Agent skill · Testing & QA

agent-browser

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill agent-browser-codewithbehnam-cc-docs --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 25 KB
Bundled scripts: none
Path: skills/agent/agent-browser-codewithbehnam-cc-docs/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Automates browser interactions using the agent-browser CLI. It guides the agent to navigate to URLs, take element references, perform interactions with those references (click, fill, select, etc.), and refresh references after DOM changes. It supports chaining commands in a single shell invocation and persists the browser session across commands via a background daemon.

How it works

  • Navigate: use commands like agent-browser open <url> to load a page.
  • Snapshot: run agent-browser snapshot -i to obtain element refs (e.g., @e1, @e2).
  • Interact: perform actions using the refs, such as agent-browser click @e1, agent-browser fill @e2 "text", or agent-browser select @e1 "option".
  • Re-snapshot: after navigation or DOM updates, run agent-browser snapshot -i again to refresh refs.
  • Command chaining: combine steps with && in one shell invocation; the browser persists between commands via a background daemon.

When to use it

Triggers include: "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation". Use when you need automated web interactions and data extraction via Bash-style commands.

What it can touch

Commands reference and manipulate web page elements via refs produced by agent-browser snapshot -i. Supported actions include open, close, click, fill, type, select, check, press, screenshot, and various wait options. Screenshots and other outputs can be saved as files per provided flags (e.g., agent-browser screenshot).

Caveats

  • Requires installation steps (e.g., npm i -g agent-browser, agent-browser install).
  • State and authentication can expose tokens in plaintext if not careful; encryption options and state handling are described in the workflow.
  • Some features rely on CDP/Chrome automation and may depend on Chrome/Chromium availability.
From the SKILL.md

# 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. ## Setup Check ```bash # Check installation command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED - run: npm install -g agent-browser && agent-browser install" ``` ### Install if needed ```bash npm install -g agent-browser agent-browser install # Downloads Chromium ``` ## 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 ``` ## Co

What's inside
Steps it walks through
  1. Setup Check
  2. Install if needed
  3. Core Workflow
  4. Command Chaining
  5. Handling Authentication
  6. Essential Commands
  7. Common Patterns
  8. Form Submission
  9. Authentication with Auth Vault (Recommended)
  10. Authentication with State Persistence
  11. Session Persistence
  12. Data Extraction
  13. Parallel Sessions
  14. Connect to Existing Chrome
Ships with 1 file
  • metadata.json
Commands it runs
Check installation
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED - run: npm install -g agent-browser && agent-browser install"
npm install -g agent-browser
agent-browser install  # Downloads Chromium
agent-browser open https://example.com/form
agent-browser snapshot -i
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the agent-browser skill do?

Browser automation using Vercel's agent-browser CLI. Use when you need to interact with web pages, fill forms, take screenshots, or scrape data. Alternative to Playwright MCP - uses Bash commands with ref-based element selection. Triggers on "browse website", "fill form", "click button", "take screenshot", "scrape page", "web automation".

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill agent-browser-codewithbehnam-cc-docs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.