{"id":"19f45910-fd1d-440d-899b-7e0454d16500","entityType":"agent","slug":"clawhub-thesethrose-agent-browser","name":"Agent Browser","canonicalUrl":"https://www.xpersona.co/agent/clawhub-thesethrose-agent-browser","canonicalPath":"/agent/clawhub-thesethrose-agent-browser","generatedAt":"2026-10-09T10:17:12.901Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"description":"A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. Skill: Agent Browser Owner: TheSethRose Summary: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. Tags: automation:0.1.0, browser:0.1.0, headless:0.1.0, latest:0.2.0, web:0.1.0 Version history: v0.2.0 | 2026-01-20T04:12:22.488Z | auto **Big update: Expanded documentation and new contribution guidelines.","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 57K downloads reported by the source. Last updated 4/15/2026.","installCommand":"clawhub skill install kn72ce44tqw8bnnnewrn1s5x3s7yz7sq:agent-browser","sourceUrl":"https://clawhub.ai/TheSethRose/agent-browser","homepage":"https://clawhub.ai/TheSethRose/agent-browser","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/TheSethRose/agent-browser","kind":"source"}],"safetyScore":84,"overallRank":62,"popularityScore":89,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured comma"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No protocol or capability metadata is available."},"protocols":[],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":0,"capabilityMatrix":{"rows":[],"flattenedTokens":""}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"stars":null,"forks":null,"downloads":56972,"packageName":null,"latestVersion":"0.2.0","tractionLabel":"57K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-02-28T16:47:00.983Z","emptyReason":null},"lastUpdatedAt":"2026-04-15T00:45:39.800Z","lastCrawledAt":"2026-02-28T16:47:00.983Z","lastIndexedAt":null,"nextCrawlAt":"2026-03-01T16:47:00.983Z","lastVerifiedAt":null,"highlights":[{"version":"0.2.0","createdAt":"2026-01-20T04:12:22.488Z","changelog":"**Big update: Expanded documentation and new contribution guidelines.** - Added a CONTRIBUTING.md file with guidelines for contributors. - Significantly revised and expanded SKILL.md: - Clearer structure, concise “Quick start,” and streamlined “Core workflow.” - Added or reorganized sections: video recording, mouse control, semantic locators, browser settings, cookies/storage, network, tabs, frames, dialogs, JS, and session state management. - More comprehensive examples and improved command explanations. - Introduced allowed-tools field in SKILL.md for clearer operational context.","fileCount":3,"zipByteSize":4637},{"version":"0.1.0","createdAt":"2026-01-11T22:27:46.579Z","changelog":"Initial release: Headless browser automation CLI for AI agents with navigation, interaction, extraction, and screenshot capabilities.","fileCount":2,"zipByteSize":1970}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install kn72ce44tqw8bnnnewrn1s5x3s7yz7sq:agent-browser","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":[]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-09T10:17:12.901Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-thesethrose-agent-browser/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":null},"readme":"Skill: Agent Browser\n\nOwner: TheSethRose\n\nSummary: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\n\nTags: automation:0.1.0, browser:0.1.0, headless:0.1.0, latest:0.2.0, web:0.1.0\n\nVersion history:\n\nv0.2.0 | 2026-01-20T04:12:22.488Z | auto\n\n**Big update: Expanded documentation and new contribution guidelines.**\n\n- Added a CONTRIBUTING.md file with guidelines for contributors.\n- Significantly revised and expanded SKILL.md:\n  - Clearer structure, concise “Quick start,” and streamlined “Core workflow.”\n  - Added or reorganized sections: video recording, mouse control, semantic locators, browser settings, cookies/storage, network, tabs, frames, dialogs, JS, and session state management.\n  - More comprehensive examples and improved command explanations.\n- Introduced allowed-tools field in SKILL.md for clearer operational context.\n\nv0.1.0 | 2026-01-11T22:27:46.579Z | user\n\nInitial release: Headless browser automation CLI for AI agents with navigation, interaction, extraction, and screenshot capabilities.