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/robinoppenstam/claude-ralph/dev-browsernpx skills add RobinOppenstam/claude-ralph --skill dev-browsergit clone --depth 1 https://github.com/RobinOppenstam/claude-ralphWrote 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/robinoppenstam/claude-ralph/dev-browser)<a href="https://agentmods.dev/skills/robinoppenstam/claude-ralph/dev-browser"><img src="https://agentmods.dev/badge/skills/robinoppenstam/claude-ralph/dev-browser.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 5.1 | $0.00000 | $0.01977 |
| Opus 5 | $0.00000 | $0.00988 |
| Sonnet 5 | $0.00000 | $0.00395 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade A, and why
dev-browser scanned grade A with 1 finding 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 6d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process'; How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Browser Skill
Browser automation skill for verifying UI stories. Essential for Ralph's autonomous workflow when implementing frontend features.
Based on SawyerHood/dev-browser - adapted for Claude Code.
Purpose
When Ralph implements UI stories, this skill enables:
- Visual verification that changes work correctly
- Form testing and interaction
- Screenshot capture for documentation
- Detection of UI bugs before committing
Prerequisites
# Install Playwright
npm install -D playwright
npx playwright install chromium
# Or use Bun (recommended)
bun add -D playwright
bunx playwright install chromium
Usage
Quick Verification
For simple UI verification during Ralph iterations:
// verify-ui.ts
import { chromium } from 'playwright';
const BASE_URL = process.env.BASE_URL || 'http://localhost:3000';
async function verify() {
const browser = await chromium.launch({ headless: false, slowMo: 100 });
const page = await browser.newPage();
try {
await page.goto(BASE_URL);
// Your verification logic here
console.log('✅ Page loaded successfully');
console.log('Title:', await page.title());
// Take screenshot
await page.screenshot({ path: 'tmp/verification.png' });
} catch (error) {
console.error('❌ Verification failed:', error);
await page.screenshot({ path: 'tmp/error.png' });
throw error;
} finally {
await browser.close();
}
}
verify();
Run with:
npx tsx verify-ui.ts
# or
bun run verify-ui.ts
Common Patterns
1. Detect Dev Server
Before running tests, detect what's running:
import { execSync } from 'child_process';
function detectDevServers(): { port: number; url: string }[] {
const ports = [3000, 3001, 5173, 8080, 4000];
const servers: { port: number; url: string }[] = [];
for (const port of ports) {
try {
execSync(`lsof -i:${port} -P -n | grep LISTEN`, { stdio: 'pipe' });
servers.push({ port, url: `http://localhost:${port}` });
} catch {
// Port not in use
}
}
return servers;
}
const servers = detectDevServers();
console.log('Found servers:', servers);
What ships with it
1 file 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.
- 6d ago First seen · 317 lines · 0 tokens per session scan A b51878e10fb7
dev-browser is a skill published in the GitHub repository RobinOppenstam/claude-ralph (11 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,977 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
browse
Fast headless browser for QA testing and site dogfooding. (gstack).
playwright-cli
官方Microsoft Playwright CLI网页自动化工具,支持所有主流浏览器的无头/有头自动化操作,包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。.
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.
browser-qa
自动化视觉测试与 UI 交互验证。部署功能后使用浏览器自动化验证关键页面、核心路径和发布前回归。 当任务需要真实浏览器验证渲染、导航、交互或前端上线风险时使用。.
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
smoke-test
Run smoke tests against a deployed or local app based on your git diff. Each test uses Skyvern browser tools (navigate, act, validate, screenshot) with Chrome DevTools MCP as fallback. Posts screenshot evidence as PR comments.