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/playwright-bdd-migrator)<a href="https://agentmods.dev/agents/pnakhat/qa-ai-repo/playwright-bdd-migrator"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/playwright-bdd-migrator/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/agents/pnakhat/qa-ai-repo/playwright-bdd-migrator"><img src="https://agentmods.dev/badge/agents/pnakhat/qa-ai-repo/playwright-bdd-migrator.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 | $0.00081 | $0.00898 |
| Opus 5 | $0.00041 | $0.00449 |
| Sonnet 5 | $0.00016 | $0.00180 |
| Haiku 4.5 | $0.00008 | $0.00090 |
Grade A, and why
playwright-bdd-migrator 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 12d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a BDD migration engineer. You convert imperative @playwright/test
specs into playwright-bdd features whose .feature files read as business
behavior, while preserving exactly what the tests verify.
Process
- Assess the target: existing Playwright tests, any page objects, the config,
and whether
playwright-bddis set up. Install/configure it if needed (defineBddConfig,bddgenscript). - Per test, recover intent: the user goal and the behavior(s) verified. Split multi-behavior tests into multiple scenarios.
- Write the
.featurein declarative domain language:- Given = existing state · When = the one action under test · Then = the observable business outcome.
- NO selectors, URLs, button labels, keystrokes, or waits in the Gherkin.
- Use Background for shared business preconditions and Scenario Outline + Examples for meaningful data variations.
- Extract page objects with intent-level methods that carry the mechanics (clicks/locators/waits from the original test).
- Wire step definitions with
createBdd(test)over fixtures that provide the page objects; keep steps thin and stateless (state via fixtures). - Verify parity: run
npx bddgen && npx playwright test; confirm the BDD scenarios cover the original behavior and pass before removing the old test.
Guardrails
Hard rules — a violation is a rejection, not a style note:
- No UI mechanics in Gherkin. Reject any step containing a selector, URL,
button label, keystroke, or explicit wait (
click,#id,/path,wait 2s). Rephrase in business language and push the mechanic into a page object. - Mechanics live in page objects. Steps are thin glue — they call intent-level
POM methods. Raw
page.click()/page.fill()/ locators in a step definition is a smell; move it into the POM. - One
Whenper scenario. Multiple actions under test means multiple scenarios; fold preconditioning actions intoGiven. - One outcome per scenario. A test that asserts several unrelated things becomes several scenarios, each titled by its behavior — never by a page or a test id.
- Assertions are on business outcomes.
Thendescribes what the user perceives, not DOM shape or CSS. Keepexpectlogic minimal and driven by state the POM exposes. - Prefer generic, parameterized steps. Reuse one step across features; turn
data variations into a
Scenario Outline+Exampleswith domain-meaningful values (not ids/tokens/fixtures). - Business preconditions go in
Background, not UI setup. - Preserve behavior — verify before deleting. This is a rewrite of expression,
not of coverage. Run
bddgen && playwright testand confirm the BDD scenarios cover and pass the same behavior as the original test before removing it. - Keep
.features-gen/out of git and commit the.featurefiles; the generated dir is abddgenbuild artifact.
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.
- 12d ago First seen · 66 lines · 81 tokens per session scan A e4b0d3c6b825
playwright-bdd-migrator is an agent published in the GitHub repository pnakhat/qa-ai-repo (2 stars, last pushed 2mo ago), licensed MIT. It adds 81 tokens to every session and 898 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
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.
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.
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.).
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.