\n\nArchive index:\n\nArchive v0.2.0: 3 files, 4637 bytes\n\nFiles: CONTRIBUTING.md (1626b), SKILL.md (10224b), _meta.json (132b)\n\nFile v0.2.0:SKILL.md\n\n---\nname: Agent Browser\ndescription: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\nread_when:\n  - Automating web interactions\n  - Extracting structured data from pages\n  - Filling forms programmatically\n  - Testing web UIs\nmetadata: {\"clawdbot\":{\"emoji\":\"🌐\",\"requires\":{\"bins\":[\"node\",\"npm\"]}}}\nallowed-tools: Bash(agent-browser:*)\n---\n\n# Browser Automation with agent-browser\n\n## Installation\n\n### npm recommended\n\n```bash\nnpm install -g agent-browser\nagent-browser install\nagent-browser install --with-deps\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/vercel-labs/agent-browser\ncd agent-browser\npnpm install\npnpm build\nagent-browser install\n```\n\n## Quick start\n\n```bash\nagent-browser open <url>        # Navigate to page\nagent-browser snapshot -i       # Get interactive elements with refs\nagent-browser click @e1         # Click element by ref\nagent-browser fill @e2 \"text\"   # Fill input by ref\nagent-browser close             # Close browser\n```\n\n## Core workflow\n\n1. Navigate: `agent-browser open <url>`\n2. Snapshot: `agent-browser snapshot -i` (returns elements with refs like `@e1`, `@e2`)\n3. Interact using refs from the snapshot\n4. Re-snapshot after navigation or significant DOM changes\n\n## Commands\n\n### Navigation\n\n```bash\nagent-browser open <url>      # Navigate to URL\nagent-browser back            # Go back\nagent-browser forward         # Go forward\nagent-browser reload          # Reload page\nagent-browser close           # Close browser\n```\n\n### Snapshot (page analysis)\n\n```bash\nagent-browser snapshot            # Full accessibility tree\nagent-browser snapshot -i         # Interactive elements only (recommended)\nagent-browser snapshot -c         # Compact output\nagent-browser snapshot -d 3       # Limit depth to 3\nagent-browser snapshot -s \"#main\" # Scope to CSS selector\n```\n\n### Interactions (use @refs from snapshot)\n\n```bash\nagent-browser click @e1           # Click\nagent-browser dblclick @e1        # Double-click\nagent-browser focus @e1           # Focus element\nagent-browser fill @e2 \"text\"     # Clear and type\nagent-browser type @e2 \"text\"     # Type without clearing\nagent-browser press Enter         # Press key\nagent-browser press Control+a     # Key combination\nagent-browser keydown Shift       # Hold key down\nagent-browser keyup Shift         # Release key\nagent-browser hover @e1           # Hover\nagent-browser check @e1           # Check checkbox\nagent-browser uncheck @e1         # Uncheck checkbox\nagent-browser select @e1 \"value\"  # Select dropdown\nagent-browser scroll down 500     # Scroll page\nagent-browser scrollintoview @e1  # Scroll element into view\nagent-browser drag @e1 @e2        # Drag and drop\nagent-browser upload @e1 file.pdf # Upload files\n```\n\n### Get information\n\n```bash\nagent-browser get text @e1        # Get element text\nagent-browser get html @e1        # Get innerHTML\nagent-browser get value @e1       # Get input value\nagent-browser get attr @e1 href   # Get attribute\nagent-browser get title           # Get page title\nagent-browser get url             # Get current URL\nagent-browser get count \".item\"   # Count matching elements\nagent-browser get box @e1         # Get bounding box\n```\n\n### Check state\n\n```bash\nagent-browser is visible @e1      # Check if visible\nagent-browser is enabled @e1      # Check if enabled\nagent-browser is checked @e1      # Check if checked\n```\n\n### Screenshots & PDF\n\n```bash\nagent-browser screenshot          # Screenshot to stdout\nagent-browser screenshot path.png # Save to file\nagent-browser screenshot --full   # Full page\nagent-browser pdf output.pdf      # Save as PDF\n```\n\n### Video recording\n\n```bash\nagent-browser record start ./demo.webm    # Start recording (uses current URL + state)\nagent-browser click @e1                   # Perform actions\nagent-browser record stop                 # Stop and save video\nagent-browser record restart ./take2.webm # Stop current + start new recording\n```\n\nRecording creates a fresh context but preserves cookies/storage from your session. If no URL is provided, it automatically returns to your current page. For smooth demos, explore first, then start recording.