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 arozumenko/sdlc-skills --skill playwright-testinggit clone --depth 1 https://github.com/arozumenko/sdlc-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/arozumenko/sdlc-skills/playwright-testing)<a href="https://agentmods.dev/skills/arozumenko/sdlc-skills/playwright-testing"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/playwright-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/arozumenko/sdlc-skills/playwright-testing"><img src="https://agentmods.dev/badge/skills/arozumenko/sdlc-skills/playwright-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 | $0.00071 | $0.02315 |
| Opus 5.5 | $0.00028 | $0.00926 |
| Sonnet 5.5 | $0.00014 | $0.00463 |
| Haiku 4.5 | $0.00007 | $0.00231 |
Grade A, and why
playwright-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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Testing (live, via MCP)
Live browser testing for the manual-QA team. You drive a real browser through
the Playwright MCP server (@playwright/mcp) to explore a web app or execute a
test case step-by-step against a running app. You never write or run Playwright
test code — no Page Object Model, no pytest, no .spec.ts files. The output is
a verdict plus evidence, not a test suite.
Writing actual Playwright test code is
test-automation-engineer's job (a different factory's copy of this skill). Here, the browser is your hands.
When to use
app-profiler— explore a running web app: map key flows, capture reliable selectors and fragile areas intoapp_profile.md.test-runner— execute one webTC-NNNcase live: run each step, verify, collect evidence, return a structured result.- Web / PWA / hybrid only. Native iOS/Android → use the
mobile-testingskill. (PWA/hybrid with a mobile viewport is still this skill.)
Core loop — snapshot first
The Playwright MCP exposes browser_* tools. The loop for every check:
browser_navigate(url)— go to{{base_url}}/path(substitutebase_urlfrom the run prompt). Navigation auto-waits for load.browser_snapshot()— the accessibility snapshot gives each element atargetref plus its role and accessible name. You need the ref before you can act, and role/name is what you assert on.- Act by passing that ref as
target(plus a short human-readableelementdescription):browser_click,browser_type,browser_fill_form,browser_select_option,browser_press_key,browser_hover. browser_wait_for({text})/({textGone})— wait for the expected text to appear, or a spinner/loader text to disappear, before continuing.browser_snapshot()again, then collect evidence:browser_take_screenshot,browser_console_messages,browser_network_requests.
Refs go stale. Every target ref comes from the latest snapshot — after
any navigation or DOM change, re-browser_snapshot before acting again. The
server is versioned; this skill is written against the browser_* toolset and
parameter names can shift between @playwright/mcp releases.
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.
- 1mo ago First seen · 186 lines · 71 tokens per session scan A 5a25b41b7651
playwright-testing is a skill published in the GitHub repository arozumenko/sdlc-skills (25 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 2,315 once invoked, about $0.0003 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 2026-08-30.
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.