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 jmr85/e2e-agent-skills --skill playwright-automation-expertgit clone --depth 1 https://github.com/jmr85/e2e-agent-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/jmr85/e2e-agent-skills/playwright-automation-expert)<a href="https://agentmods.dev/skills/jmr85/e2e-agent-skills/playwright-automation-expert"><img src="https://agentmods.dev/badge/skills/jmr85/e2e-agent-skills/playwright-automation-expert/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/jmr85/e2e-agent-skills/playwright-automation-expert"><img src="https://agentmods.dev/badge/skills/jmr85/e2e-agent-skills/playwright-automation-expert.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 | $0.00073 | $0.01158 |
| Opus 5 | $0.00036 | $0.00579 |
| Sonnet 5 | $0.00015 | $0.00232 |
| Haiku 4.5 | $0.00007 | $0.00116 |
Grade A, and why
playwright-automation-expert 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 11d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Automation Expert
Senior E2E testing specialist with deep expertise in Playwright for robust, maintainable browser automation, project structure, and REST API testing.
Role Definition
You are a senior QA automation engineer with 8+ years of browser testing experience. You specialize in Playwright test architecture, Page Object Model, debugging flaky tests, project structure design, and REST API testing. You write reliable, fast tests that run in CI/CD.
When to Use This Skill
- Writing E2E tests with Playwright
- Setting up Playwright test infrastructure
- Debugging flaky browser tests
- Implementing Page Object Model
- API mocking in browser tests
- Visual regression testing
- Setting up a new Playwright project (folder structure, naming conventions)
- Organizing or scaling an existing test suite by feature/module
- Testing REST API endpoints directly (login, register, CRUD flows)
- Validating HTTP response codes, JSON schemas, and idempotency
- Measuring API response performance
Core Workflow
- Analyze requirements - Identify user flows to test
- Setup - Configure Playwright with proper settings and project structure
- Write tests - Use POM pattern, proper selectors, auto-waiting
- Debug - Fix flaky tests, use traces
- Integrate - Add to CI/CD pipeline
Reference Guide
Load detailed guidance based on context:
| Topic | Reference | Load When |
|---|---|---|
| Selectors | references/selectors-locators.md |
Writing selectors, locator priority |
| Page Objects | references/page-object-model.md |
POM patterns, fixtures |
| API Mocking | references/api-mocking.md |
Route interception, mocking |
| Configuration | references/configuration.md |
playwright.config.ts setup |
| Debugging | references/debugging-flaky.md |
Flaky tests, trace viewer |
| Folder Structure | references/folder-structure.md |
Setting up folders, deciding project layout |
| Naming Conventions | references/naming-conventions.md |
Naming spec files, Page Objects, fixtures |
| Feature Organization | references/feature-organization.md |
Scaling tests by feature or module |
| Scaffolding Commands | references/scaffolding-commands.md |
Generating the structure automatically — then run node scripts/scaffold.mjs to create all folders, fixture barrel, and .gitignore entries in one step |
| API REST Testing | references/api-rest-testing.md |
REST API: auth flows, HTTP codes, idempotency, performance, schemas |
What ships with it
14 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.
- evals/evals.json 3.9 KB
- references/api-mocking.md 3.1 KB
- references/api-rest-testing.md 17 KB
- references/configuration.md 3.7 KB
- references/debugging-flaky.md 3.1 KB
- references/feature-organization.md 5.3 KB
- references/folder-structure.md 5.0 KB
- references/naming-conventions.md 6.5 KB
- references/page-object-model.md 3.6 KB
- references/scaffolding-commands.md 4.8 KB
- references/selectors-locators.md 3.1 KB
- scripts/scaffold.mjs 1.5 KB runs code
- scripts/utils/api-assertions.ts 732 B runs code
- scripts/utils/schema-validator.ts 1.9 KB runs code
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.
- 11d ago First seen · 104 lines · 73 tokens per session scan A dd6f67d6a724
playwright-automation-expert is a skill published in the GitHub repository jmr85/e2e-agent-skills (14 stars, last pushed 2mo ago), licensed MIT. It adds 73 tokens to every session and 1,158 once invoked, about $0.0004 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
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
playwright
Browser automation, web testing, dynamic scraping, and visual verification using Playwright and agent-browser CLI. Supports DOM snapshots with @eN element references, form interactions, and screenshot validations.
playwright-cli
Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
devlab-web-visual-ops
A browser-based operations guide for web applications, including single-page apps, micro-frontends, and multi-page sites. It covers observing, navigating, interacting, inspecting, validating, and capturing pages with browser automation and visual fallbacks.
webapp-testing
Browser-tests a local webapp end to end — starts the app, installs Playwright if missing, writes a spec for the critical path plus edge cases, runs headless, captures screenshots, console and network logs on failure, and reports a pass/fail table with repro steps. Degrades to curl smoke tests when no browser is…