\n\n### Wait\n\n```bash\nagent-browser wait @e1                     # Wait for element\nagent-browser wait 2000                    # Wait milliseconds\nagent-browser wait --text \"Success\"        # Wait for text\nagent-browser wait --url \"/dashboard\"    # Wait for URL pattern\nagent-browser wait --load networkidle      # Wait for network idle\nagent-browser wait --fn \"window.ready\"     # Wait for JS condition\n```\n\n### Mouse control\n\n```bash\nagent-browser mouse move 100 200      # Move mouse\nagent-browser mouse down left         # Press button\nagent-browser mouse up left           # Release button\nagent-browser mouse wheel 100         # Scroll wheel\n```\n\n### Semantic locators (alternative to refs)\n\n```bash\nagent-browser find role button click --name \"Submit\"\nagent-browser find text \"Sign In\" click\nagent-browser find label \"Email\" fill \"user@test.com\"\nagent-browser find first \".item\" click\nagent-browser find nth 2 \"a\" text\n```\n\n### Browser settings\n\n```bash\nagent-browser set viewport 1920 1080      # Set viewport size\nagent-browser set device \"iPhone 14\"      # Emulate device\nagent-browser set geo 37.7749 -122.4194   # Set geolocation\nagent-browser set offline on              # Toggle offline mode\nagent-browser set headers '{\"X-Key\":\"v\"}' # Extra HTTP headers\nagent-browser set credentials user pass   # HTTP basic auth\nagent-browser set media dark              # Emulate color scheme\n```\n\n### Cookies & Storage\n\n```bash\nagent-browser cookies                     # Get all cookies\nagent-browser cookies set name value      # Set cookie\nagent-browser cookies clear               # Clear cookies\nagent-browser storage local               # Get all localStorage\nagent-browser storage local key           # Get specific key\nagent-browser storage local set k v       # Set value\nagent-browser storage local clear         # Clear all\n```\n\n### Network\n\n```bash\nagent-browser network route <url>              # Intercept requests\nagent-browser network route <url> --abort      # Block requests\nagent-browser network route <url> --body '{}'  # Mock response\nagent-browser network unroute [url]            # Remove routes\nagent-browser network requests                 # View tracked requests\nagent-browser network requests --filter api    # Filter requests\n```\n\n### Tabs & Windows\n\n```bash\nagent-browser tab                 # List tabs\nagent-browser tab new [url]       # New tab\nagent-browser tab 2               # Switch to tab\nagent-browser tab close           # Close tab\nagent-browser window new          # New window\n```\n\n### Frames\n\n```bash\nagent-browser frame \"#iframe\"     # Switch to iframe\nagent-browser frame main          # Back to main frame\n```\n\n### Dialogs\n\n```bash\nagent-browser dialog accept [text]  # Accept dialog\nagent-browser dialog dismiss        # Dismiss dialog\n```\n\n### JavaScript\n\n```bash\nagent-browser eval \"document.title\"   # Run JavaScript\n```\n\n### State management\n\n```bash\nagent-browser state save auth.json    # Save session state\nagent-browser state load auth.json    # Load saved state\n```\n\n## Example: Form submission\n\n```bash\nagent-browser open https://example.com/form\nagent-browser snapshot -i\n# Output shows: textbox \"Email\" [ref=e1], textbox \"Password\" [ref=e2], button \"Submit\" [ref=e3]\n\nagent-browser fill @e1 \"user@example.com\"\nagent-browser fill @e2 \"password123\"\nagent-browser click @e3\nagent-browser wait --load networkidle\nagent-browser snapshot -i  # Check result\n```\n\n## Example: Authentication with saved state\n\n```bash\n# Login once\nagent-browser open https://app.example.com/login\nagent-browser snapshot -i\nagent-browser fill @e1 \"username\"\nagent-browser fill @e2 \"password\"\nagent-browser click @e3\nagent-browser wait --url \"/dashboard\"\nagent-browser state save auth.json\n\n# Later sessions: load saved state\nagent-browser state load auth.json\nagent-browser open https://app.example.com/dashboard\n```\n\n## Sessions (parallel browsers)\n\n```bash\nagent-browser --session test1 open site-a.com\nagent-browser --session test2 open site-b.com\nagent-browser session list\n```\n\n## JSON output (for parsing)\n\nAdd `--json` for machine-readable output:\n\n```bash\nagent-browser snapshot -i --json\nagent-browser get text @e1 --json\n```\n\n## Debugging\n\n```bash\nagent-browser open example.com --headed              # Show browser window\nagent-browser console                                # View console messages\nagent-browser console --clear                        # Clear console\nagent-browser errors                                 # View page errors\nagent-browser errors --clear                         # Clear errors\nagent-browser highlight @e1                          # Highlight element\nagent-browser trace start                            # Start recording trace\nagent-browser trace stop trace.zip                   # Stop and save trace\nagent-browser record start ./debug.webm              # Record from current page\nagent-browser record stop                            # Save recording\nagent-browser --cdp 9222 snapshot                    # Connect via CDP\n```\n\n## Troubleshooting\n\n- If the command is not found on Linux ARM64, use the full path in the bin folder.