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 simiancraft/simiancraft-skills --skill playwright-camera-mask-testinggit clone --depth 1 https://github.com/simiancraft/simiancraft-skillsWrote 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/simiancraft/simiancraft-skills/playwright-camera-mask-testing)<a href="https://agentmods.dev/skills/simiancraft/simiancraft-skills/playwright-camera-mask-testing"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/playwright-camera-mask-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/simiancraft/simiancraft-skills/playwright-camera-mask-testing"><img src="https://agentmods.dev/badge/skills/simiancraft/simiancraft-skills/playwright-camera-mask-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 | $0.00158 | $0.01649 |
| Opus 5 | $0.00079 | $0.00825 |
| Sonnet 5 | $0.00032 | $0.00330 |
| Haiku 4.5 | $0.00016 | $0.00165 |
Grade A, and why
playwright-camera-mask-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 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Camera / Mask Testing: specialization of playwright-harness
Read playwright-harness first. The base owns prerequisites, the run pattern
(write to /tmp/pw-*.mjs, run with playwright resolvable), and the drive/assert
- WebGL-GPU patterns. This skill changes only how the camera is fed. MediaPipe selfie segmentation runs in WASM and works headless.
Prerequisites (in addition to the base)
ffmpeg, only to turn the still fixture into the looping .y4m Chrome plays as a
fake camera; no system install needed, npm i ffmpeg-static in a /tmp dir gives a
binary path.
This skill ships two fixtures (derivations and provenance in
fixtures/README.md):
fixtures/person-web.png: a 640x480 webcam-shaped frame, full-body subject occupying ~82% of frame height, vertically centered, on a clean light-gray ground (#CDD0D4). Derived fromandroid-emulator-mask-testing/fixtures/person-framed.png. Web presents the capture file 1:1 (no sensor crop), so do NOT reuse the Android fixture directly; its left-quarter framing compensates an emulator sensor shift that does not exist on web.fixtures/office-empty.png: a 1280x720 empty office, the no-person negative case: a realistic scene (furniture, plants, windows, hard shadows) with nothing segmentable in it. Use it to mock the scene itself when the feed should contain no one.
The three camera modes (pick by what you are asserting)
-
Green-ball mode (Chromium's built-in synthetic feed): proves the pipeline RUNS end to end (getUserMedia resolves, effects apply, no page errors). Useless for mask quality; the feed has no person.
args: [ '--use-fake-device-for-media-stream', '--use-fake-ui-for-media-stream', // auto-grants the permission prompt '--autoplay-policy=no-user-gesture-required', ] -
Person mode (file-backed feed): proves mask SHAPE and compositing (person kept, background replaced/blurred). Add one flag; it requires
--use-fake-device-for-media-streamto be present too:
What ships with it
3 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 · 137 lines · 158 tokens per session scan A 9762301077eb
playwright-camera-mask-testing is a skill published in the GitHub repository simiancraft/simiancraft-skills (7 stars, last pushed 6d ago), licensed MIT. It adds 158 tokens to every session and 1,649 once invoked, about $0.0008 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
test-site
Tests a deployed, activated Power Pages site at runtime using browser-based navigation, page crawling, and API request verification via Playwright. Use when the user wants to test, verify, or smoke-test their deployed site.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
browser-check
Drive a real browser and come back with a MEASUREMENT rather than an impression - console errors and >=400 responses as counts, computed styles as JSON when appearance is disputed. Use when work touches UI, when a review must verify one, or when fidelity-gate asks for its measurement.
symfony:e2e-panther-playwright
Write end-to-end tests with Symfony Panther 2.4 for browser automation or Playwright for complex scenarios.
browser-testing
Test and debug browser code with Chrome DevTools MCP. Use when building or debugging browser UI, inspecting the DOM, capturing console errors, analyzing network requests, or verifying visual output.
write-e2e
Generate Playwright E2E tests from codebase analysis. Discovers routes, scores user flows by criticality, writes .spec.ts files that assert causality, and reports what was actually proven: GENERATED, STATICCHECKED, VERIFIEDLOCAL or VALIDATEDLIVE. Modes: --scope , --flow , --output , --base-url , --max-flows N, --live…