Moltworker runs OpenClaw, a personal AI assistant, inside a Cloudflare Sandbox managed through Cloudflare Workers. It is intended for people who want to deploy that assistant using Cloudflare's infrastructure and services. The catalogue entries provide instructions and a skill for operating this deployment.
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 cloudflare/moltworker --skill cloudflare-browsergit clone --depth 1 https://github.com/cloudflare/moltworkerWrote 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/cloudflare/moltworker/cloudflare-browser)<a href="https://agentmods.dev/skills/cloudflare/moltworker/cloudflare-browser"><img src="https://agentmods.dev/badge/skills/cloudflare/moltworker/cloudflare-browser/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/cloudflare/moltworker/cloudflare-browser"><img src="https://agentmods.dev/badge/skills/cloudflare/moltworker/cloudflare-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00058 | $0.00731 |
| Opus 5.5 | $0.00023 | $0.00292 |
| Sonnet 5.5 | $0.00012 | $0.00146 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
cloudflare-browser 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cloudflare-browser — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloudflare Browser Rendering
Control headless browsers via Cloudflare's Browser Rendering service using CDP (Chrome DevTools Protocol) over WebSocket.
Prerequisites
CDP_SECRETenvironment variable set- Browser profile configured in openclaw.json with
cdpUrlpointing to the worker endpoint:"browser": { "profiles": { "cloudflare": { "cdpUrl": "https://your-worker.workers.dev/cdp?secret=..." } } }
Quick Start
Screenshot
node /path/to/skills/cloudflare-browser/scripts/screenshot.js https://example.com output.png
Multi-page Video
node /path/to/skills/cloudflare-browser/scripts/video.js "https://site1.com,https://site2.com" output.mp4
CDP Connection Pattern
The worker creates a page target automatically on WebSocket connect. Listen for Target.targetCreated event to get the targetId:
const WebSocket = require('ws');
const CDP_SECRET = process.env.CDP_SECRET;
const WS_URL = `wss://your-worker.workers.dev/cdp?secret=${encodeURIComponent(CDP_SECRET)}`;
const ws = new WebSocket(WS_URL);
let targetId = null;
ws.on('message', (data) => {
const msg = JSON.parse(data.toString());
if (msg.method === 'Target.targetCreated' && msg.params?.targetInfo?.type === 'page') {
targetId = msg.params.targetInfo.targetId;
}
});
Key CDP Commands
| Command | Purpose |
|---|---|
| Page.navigate | Navigate to URL |
| Page.captureScreenshot | Capture PNG/JPEG |
| Runtime.evaluate | Execute JavaScript |
| Emulation.setDeviceMetricsOverride | Set viewport size |
Common Patterns
Navigate and Screenshot
await send('Page.navigate', { url: 'https://example.com' });
await new Promise(r => setTimeout(r, 3000)); // Wait for render
const { data } = await send('Page.captureScreenshot', { format: 'png' });
fs.writeFileSync('out.png', Buffer.from(data, 'base64'));
Scroll Page
await send('Runtime.evaluate', { expression: 'window.scrollBy(0, 300)' });
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.
- 1mo ago First seen · 100 lines · 58 tokens per session scan A 06f8f6741095
cloudflare-browser is a skill published in the GitHub repository cloudflare/moltworker (9,949 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 58 tokens to every session and 731 once invoked, about $0.0002 per session on Opus 5.5. 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
website-to-video
Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→…
browser-adapter-author
Author, replay, and repair reusable Generic Web BrowserPage adapters as ordinary project Skills. Use when a task says "teach Herdr this website", asks for a browser/site adapter, or needs a saved site workflow replayed or repaired after page drift.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
openclaw-web-scraper
Stealth web scraping MCP server with 5 tools for structured data extraction. Use when: (1) 'scrape this URL' or 'extract data from this site', (2) 'get all prices from this page' or 'extract structured data', (3) 'take a screenshot of this page', (4) 'click this button and get the result' or 'interact with a page'…
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.