\n- If an element is not found, use snapshot to find the correct ref.\n- If the page is not loaded, add a wait command after navigation.\n- Use --headed to see the browser window for debugging.\n\n## Options\n\n- --session <name> uses an isolated session.\n- --json provides JSON output.\n- --full takes a full page screenshot.\n- --headed shows the browser window.\n- --timeout sets the command timeout in milliseconds.\n- --cdp <port> connects via Chrome DevTools Protocol.\n\n## Notes\n\n- Refs are stable per page load but change on navigation.\n- Always snapshot after navigation to get new refs.\n- Use fill instead of type for input fields to ensure existing text is cleared.\n\n## Reporting Issues\n\n- Skill issues: Open an issue at https://github.com/TheSethRose/Agent-Browser-CLI\n- agent-browser CLI issues: Open an issue at https://github.com/vercel-labs/agent-browser\n\nFile v0.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn72ce44tqw8bnnnewrn1s5x3s7yz7sq\",\n  \"slug\": \"agent-browser\",\n  \"version\": \"0.2.0\",\n  \"publishedAt\": 1768882342488\n}\n\nFile v0.2.0:CONTRIBUTING.md\n\n# Contributing to Agent Browser Skill\n\nThis skill wraps the agent-browser CLI. Determine where the problem lies before reporting issues.\n\n## Issue Reporting Guide\n\n### Open an issue in this repository if\n\n- The skill documentation is unclear or missing\n- Examples in SKILL.md do not work\n- You need help using the CLI with this skill wrapper\n- The skill is missing a command or feature\n\n### Open an issue at the agent-browser repository if\n\n- The CLI crashes or throws errors\n- Commands do not behave as documented\n- You found a bug in the browser automation\n- You need a new feature in the CLI\n\n## Before Opening an Issue\n\n1. Install the latest version\n   ```bash\n   npm install -g agent-browser@latest\n   ```\n\n2. Test the command in your terminal to isolate the issue\n\n## Issue Report Template\n\nUse this template to provide necessary information.\n\n```markdown\n### Description\n[Provide a clear and concise description of the bug]\n\n### Reproduction Steps\n1. [First Step]\n2. [Second Step]\n3. [Observe error]\n\n### Expected Behavior\n[Describe what you expected to happen]\n\n### Environment Details\n- **Skill Version:** [e.g. 1.0.2]\n- **agent-browser Version:** [output of agent-browser --version]\n- **Node.js Version:** [output of node -v]\n- **Operating System:** [e.g. macOS Sonoma, Windows 11, Ubuntu 22.04]\n\n### Additional Context\n- [Full error output or stack trace]\n- [Screenshots]\n- [Website URLs where the failure occurred]\n```\n\n## Adding New Commands to the Skill\n\nUpdate SKILL.md when the upstream CLI adds new commands.\n- Keep the Installation section\n- Add new commands in the correct category\n- Include usage examples\n\nArchive v0.1.0: 2 files, 1970 bytes\n\nFiles: SKILL.md (4617b), _meta.json (132b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: Agent Browser\ndescription: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\nread_when:\n  - Automating web interactions\n  - Extracting structured data from pages\n  - Filling forms programmatically\n  - Testing web UIs\nmetadata: {\"clawdbot\":{\"emoji\":\"🌐\",\"requires\":{\"bins\":[\"node\",\"npm\"]}}}\n---\n\n# Agent Browser\n\nA fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\n\n## Installation\n\n### npm recommended\n\n```bash\nnpm install -g agent-browser\nagent-browser install\nagent-browser install --with-deps\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/vercel-labs/agent-browser\ncd agent-browser\npnpm install\npnpm build\nagent-browser install\n```\n\n## Quick Start\n\n```bash\nagent-browser open example.com\nagent-browser snapshot\nagent-browser click @e2\nagent-browser fill @e3 \"test@example.com\"\nagent-browser get text @e1\nagent-browser screenshot page.png\nagent-browser close\n```\n\n## Core Commands\n\n### Navigation\n\n```bash\nagent-browser open <url>\nagent-browser back\nagent-browser forward\nagent-browser reload\n```\n\n### Interaction\n\n```bash\nagent-browser