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 agentmods add skills/idavidov13/agentic-playwright/page-objectsnpx skills add idavidov13/agentic-playwright --skill page-objectsgit clone --depth 1 https://github.com/idavidov13/agentic-playwrightWhat 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 | $0.00129 | $0.03127 |
| Opus 5 | $0.00064 | $0.01563 |
| Sonnet 5 | $0.00026 | $0.00625 |
| Haiku 4.5 | $0.00013 | $0.00313 |
Grade A, and why
page-objects 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 2d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Page Object Model
Critical
- Locators are
getaccessors returningLocator. This is a style/readability convention — Playwright'sLocatoris lazy either way (it only queries the DOM when an action runs), sogetvsreadonlyfield behave identically at runtime. Usegetfor consistency with the rest of the scaffold. - Constructor uses
private readonly page: Page. No other visibility modifiers, no alternative DI patterns. - Page objects import
expect, Locator, Pagefrom@playwright/test— never fromfixtures/pom/test-options.ts(that's for spec files and fixtures). - JSDoc rules:
- Forbidden on locator getters and on any method that returns a
Locator. Names are self-documenting. - Required (with
@paramand@returns) on every action method and every verification method. - Allowed on component fields (e.g.
readonly nav: NavigationComponent) — these are not locators.
- Forbidden on locator getters and on any method that returns a
- Three locator sections when the page has forms or CRUD: interactive-element locators, feedback/validation-message locators, action methods. Feedback locators are not optional — see the
selectorsskill. - Feedback/message strings come from
enums/{area}/*(e.g.Messages.LOGIN_ERROR). Never hardcoded strings insidegetByText(...). - NEVER
page.waitForTimeout(...)inside a page object. Use web-first assertions (await expect(locator).toBeVisible()) orpage.waitForResponse(...). - Exploration with
playwright-cliis mandatory before writing any locators (see theselectorsskill's Exploration-First Workflow). No guessing from wireframes, docs, or screenshots. If the app is unavailable, stop and say so — never ship placeholder locators. - Register every new page object as a fixture in
fixtures/pom/page-object-fixture.ts. Tests consume page objects through the fixture, never vianew PageObject(page).
File Locations
{area}is a placeholder. Before creating or referencing any path below, runls pages/to discover the real subdirectory names in this repo (e.g.,front-office,back-office) and use those instead.
What ships with it
2 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.
- 2d ago First seen · 293 lines · 129 tokens per session scan A 28e50e48881d
page-objects is a skill published in the GitHub repository idavidov13/agentic-playwright (139 stars, last pushed 6d ago), licensed MIT. It adds 129 tokens to every session and 3,127 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
vindicate
Use when the user wants to write, add, fix, stabilize (flaky), refactor, run, or audit Playwright browser tests, draft requirements/stories from a recording (no tests), find test-coverage gaps, scaffold a Playwright project, or set up Playwright CI. Vindicate's guided workflow for grounded, conformant Playwright test…
ac-qa-e2e-review
Reviews spec implementation with E2E visual browser validation via Playwright. Triggers on keywords: e2e review, visual review, spec review, browser validation.
ac-qa-test-e2e
Executes E2E tests from definition files with Playwright browser automation. Triggers on keywords: test e2e, run e2e, execute e2e test, e2e test runner.
ac-qa-browser
Opens browser at URL for E2E testing via playwright-cli. Provides CLI commands for navigation, screenshots, and interaction. Triggers on keywords: browser, open browser, playwright browser, e2e browser.
ac-qa-e2e-template
Template generator for E2E test definitions. Creates structured test files for use with test-e2e skill. Triggers on keywords: e2e template, test template, create test definition.
Playwright Test Builder
Generates robust Playwright end-to-end tests for web pages and user flows.