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/shapediver/AppBuilderSdkWrote 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/rules/shapediver/appbuildersdk/e2e-playwright)<a href="https://agentmods.dev/rules/shapediver/appbuildersdk/e2e-playwright"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/e2e-playwright/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/rules/shapediver/appbuildersdk/e2e-playwright"><img src="https://agentmods.dev/badge/rules/shapediver/appbuildersdk/e2e-playwright.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 | $0.00000 | $0.00936 |
| Opus 5.5 | $0.00000 | $0.00374 |
| Sonnet 5.5 | $0.00000 | $0.00187 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
e2e-playwright 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 22d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright e2e
- Discovery:
tests/helpers/fetchAppLinks.tscrawls the rendered App Builder and BETA pages. Do not parsedefinitions.md— those files are stubs filled fromexamples.jsonat docs build. Every discovered slug gets smoke + visual tests;scenarioActions.tsonly adds interactions. - Scenarios:
tests/config/scenarioActions.ts— one entry per slug:params(e.g.gfor settings file),actions(page, slug)ornamedActions[](one Playwright test per name). E-commerce and tools APIs have dedicated specs (tests/specs/ecommerceApi.spec.ts,tests/specs/toolsApi.spec.ts) so they do not duplicate smoke/visual ofexample-executeActions. Those specs loop a namedactions[](one Playwright test per API method). - Helpers:
viewportCoords(normalised to the canvas bounding box; canvas starts at x=300 in the default layout),waitForModelRecomputed,takeSnapshot,getParameterElement,getStandardContainer/setViewportBelowMobileBreakpoint/setViewportBelowNavbarBreakpoint/openAppShellNavbar/expectAppShellNavbarCollapsed(tests/helpers/appBuilderContainers.ts; AppShellmdis 992px; collapsed navbar uses thehiddenattribute — PlaywrighttoBeHidden()is not reliable because Mantine CSS keeps a layout box). E-commerce and tools e2e both use the localhost parent onhttp://127.0.0.1:3000(tests/fixtures/cross-window, iframename="app"). E-commerce:openCrossWindowScenario, parent__connector. Tools:openToolsApiScenario(?api=tools), Open agent stubbed towindow.parentbecause deployed App Builder sends COOPsame-origin(a popup to localhost haswindow.opener === null); parent__toolsApi. SDV, recompute, and notifications usesdvTarget(page)(the iframe). SettingsagentOverrideis a test intercept so Open agent appears; App Builder source is unchanged.example-ecommerceApicovers every connector method exceptaddToCart(dummy parent rejects after creating a model state).example-toolsApicovers every in-scope generic tool.example-mobileFallback(public/example-mobileFallback.json) covers AppShell theme + JSON overlay + one-hop chain: desktop slots, closed-navbar portrait/landscape layout (leftoverrightin the grid), and open-navbar drawer contents.example-mobileFallback-grid(public/example-mobileFallback-grid.json) is the same remapping on Grid (no burger; leftoverleft/right/bottomall on screen).example-mobileFallback-tabscovers a tabbed source container and extras landing in a tabbed target’s active tab.example-mobileFallback-anchorscovers 3d default-to-right vs JSON overlay, 2d theme isolation, and closed-anchorpreviewIconswap.example-mobileFallback-keepBottomcovers AppShellkeepBottomInGridleftover bottom in the main grid. - Device: Desktop Chrome, 1280x800. Mobile-fallback cases resize below
md(390×844 portrait, 900×700 landscape). - Deterministic snapshots:
public/example-simple-interaction-colors.jsonviaparams: {g: ...}instead of pixel tolerances. - New behaviours get a scenario entry; models not yet on the test server get the entry without running it.
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.
- 22d ago Changed b4e44c808a37
- 25d ago Changed 903d4435acb3
- 1mo ago Changed · +1 lines 04b36f6c807a
- 1mo ago First seen · 22 lines · 0 tokens per session scan A 1e121a81c977
e2e-playwright is a cursor rule published in the GitHub repository shapediver/AppBuilderSdk (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 936 tokens. 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 2026-09-10.
Other cursor rules, from other repositories
puppeteer
This guide provides opinionated, actionable best practices for writing robust, performant, and maintainable Puppeteer scripts for web scraping, automation, and testing. It emphasizes modern patterns like page.locator() and efficient resource management.
vasu-playwright-utils
../../templates/cursor-rules/vasu-playwright-utils.mdc.
qa-script-executor
QA Script Executor - Executes natural language test scripts using Chrome DevTools MCP and enhances them with technical hints.
playwright
Playwright: e2e testing, page objects, fixtures, assertions.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.