Agent Browser
Drive the agent-browser CLI to open local or remote pages, click, fill forms, screenshot, and sanity-check dev servers after npm run dev.
Install
npx skills add https://github.com/vercel-labs/vercel-plugin --skill agent-browserWhat is this skill?
- Browser automation CLI tuned for AI agents: navigate, forms, clicks, screenshots, and data extraction
- Metadata pathPatterns cover playwright.config, e2e, cypress, and agent-browser.json
- Bash patterns hook next dev, vite, vercel dev, and localhost URLs for automatic visual verification
- chainTo agent-browser-verify when a dev server URL is detected for structured gut-check messaging
- Retrieval aliases include puppeteer, playwright, web scraping, and headless browser tasks
Adoption & trust: 404k installs on skills.sh; 187 GitHub stars; 2/3 security scanners passed (skills.sh audits).
Recommended Skills
Agent Browservercel-labs/open-agents
Tddmattpocock/skills
Use My Browserxixu-me/skills
Test Driven Developmentobra/superpowers
Verification Before Completionobra/superpowers
Webapp Testinganthropics/skills
Journey fit
Primary fit
Visual and interactive verification belongs in Ship when you are proving the app works beyond unit tests and before you call a release good. Testing is the canonical shelf because the skill targets e2e-style browser automation, Playwright/Cypress path patterns, and post-dev-server gut checks.
Common Questions / FAQ
Is Agent Browser safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Agent Browser
# Browser Automation with agent-browser The CLI uses Chrome/Chromium via CDP directly. Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Run `agent-browser upgrade` to update to the latest version. ## Core Workflow Every browser automation follows this pattern: 1. **Navigate**: `agent-browser open <url>` 2. **Snapshot**: `agent-browser snapshot -i` (get element refs like `@e1`, `@e2`) 3. **Interact**: Use refs to click, fill, select 4. **Re-snapshot**: After navigation or DOM changes, get fresh refs ```bash agent-browser open https://example.com/form agent-browser snapshot -i # Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit" agent-browser fill @e1 "user@example.com" agent-browser fill @e2 "password123" agent-browser click @e3 agent-browser wait --load networkidle agent-browser snapshot -i # Check result ``` ## Command Chaining Commands can be chained with `&&` in a single shell invocation. The browser persists between commands via a background daemon, so chaining is safe and more efficient than separate calls. ```bash # Chain open + wait + snapshot in one call agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i # Chain multiple interactions agent-browser fill @e1 "user@example.com" && agent-browser fill @e2 "password123" && agent-browser click @e3 # Navigate and capture agent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser screenshot page.png ``` **When to chain:** Use `&&` when you don't need to read the output of an intermediate command before proceeding (e.g., open + wait + screenshot). Run commands separately when you need to parse the output first (e.g., snapshot to discover refs, then interact using those refs). ## Handling Authentication When automating a site that requires login, choose the approach that fits: **Option 1: Import auth from the user's browser (fastest for one-off tasks)** ```bash # Connect to the user's running Chrome (they're already logged in) agent-browser --auto-connect state save .