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/summarybotng/summarybot-ng/compatibility-testingnpx skills add summarybotng/summarybot-ng --skill compatibility-testinggit clone --depth 1 https://github.com/summarybotng/summarybot-ngWrote 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/summarybotng/summarybot-ng/compatibility-testing)<a href="https://agentmods.dev/skills/summarybotng/summarybot-ng/compatibility-testing"><img src="https://agentmods.dev/badge/skills/summarybotng/summarybot-ng/compatibility-testing.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.01482 |
| Opus 5 | $0.00018 | $0.00741 |
| Sonnet 5 | $0.00007 | $0.00296 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
compatibility-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 today.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compatibility Testing
<default_to_action> When validating cross-browser/platform compatibility:
- DEFINE browser matrix (cover 95%+ of users)
- TEST responsive breakpoints (mobile, tablet, desktop)
- RUN in parallel across browsers/devices
- USE cloud services for device coverage (BrowserStack, Sauce Labs)
- COMPARE visual screenshots across platforms
Quick Compatibility Checklist:
- Chrome, Firefox, Safari, Edge (latest + N-1)
- Mobile Safari (iOS), Mobile Chrome (Android)
- Screen sizes: 320px, 768px, 1920px
- Test on actual target devices for critical flows
Critical Success Factors:
- Users access from 100+ browser/device combinations
- Test where users are, not where you develop
- Cloud testing reduces 10 hours to 15 minutes </default_to_action>
Quick Reference Card
When to Use
- Before release
- After CSS/layout changes
- Launching in new markets
- Responsive design validation
Browser Matrix
| Browser | Versions | Priority |
|---|---|---|
| Chrome | Latest, N-1 | High |
| Firefox | Latest, N-1 | High |
| Safari | Latest, N-1 | High |
| Edge | Latest | Medium |
| Mobile Safari | iOS latest | High |
| Mobile Chrome | Android latest | High |
Screen Breakpoints
| Category | Width Range |
|---|---|
| Mobile | 320px - 480px |
| Tablet | 481px - 768px |
| Desktop | 769px - 1920px+ |
Responsive Design Testing
import { test, expect } from '@playwright/test';
const devices = [
{ name: 'iPhone 12', width: 390, height: 844 },
{ name: 'iPad', width: 768, height: 1024 },
{ name: 'Desktop', width: 1920, height: 1080 }
];
for (const device of devices) {
test(`layout on ${device.name}`, async ({ page }) => {
await page.setViewportSize({
width: device.width,
height: device.height
});
await page.goto('https://example.com');
const nav = await page.locator('nav');
if (device.width < 768) {
// Mobile: hamburger menu
expect(await nav.locator('.hamburger')).toBeVisible();
} else {
// Desktop: full menu
expect(await nav.locator('.menu-items')).toBeVisible();
}
});
}
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.
- today First seen · 210 lines · 36 tokens per session scan A 68ff9da26904
compatibility-testing is a skill published in the GitHub repository summarybotng/summarybot-ng (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 1,482 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
BrowserStack Cloud Testing
Cloud-based cross-browser and cross-device testing with BrowserStack including Automate, App Automate, Percy visual testing, Observability, and integration with Playwright, Selenium, and CI/CD pipelines.
Cross-Browser Compatibility Testing
Automated cross-browser testing across Chrome, Firefox, Safari, and Edge with visual comparison, feature detection, and polyfill verification.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
playwright-trace
Inspect Playwright trace files from the command line — list actions, view requests, console, errors, snapshots and screenshots.
playwright-triage
Triage a Playwright bug report by reproducing it from the information in the issue. Use when asked to triage, reproduce, or verify a GitHub issue (a new bug report, or an existing report with a new comment).