Dev Browser Automation

What it does

When your agent uses it

• Navigating a website, clicking through it and filling out forms
• Taking screenshots of a page to check how it looks
• Extracting data from a site that needs several steps to reach
• Testing a local web app by driving it in a browser
• Automating something behind a login using your own Chrome session

Example prompts

• “Open my staging site, fill in the signup form with a test user and screenshot the confirmation page.”
• “Go to the pricing page and pull the plan names and prices into a table.”
• “Using my logged-in Chrome, open the analytics dashboard and screenshot the weekly chart.”

Requirements

• Node.js with npx and tsx
• Chromium, or Chrome with the dev-browser extension for extension mode

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

1. 1Scripts call client.page("name") just like the normal mode to create new pages / connect to existing ones.
2. 2Automation runs on the user's actual browser session

What it can do on your machine

Read from SKILL.md and the folder at commit a7367d0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (TypeScript and Shell, from the files we listed), which the agent can run.

  Shell commands in SKILL.md call:

  • npm
  • npx

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Dev Browser Automation loads about 1.7k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 94 tokens; SKILL.md has 516 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~94

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from MemTensor/MemOS at commit a7367d0, republished under its Apache-2.0 licence (© MemTensor). 516 words, ~1,722 tokens.

name

dev-browser

description

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

./skills/dev-browser/server.sh &

cd skills/dev-browser && npm i && npm run start-extension &

cd skills/dev-browser && npx tsx <<'EOF'
import { connect, waitForPageLoad } from "@/client.js";

const client = await connect();
// Create page with custom viewport size (optional)
const page = await client.page("example", { viewport: { width: 1920, height: 1080 } });

await page.goto("https://example.com");
await waitForPageLoad(page);

console.log({ title: await page.title(), url: page.url() });
await client.disconnect();
EOF

// ✅ Correct: plain JavaScript
const text = await page.evaluate(() => {
  return document.body.innerText;
});

// ❌ Wrong: TypeScript syntax will fail at runtime
const text = await page.evaluate(() => {
  const el: HTMLElement = document.body; // Type annotation breaks in browser!
  return el.innerText;
});

const client = await connect();

// Get or create named page (viewport only applies to new pages)
const page = await client.page("name");
const pageWithSize = await client.page("name", { viewport: { width: 1920, height: 1080 } });

const pages = await client.list(); // List all page names
await client.close("name"); // Close a page
await client.disconnect(); // Disconnect (pages persist)

// ARIA Snapshot methods
const snapshot = await client.getAISnapshot("name"); // Get accessibility tree
const element = await client.selectSnapshotRef("name", "e5"); // Get element by ref

import { waitForPageLoad } from "@/client.js";

await waitForPageLoad(page); // After navigation
await page.waitForSelector(".results"); // For specific elements
await page.waitForURL("**/success"); // For specific URL

await page.screenshot({ path: "tmp/screenshot.png" });
await page.screenshot({ path: "tmp/full.png", fullPage: true });

- banner:
  - link "Hacker News" [ref=e1]
  - navigation:
    - link "new" [ref=e2]
- main:
  - list:
    - listitem:
      - link "Article Title" [ref=e8]
      - link "328 comments" [ref=e9]
- contentinfo:
  - textbox [ref=e10]
    - /placeholder: "Search"

const snapshot = await client.getAISnapshot("hackernews");
console.log(snapshot); // Find the ref you need

const element = await client.selectSnapshotRef("hackernews", "e2");
await element.click();

cd skills/dev-browser && npx tsx <<'EOF'
import { connect } from "@/client.js";

const client = await connect();
const page = await client.page("hackernews");

await page.screenshot({ path: "tmp/debug.png" });
console.log({
  url: page.url(),
  title: await page.title(),
  bodyText: await page.textContent("body").then((t) => t?.slice(0, 200)),
});

await client.disconnect();
EOF

© MemTensor, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 16 other files (scripts, references) in apps/openwork-memos-integration/apps/desktop/skills/dev-browser of MemTensor/MemOS.

• SKILL.md
• .gitignore
• package.json
• references/scraping.md
• scripts/start-relay.ts
• scripts/start-server.ts
• server.sh
• src/client.ts
• src/index.ts
• src/relay.ts
• src/snapshot/__tests__/snapshot.test.ts
• src/snapshot/browser-script.ts
• src/snapshot/index.ts
• src/snapshot/inject.ts
• src/types.ts
• tsconfig.json
• … and 1 more

Open the folder on GitHubat commit a7367d0

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in MemTensor/MemOS, which our catalogue first saw on October 7, 2026.

• code-yeongyu/oh-my-openagentpackages/skills-loader-core/src/features/builtin-skills/dev-browser
• ynulihao/AgentSkillOSdata/skill_seeds/dev-browser
• cashew-labs/librettopackages/browser-tools/benchmarks/skills/dev-browser