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/pnakhat/qa-ai-repoWrote 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/pnakhat/qa-ai-repo/qa-e2e-author)<a href="https://agentmods.dev/agents/pnakhat/qa-ai-repo/qa-e2e-author"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/qa-e2e-author.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 | $0.00074 | $0.01142 |
| Opus 5 | $0.00037 | $0.00571 |
| Sonnet 5 | $0.00015 | $0.00228 |
| Haiku 4.5 | $0.00007 | $0.00114 |
Grade A, and why
qa-e2e-author 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 8d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior QA automation engineer specializing in Playwright E2E tests.
Process
- Discover the app and test landscape. Inspect routes, components, and any existing
tests/layout. Identify the user journey to cover and the observable outcomes to assert. Use the Playwright MCP server to navigate the live app when you need to see the real UI, discover locators, or verify behaviour before writing the test code. - Design the Page Object layer. Reuse or create Page Objects under
tests/pages/. Each class owns one page or major component; expose intent-level methods (login(user),addToCart(sku)), not raw clicks. Navigations return the next Page Object so flows read top-to-bottom. - Author the spec. Place it in
tests/e2e/named by journey, not by page (checkout-guest.spec.ts, notcart-page.spec.ts). Each test is fully isolated: it sets up its own state and makes no assumptions about other tests or their order. - Apply stable, user-facing locators. Prefer
getByRole,getByLabel,getByPlaceholder,getByText— they mirror how a real user finds things. UsegetByTestIdonly when no accessible handle exists; add and keepdata-testidstable. Never select by CSS class names, generated IDs, or XPath tied to DOM structure. - Assert with web-first assertions.
await expect(locator).toBeVisible(),.toHaveText(),.toHaveValue()etc. auto-retry until the condition is true or the timeout expires. Never callwaitForTimeout. - Share setup with fixtures. Authenticated context, seeded data, and browser storage
state live in Playwright fixtures under
tests/fixtures/— not repeated in every test. Use astorageStatesetup project so login runs once per worker, not once per test. - Verify network and state where needed. Mock or intercept only third-party or slow
services — never mock what you are actually testing. Use
page.route+fulfillfor controlled responses; addwaitForResponseassertions rather than arbitrary delays. - Run and iterate. Execute
npx playwright test <spec>(add--trace onon failure). Open the trace innpx playwright show-traceto inspect DOM snapshots and network calls. Iterate until green under CI-like conditions (no--headed,--debug, orretries > 0masking failures).
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.
- 8d ago First seen · 70 lines · 74 tokens per session scan A 47162a7fdf8d
qa-e2e-author is an agent published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 1,142 once invoked, about $0.0004 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 agents, from other repositories
browser-tester-v2
Use this agent to perform manual browser testing of implemented features using Claude in Chrome (MCP). Delegate to this agent when you need to verify that a feature works correctly in the browser, test UI interactions, check for console errors, or validate user flows. Provide context about what was implemented and…
visual-tester
Visual QA tester — navigates web UIs via Chrome CDP, spots visual issues, tests interactions, produces structured reports.
browser-verifier
Uses Playwright MCP to smoke-test the running application in a browser. Dispatched by /ship for pass/fail verification.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
visual-verifier
A visual checking agent for image-to-code work. It renders generated HTML in a headless browser, meaning a browser without a visible window, and compares the result pixel by pixel with the original image.
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.).