Borrowing it
Nothing to install: this file belongs to vchelaru/XnaFiddle. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/vchelaru/XnaFiddle/main/.claude/skills/e2e-testing/SKILL.mdgit clone --depth 1 https://github.com/vchelaru/XnaFiddleWrote 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/vchelaru/xnafiddle/e2e-testing)<a href="https://agentmods.dev/skills/vchelaru/xnafiddle/e2e-testing"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/e2e-testing/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/vchelaru/xnafiddle/e2e-testing"><img src="https://agentmods.dev/badge/skills/vchelaru/xnafiddle/e2e-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.02306 |
| Opus 5.5 | $0.00038 | $0.00922 |
| Sonnet 5.5 | $0.00019 | $0.00461 |
| Haiku 4.5 | $0.00010 | $0.00231 |
Grade A, and why
e2e-testing 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
E2E Testing
Test project: XnaFiddle.E2E.Tests (NUnit + Microsoft.Playwright.NUnit). Nullable is enabled here (unlike BlazorGL/Core — don't copy their nullable-off assumptions). dotnet test auto-discovers every [Test], so adding a test needs no CI edit. Runtime domain facts (leaks, lifecycle, UseReferenceDevice) live in the game-lifecycle skill; this skill is only about authoring tests.
The harness flow
dotnet publish XnaFiddle.BlazorGL -c Release -o <dir>produces the standalone WASM app.PublishOutput.ResolveWebRoot()finds the served web root: honors env varE2E_PUBLISH_DIR, else falls back to<repoRoot>/artifacts/e2e-publish. Accepts either the publish root (has awwwroot) or thewwwrootitself; throws if noindex.html.StaticSiteHost.StartAsync(webRoot)serves it in-process via Kestrel on an OS-assigned port (http://127.0.0.1:0). UsesUseBlazorFrameworkFilesso_frameworkWebcil assemblies getapplication/wasm(a plain static server serves octet-stream, which the browser refuses).MapFallbackToFile("index.html")for deep links.- Playwright drives headless Chromium against
host.BaseUrl.
E2ETestBase (base fixture) owns the expensive shared pieces in OneTimeSetUp: the Kestrel host, Playwright, the browser, and one IBrowserContext. Each [Test] gets a fresh IPage ([SetUp]/[TearDown]) so a still-running game, a set window._canvasContextType, or leftover DOM can't leak across tests. The context is shared (not per-test) so the ~15-20 MB WASM payload stays in the HTTP cache between pages instead of re-downloading each test. SmokeTest and CoreBehaviorsTest both extend it; put shared helpers (BootAsync, ClickRunAsync, WaitForWebGlContextAsync, SetEditorValueAsync, etc.) on the base.
A publish is only servable with the submodules checked out (git submodule update --init --recursive) and the wasm-tools workload installed. Both are silent at build time and fail as e2e symptoms instead: missing submodules make the KNI assemblies 404 at boot (no WebGL context, every test times out), and missing wasm-tools skips native linking so SkiaSharp throws DllNotFoundException: libSkiaSharp on boot, raising the Blazor error banner that every test's AssertNoBlazorErrorAsync then fails on. dotnet workload install wasm-tools needs elevation for a Program Files SDK.
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.
- 1mo ago Changed · +2 lines c99f8adc16be
- 1mo ago First seen · 85 lines · 96 tokens per session scan A 1b467c235362
e2e-testing is a skill published in the GitHub repository vchelaru/XnaFiddle (14 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 2,306 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
verify-omnigent
Drive Omnigent the way a user does and prove a behavior with recorded evidence, using an isolated server, runner, and mock model plus a feature map of every user entry point. Load before reproducing a user-facing bug, before claiming a fix works, or when reviewing whether a change covered every surface (session vs.…
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
critique
Adversarial design critique of the current work. Render it, look at it, and argue for rejection. Run after the gates are green, never instead of them.