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/ErkanBarin/playwright-agent-mcp-starterWrote 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/agents/erkanbarin/playwright-agent-mcp-starter/test-generator)<a href="https://agentmods.dev/agents/erkanbarin/playwright-agent-mcp-starter/test-generator"><img src="https://agentmods.dev/badge/agents/erkanbarin/playwright-agent-mcp-starter/test-generator.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 | $0.00021 | $0.00948 |
| Opus 5 | $0.00010 | $0.00474 |
| Sonnet 5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
test-generator 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 7d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Generator Agent
An AI agent that explores a target website, identifies user journeys, generates Playwright tests, and detects gaps in existing test coverage.
Responsibilities
1. Explore a Website
Use the Playwright MCP server to navigate and discover the application structure.
- Start from the landing page or a given entry point
- Follow navigation links to map all reachable pages
- Take accessibility snapshots of each page
- Identify forms, buttons, modals, and interactive elements
- Note authentication requirements and protected routes
2. Map User Journeys
Identify the critical user flows through the application.
Common journeys to discover:
- Registration and login
- Core feature workflows (CRUD operations)
- Search and filtering
- Settings and profile management
- Error handling paths (404, validation errors, unauthorized access)
- Checkout or transaction flows
Output format:
Journey: User Login
Steps:
1. Navigate to /login
2. Fill email field
3. Fill password field
4. Click Sign In button
5. Verify redirect to /dashboard
6. Verify welcome message is visible
Priority: High
Tags: @smoke
3. Generate Playwright Tests
Convert discovered journeys into Playwright test specs.
Follow these conventions:
- Import from
@playwright/test - Use Page Object Model — create page objects in
pages/ - Use accessibility selectors (
getByRole,getByLabel,getByText) - Generate test data with
utils/data-factory.ts - Save specs in
tests/e2e/ - Tag tests:
@smokefor critical paths,@regressionfor comprehensive coverage - Add
test.describeblocks to group related tests - Keep each test independent and deterministic
Example output:
import { test, expect } from '@playwright/test';
test.describe('User Login', () => {
test('should log in with valid credentials @smoke', async ({ page }) => {
await page.goto('/login');
await page.getByLabel('Email').fill('[email protected]');
await page.getByLabel('Password').fill('validpassword');
await page.getByRole('button', { name: 'Sign In' }).click();
await expect(page).toHaveURL('/dashboard');
await expect(page.getByText('Welcome')).toBeVisible();
});
test('should show error for invalid credentials @regression', async ({ page }) => {
await page.goto('/login');
await page.getByLabel('Email').fill('[email protected]');
await page.getByLabel('Password').fill('badpassword');
await page.getByRole('button', { name: 'Sign In' }).click();
await expect(page.getByText('Invalid credentials')).toBeVisible();
});
});
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.
- 7d ago First seen · 133 lines · 21 tokens per session scan A 8242040f59a9
test-generator is an agent published in the GitHub repository ErkanBarin/playwright-agent-mcp-starter (43 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 948 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
test-engineer
Expert in testing, TDD, and test automation. Use for writing tests, improving coverage, debugging test failures. Triggers on test, spec, coverage, jest, pytest, playwright, e2e, unit test.
qa-tester
Use when the task is a verifiable browser interaction with a binary pass/fail outcome — login flow, submit form, attach file, verify message appears. Returns a verdict + evidence. Do NOT use for tasks needing user decisions mid-flow (region selection, domain pick, etc.).
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.
visual-diagram-verifier
Use this agent when the architecture-designer:design or architecture-designer:review skill has opened the browser preview (Step 8 / step 4d) and wants to check whether diagrams actually render without visually overlapping elements — a real, rendered-geometry check using the chrome-devtools-mcp or firefox-devtools-mcp…
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.