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 Mallikarjun-Roddannavar/playwright-agentic-automation --skill pw-ui-pomgit clone --depth 1 https://github.com/Mallikarjun-Roddannavar/playwright-agentic-automationWrote 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/mallikarjun-roddannavar/playwright-agentic-automation/pw-ui-pom)<a href="https://agentmods.dev/skills/mallikarjun-roddannavar/playwright-agentic-automation/pw-ui-pom"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/pw-ui-pom/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/mallikarjun-roddannavar/playwright-agentic-automation/pw-ui-pom"><img src="https://agentmods.dev/badge/skills/mallikarjun-roddannavar/playwright-agentic-automation/pw-ui-pom.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 | $0.00061 | $0.00980 |
| Opus 5.5 | $0.00024 | $0.00392 |
| Sonnet 5.5 | $0.00012 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
pw-ui-pom 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 20d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PW UI POM
Maintain the UI automation layer in a way that matches this repo's current conventions.
Use This Skill When
- Adding a new UI scenario under
ui/specs. - Repairing or updating an existing UI flow.
- Cleaning up recorded or generated UI tests so they match the framework conventions.
- Creating or changing page-object methods, selectors, waits, or navigation returns.
- Adjusting UI auth/setup behavior in
ui/setuporutils/fixtures/TestFixtures.ts.
Follow These Rules
- Keep selectors in page objects under
ui/pages. - Keep assertions in specs under
ui/specs. - Do not add assertions to page objects.
- Prefer
data-testidlocators and explicit user-visible locators. - Use aliases such as
@pages/*,@utils/*, and@config/*. - Keep shared page behavior in
ui/pages/BasePage.ts.
Inspect First
- Identify the impacted spec, page object, and fixture or setup file before editing.
- Reuse an existing page object and method before adding a new one.
- If the task changes auth or role setup, inspect
ui/setup/auth.setup.tsandutils/fixtures/TestFixtures.ts. - If the task changes navigation or route ownership, inspect
ui/pages/BasePage.tsfirst.
Decide What To Edit
- Edit a page object when selectors, interactions, readiness, or truthful navigation returns change.
- Edit a spec when the scenario, test data, or user-visible expectations change.
- Edit a fixture or setup file only when session creation, role bootstrap, or auth state behavior changes.
- Keep the change in the narrowest layer that actually owns the behavior.
New UI Test Flow
- Inspect a similar spec and the target page object.
- Reuse existing fixture/page-object coverage before adding methods.
- Add selectors only to the relevant page object.
- Keep the spec readable and assertion-focused.
- Register cleanup through the shared
cleanupfixture as soon as the test has the created resource id. - Validate with the smallest relevant command set.
Cleanup Generated Or Recorded UI Tests
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.
- 20d ago Changed c172972638c6
- 1mo ago First seen · 106 lines · 61 tokens per session scan A 052f08457287
pw-ui-pom is a skill published in the GitHub repository Mallikarjun-Roddannavar/playwright-agentic-automation (13 stars, last pushed 20d ago), licensed MIT. It adds 61 tokens to every session and 980 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
verify
How to run and drive this app to verify UI/server changes at runtime.
sidekick-audit
Deterministic UI quality audit of a web page or a whole product — WCAG 2.2 A/AA accessibility (axe-core), Core Web Vitals (LCP/CLS), browser health (console errors, failed requests, mixed content) and tap-target size — reported dimensions-first, with confirmed-vs-uncertain findings clustered into root-cause families…
sidekick-test
Goal-based end-to-end UI testing that PROVES the outcome. Given a URL and a plain-language goal (e.g. 'sign up, create a project, and invite a teammate'), sidekick drives a real browser to do it and then verifies success with a DETERMINISTIC signal on the real page — the execution agent is never allowed to grade its…
textual-ui-developer
Develop and debug the MassGen Textual TUI with deterministic replay, snapshot regression tests, and targeted runtime checks.
dogfood
Systematic exploratory QA testing of web applications — find bugs, capture evidence, and generate structured reports.