Core Agent Browser

by actionbook5c40d3ad7851No license1.5K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 6 weeks ago

Internal support skill for agent-browser CLI workflows used by rust-learner, docs-researcher, and crate-researcher. Use only when browser automation is explicitly required.

Instructions onlyAI & Agents

AI-generated overview

Internal support skill documenting agent-browser CLI commands for browser automation workflows.

What it does: This skill is an internal reference for driving the agent-browser command-line tool. It lists commands for navigation, accessibility-tree snapshots, element interaction by reference, form filling, information retrieval, screenshots, waits, and semantic locators, plus a worked form-submission example. It also sets a priority order that places direct browser automation last, after other fetching approaches.
When to use it: Use it only when browser automation is explicitly required, such as when no pre-computed selectors exist for a target site, when interactive browser testing is needed, or when screenshots or form filling are required. It is not user-invocable and is not meant to be triggered automatically.
Requirements: Requires the agent-browser CLI to be installed and available, plus network access to reach target pages. It ships no scripts; it is instructions only.

Browser Automation with agent-browser

Priority Note

For fetching Rust/crate information, use this priority order:

rust-learner skill - Orchestrates actionbook + browser-fetcher
actionbook MCP - Pre-computed selectors for known sites
agent-browser CLI - Direct browser automation (last resort)

Use agent-browser directly only when:

actionbook has no pre-computed selectors for the target site
You need interactive browser testing/automation
You need screenshots or form filling

Quick start

bash

agent-browser open <url>        # Navigate to pageagent-browser snapshot -i       # Get interactive elements with refsagent-browser click @e1         # Click element by refagent-browser fill @e2 "text"   # Fill input by refagent-browser close             # Close browser

agent-browser open <url>        # Navigate to pageagent-browser snapshot -i       # Get interactive elements with refsagent-browser click @e1         # Click element by refagent-browser fill @e2 "text"   # Fill input by refagent-browser close             # Close browser

Core workflow

Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes

Commands

Navigation

bash

agent-browser open <url>      # Navigate to URLagent-browser back            # Go backagent-browser forward         # Go forwardagent-browser reload          # Reload pageagent-browser close           # Close browser

agent-browser open <url>      # Navigate to URLagent-browser back            # Go backagent-browser forward         # Go forwardagent-browser reload          # Reload pageagent-browser close           # Close browser

Snapshot (page analysis)

bash

agent-browser snapshot        # Full accessibility treeagent-browser snapshot -i     # Interactive elements only (recommended)agent-browser snapshot -c     # Compact outputagent-browser snapshot -d 3   # Limit depth to 3

agent-browser snapshot        # Full accessibility treeagent-browser snapshot -i     # Interactive elements only (recommended)agent-browser snapshot -c     # Compact outputagent-browser snapshot -d 3   # Limit depth to 3

Interactions (use @refs from snapshot)

bash

agent-browser click @e1           # Clickagent-browser dblclick @e1        # Double-clickagent-browser fill @e2 "text"     # Clear and typeagent-browser type @e2 "text"     # Type without clearingagent-browser press Enter         # Press keyagent-browser press Control+a     # Key combinationagent-browser hover @e1           # Hoveragent-browser check @e1           # Check checkboxagent-browser uncheck @e1         # Uncheck checkboxagent-browser select @e1 "value"  # Select dropdownagent-browser scroll down 500     # Scroll pageagent-browser scrollintoview @e1  # Scroll element into view

agent-browser click @e1           # Clickagent-browser dblclick @e1        # Double-clickagent-browser fill @e2 "text"     # Clear and typeagent-browser type @e2 "text"     # Type without clearingagent-browser press Enter         # Press keyagent-browser press Control+a     # Key combinationagent-browser hover @e1           # Hoveragent-browser check @e1           # Check checkboxagent-browser uncheck @e1         # Uncheck checkboxagent-browser select @e1 "value"  # Select dropdownagent-browser scroll down 500     # Scroll pageagent-browser scrollintoview @e1  # Scroll element into view

Get information

bash

agent-browser get text @e1        # Get element textagent-browser get value @e1       # Get input valueagent-browser get title           # Get page titleagent-browser get url             # Get current URL

agent-browser get text @e1        # Get element textagent-browser get value @e1       # Get input valueagent-browser get title           # Get page titleagent-browser get url             # Get current URL

Screenshots

bash

agent-browser screenshot          # Screenshot to stdoutagent-browser screenshot path.png # Save to fileagent-browser screenshot --full   # Full page

agent-browser screenshot          # Screenshot to stdoutagent-browser screenshot path.png # Save to fileagent-browser screenshot --full   # Full page

Wait

bash

agent-browser wait @e1                     # Wait for elementagent-browser wait 2000                    # Wait millisecondsagent-browser wait --text "Success"        # Wait for textagent-browser wait --load networkidle      # Wait for network idle

agent-browser wait @e1                     # Wait for elementagent-browser wait 2000                    # Wait millisecondsagent-browser wait --text "Success"        # Wait for textagent-browser wait --load networkidle      # Wait for network idle

Semantic locators (alternative to refs)

bash

agent-browser find role button click --name "Submit"agent-browser find text "Sign In" clickagent-browser find label "Email" fill "[email protected]"

agent-browser find role button click --name "Submit"agent-browser find text "Sign In" clickagent-browser find label "Email" fill "[email protected]"

Example: Form submission

bash

agent-browser open https://example.com/formagent-browser snapshot -i# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
agent-browser fill @e1 "[email protected]"agent-browser fill @e2 "password123"agent-browser click @e3agent-browser wait --load networkidleagent-browser snapshot -i  # Check result

agent-browser open https://example.com/formagent-browser snapshot -i# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
agent-browser fill @e1 "[email protected]"agent-browser fill @e2 "password123"agent-browser click @e3agent-browser wait --load networkidleagent-browser snapshot -i  # Check result

Source and attribution

Source:actionbook/rust-skillsinskills/core-agent-browserat commit5c40d3a

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Core Agent Browser

Browser Automation with agent-browser

Priority Note

Quick start

Core workflow

Commands

Navigation

Snapshot (page analysis)

Interactions (use @refs from snapshot)

Get information

Screenshots

Wait

Semantic locators (alternative to refs)

Example: Form submission

Source and attribution

More from actionbook/rust-skills

Rust Trait Explorer

Rust Symbol Analyzer

Rust Skill Creator

Rust Router

Rust Refactor Helper

Rust Daily

More in AI & Agents

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills

Plugin Creator