core-agent-browser

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass, no license.

Audit 0.4.1 · source sha f4ff8c82542d · 22 Oct 2026Report an issue or request a re-scan

• Publisheractionbook GitHub organizationOwner of the repository this skill is read from
• Source folderactionbook/rust-skills/skills/core-agent-browserThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdictf4ff8c82542dA new audit runs when the source changes
• Repository statusNot archivedLast push 59 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: 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.

---
name: core-agent-browser
description: "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."
user-invocable: false
disable-model-invocation: true
---

# Browser Automation with agent-browser

## Priority Note

For fetching Rust/crate information, use this priority order:
1. **rust-learner skill** - Orchestrates actionbook + browser-fetcher
2. **actionbook MCP** - Pre-computed selectors for known sites
3. **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 page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser
```

## Core workflow

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

## Commands

### Navigation
```bash
agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser
```

### Snapshot (page analysis)
```bash
agent-browser snapshot        # Full accessibility tree
agent-browser snapshot -i     # Interactive elements only (recommended)
agent-browser snapshot -c     # Compact output
agent-browser snapshot -d 3   # Limit depth to 3
```

### Interactions (use @refs from snapshot)
```bash
agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view
```

### Get information
```bash
agent-browser get text @e1        # Get element text
agent-browser get value @e1       # Get input value
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
```

### Screenshots
```bash
agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
```

### Wait
```bash
agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text
agent-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" click
agent-browser find label "Email" fill "[email protected]"
```

## Example: Form submission

```bash
agent-browser open https://example.com/form
agent-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 @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result
```

Excerpt, first 3,817 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/actionbook/rust-skills
git -C rust-skills checkout f4ff8c82542d

Works in

1. 2026-10-22
   ✓SAFE B 89 / 100

   first audit · source f4ff8c82542d

Questions about core-agent-browser

• github.com/actionbook/rust-skills/tree/main/skills/core-agent-br — the audited source at commit f4ff8c82542d and every finding aboveObserved · 22 Oct 2026

Spotted something wrong? Report a correction · Methodology