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/dork-labs/dorkos/browser-testingnpx skills add dork-labs/dorkos --skill browser-testinggit clone --depth 1 https://github.com/dork-labs/dorkosWhat 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 | $0.00055 | $0.02557 |
| Opus 5 | $0.00028 | $0.01278 |
| Sonnet 5 | $0.00011 | $0.00511 |
| Haiku 4.5 | $0.00006 | $0.00256 |
Grade A, and why
browser-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 3d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Browser Testing Methodology
1. When to Write a Browser Test vs Unit Test
Browser test (Playwright):
- Cross-component flows (sidebar click updates chat panel)
- SSE streaming verification (message send → streaming indicator → response rendered)
- Real API calls through the full stack (client → Express → Agent SDK)
- CSS/layout regressions visible only in a real browser
- Browser-specific behavior (keyboard shortcuts, focus management)
Unit test (Vitest):
- Individual component rendering and props
- Hook logic and state transitions
- Service functions and data transformations
- Schema validation (Zod)
- Pure utility functions
Rule of thumb: If the behavior spans multiple FSD layers or requires a real server, it's a browser test.
2. Page Object Model Patterns
POMs live in apps/e2e/pages/ and are injected as Playwright fixtures via fixtures/index.ts.
Each POM encapsulates locators and interaction methods for one page or component:
// apps/e2e/pages/FeaturePage.ts
import type { Page, Locator } from '@playwright/test';
export class FeaturePage {
readonly page: Page;
readonly primaryAction: Locator;
constructor(page: Page) {
this.page = page;
this.primaryAction = page.getByRole('button', { name: /action/i });
}
async doAction() {
await this.primaryAction.click();
}
}
Register in fixtures:
// apps/e2e/fixtures/index.ts
import { test as base } from '@playwright/test';
import { FeaturePage } from '../pages/FeaturePage';
export const test = base.extend<{ featurePage: FeaturePage }>({
featurePage: async ({ page }, use) => {
await use(new FeaturePage(page));
},
});
Test files import from fixtures, never from @playwright/test directly:
import { test, expect } from '../../fixtures';
3. Selector Strategy
Priority order:
-
getByRole()— Best: semantic, resilient to UI changespage.getByRole('button', { name: /send/i }); page.getByRole('textbox', { name: /message/i }); page.getByRole('tab', { name: /settings/i });
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.
- 3d ago First seen · 224 lines · 55 tokens per session scan A 0461246aebc5
browser-testing is a skill published in the GitHub repository dork-labs/dorkos (9 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 2,557 once invoked, about $0.0003 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
browser-proof
Browser-visible verification — route smoke, screenshots, console errors. Receipt required.
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.
auto-ui-explorer
UI 自动化全流程 E2E 测试编排技能。基于"脚本全栈扫描 -> 大模型手工精修 -> 跨页流程编排 -> MCP单点执行"的高阶测试体系。当用户要求测试完整业务流、集成测试或传入整个模块路径时触发。.
playwright-cli
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-cli
Automate browser interactions, test web pages and work with Playwright tests.
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.