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 skills add pnakhat/qa-ai-repo --skill playwright-bddgit 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/skills/pnakhat/qa-ai-repo/playwright-bdd)<a href="https://agentmods.dev/skills/pnakhat/qa-ai-repo/playwright-bdd"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/playwright-bdd/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/skills/pnakhat/qa-ai-repo/playwright-bdd"><img src="https://agentmods.dev/badge/skills/pnakhat/qa-ai-repo/playwright-bdd.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 | $0.00089 | $0.01503 |
| Opus 5 | $0.00044 | $0.00751 |
| Sonnet 5 | $0.00018 | $0.00301 |
| Haiku 4.5 | $0.00009 | $0.00150 |
Grade A, and why
playwright-bdd 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 10d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright → BDD Converter
Turn @playwright/test specs into BDD with playwright-bdd (runs Gherkin
.feature files on the Playwright test runner). The point of BDD is a spec the
business can read — so the .feature files describe behavior in domain
language, and all the mechanical detail (locators, clicks, waits) lives in step
definitions and page objects. See reference.md for setup/wiring and
gherkin-style.md for the business-language rules.
The golden rule
Feature files contain zero UI mechanics. No click, fill, selectors, URLs,
or waits in Gherkin. A step reads like a product requirement:
- ❌
When I click "#login-btn" and type "[email protected]" into "#email" - ✅
When she signs in as a registered customer
The imperative "how" goes into the step definition, which calls a page-object method. If a non-engineer can't read the scenario, it's wrong.
Conversion method (per test)
- Recover the intent. Read the imperative test and ask: what user goal and what behavior(s) does it verify? Ignore the mechanics for now.
- Split by behavior. One
Scenario= one behavior/outcome. A test that asserts several unrelated things becomes several scenarios. - Map to Given / When / Then in domain terms:
- preconditions/state → Given
- the user action or event under test → When
- the observable business outcome → Then Use the product's vocabulary (customer, cart, invoice), never widget names.
- Extract page objects. Turn the raw steps into intent-level methods on a
POM (
loginPage.signInAs(user),cart.checkout()). These carry the clicks. - Write step definitions that bind each Gherkin step to a POM method via
fixtures (see
reference.md) — thin glue, no assertions logic beyond calling the object and checking outcomes. - Parameterize data variations as a
Scenario Outline+Examples, where the examples are business-meaningful values (not test scaffolding). - Factor shared setup into
Background(business preconditions), and reuse steps across features — write them once, phrase them generically. - Verify parity. Run
bddgenthenplaywright test; the BDD suite must cover the same behavior as the original before you delete it.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 101 lines · 89 tokens per session scan A c004dfc0ae7e
playwright-bdd is a skill published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 1,503 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 skills, from other repositories
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
test-warp-ui
Guides testing Warp UI features and changes using the computer use tool. Use this skill only when computer-use testing was requested (explicit request or accepted offer) and the computeruse tool is available to the agent. Covers launching Warp and verifying UI behavior.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
pyats-dynamic-test
Generate and execute deterministic pyATS aetest validation scripts - interface state, OSPF neighbors, BGP paths, ping matrices, and custom compliance tests. Use when writing a network test, validating post-change state, running pass/fail checks, or building automated regression tests.
test-loop
Plan, generate, and heal an executable E2E test suite from approved acceptance criteria (web and mobile).
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…