interactions go through POMs in
tests/e2e/challenges/*/poms/- Locators must be declared at class top and initialized in constructor
- Use
@Fixturedecorator with PascalCase name matching class name - Constructor receives
Pageasprivate page: Pageorprotected page: Page
- BDD Decorators - Use
@Given,@When,@Thendecorators directly on POM methods- Step text must match Gherkin scenarios exactly
- All step methods must be
async
- Internal Helper Methods - Use
@Stepdecorator for helper methods- Must start with "i" following BDD naming:
iSee...,iClick...,iSelect...,iNavigate...
- Must start with "i" following BDD naming:
- Fixture Registration - POMs are registered as fixtures using
@Fixturedecorator - Path Aliases - Use path aliases instead of relative imports:
@world-tests/e2e/world.ts(decorators, expect, types)@components/*- Component POMs (UITestingPlayground only)@pages/*- Page POMs (UITestingPlayground only)@automationexercise/*- AutomationExercise challenge resources@utils-tests/utils/index.ts
- Environment Variables - Access via
environment('BASE_URL_*')from@world
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.
- 5d ago First seen · 231 lines · 2,749 tokens per session scan A 4f330175c634
playwright-bdd-cursor-template CLAUDE.md is an instructions file published in the GitHub repository m3au/playwright-bdd-cursor-template (2 stars, last pushed 6mo ago), licensed MIT. It adds 2,749 tokens to every session, about $0.0137 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 instructions, from other repositories
wcagc-mcp AGENTS.md
AGENTS.md instructions for WCAG-Compliance/wcagc-mcp, covering agents.md — wcagc-mcp (node/ts, mcp server), 1. ⚠️ bump the version — every change that ships, 2. releasing is automatic — do not run publish commands, 3. hosted and local must stay identical and 4. honesty rules (roadmap §2.6 — non-negotiable).
wcagc-mcp CLAUDE.md
Claude Code instructions for WCAG-Compliance/wcagc-mcp, covering claude.md — wcagc-mcp, the one that bites and quick reminders (full detail in agents.md).
periscope-mcp CLAUDE.md
Claude Code instructions for segentic-lab/periscope-mcp, covering periscope-mcp - project guide, what this is, how to run, key files and adding a new mcp tool.
Playwright-AI-Agent-POM-MCP-Server copilot-instructions.md
Copilot instructions for padmarajnidagundi/Playwright-AI-Agent-POM-MCP-Server, a project described as: Playwright AI Agent POM MCP ServerPlaywright AI Agent using Page Object Model (POM) architecture with MCP Server integration for automated web and mobile testing.
ACCESSIBILITY.md AGENTS.md
AGENTS.md instructions for mgifford/ACCESSIBILITY.md, covering repository instructions for ai coding agents, scope, when each instruction file is useful, project mission and status and required project context.
monochrome-ui AGENTS.md
AGENTS.md instructions for vaneenige/monochrome-ui, covering agents.md, north stars (non-negotiables), why the core looks weird (and should stay weird), clever tricks and code style.