click <sel>\nagent-browser dblclick <sel>\nagent-browser focus <sel>\nagent-browser type <sel> <text>\nagent-browser fill <sel> <text>\nagent-browser clear <sel>\nagent-browser press <key>\nagent-browser keydown <key>\nagent-browser keyup <key>\nagent-browser hover <sel>\nagent-browser select <sel> <val>\nagent-browser check <sel>\nagent-browser uncheck <sel>\nagent-browser drag <src> <tgt>\nagent-browser upload <sel> <files>\n```\n\n### Extraction and Info\n\n```bash\nagent-browser snapshot\nagent-browser get text <sel>\nagent-browser get html <sel>\nagent-browser get value <sel>\nagent-browser get attr <sel> <attr>\nagent-browser get title\nagent-browser get url\nagent-browser get count <sel>\nagent-browser get box <sel>\nagent-browser screenshot [path]\nagent-browser pdf <path>\n```\n\n### Check State\n\n```bash\nagent-browser is visible <sel>\nagent-browser is enabled <sel>\nagent-browser is checked <sel>\n```\n\n### Find Elements\n\n- agent-browser find role <role> <action> [value]\n- agent-browser find text <text> <action>\n- agent-browser find label <label> <action> [value]\n- agent-browser find placeholder <ph> <action> [value]\n- agent-browser find alt <text> <action>\n- agent-browser find title <text> <action>\n- agent-browser find testid <id> <action> [value]\n\nActions include click, fill, check, hover, and text.\n\n### Wait and Timing\n\n```bash\nagent-browser wait <selector>\nagent-browser wait <ms>\nagent-browser wait --text \"Welcome\"\nagent-browser wait --url \"**/dash\"\nagent-browser wait --load networkidle\n```\n\n### Advanced Control\n\n```bash\nagent-browser scroll <dir> [px]\nagent-browser scrollintoview <sel>\nagent-browser eval <js>\nagent-browser mouse move <x> <y>\nagent-browser cookies\nagent-browser storage local\nagent-browser tab new [url]\nagent-browser frame <sel>\nagent-browser dialog accept [text]\n```\n\n## Sessions\n\nRun multiple isolated browser instances.\n\n```bash\nagent-browser --session agent1 open site-a.com\nagent-browser --session agent2 open site-b.com\n```\n\n## Snapshot Options\n\nThe snapshot command supports filtering to reduce output size.\n\n- agent-browser snapshot -i\n- agent-browser snapshot -c\n- agent-browser snapshot -d 3\n- agent-browser snapshot -s \"#main\"\n\n## Selectors and Refs\n\nRefs provide deterministic element selection from snapshots. Use the @ref syntax.\n\n```bash\nagent-browser snapshot\nagent-browser click @e2\n```\n\n## Agent Mode\n\nUse --json for machine readable output.\n\n```bash\nagent-browser snapshot --json\n```\n\n### Optimal AI Workflow\n\n- Navigate with agent-browser open <url>\n- Observe with agent-browser snapshot -i --json\n- Act with @ref from the snapshot\n- Verify with agent-browser snapshot\n\n## Troubleshooting\n\n- If the command is not found on Linux ARM64, use the full path in the bin folder.\n- If an element is not found, use snapshot to find the correct ref.\n- If the page is not loaded, add a wait command after navigation.\n- Use --headed to see the browser window for debugging.\n\n## Options\n\n- --session <name> uses an isolated session.\n- --json provides JSON output.\n- --full takes a full page screenshot.\n- --headed shows the browser window.\n- --timeout sets the command timeout in milliseconds.\n\n## Notes\n\n- Refs are stable per page load but change on navigation.\n- Always snapshot after navigation to get new refs.\n- Use fill instead of type for input fields to ensure existing text is cleared.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72ce44tqw8bnnnewrn1s5x3s7yz7sq\",\n  \"slug\": \"agent-browser\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1768170466579\n}","readmeExcerpt":"Skill: Agent Browser Owner: TheSethRose Summary: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. Tags: automation:0.1.0, browser:0.1.0, headless:0.1.0, latest:0.2.0, web:0.1.0 Version history: v0.2.0 | 2026-01-20T04:12:22.488Z | auto **Big update: Expanded documentation and new contribution guidelines.","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"npm install -g agent-browser\nagent-browser install\nagent-browser install --with-deps"},{"language":"bash","snippet":"git clone https://github.com/vercel-labs/agent-browser\ncd agent-browser\npnpm install\npnpm build\nagent-browser install"},{"language":"bash","snippet":"agent-browser open <url>        # Navigate to page\nagent-browser snapshot -i       # Get interactive elements with refs\nagent-browser click @e1         # Click element by ref\nagent-browser fill @e2 \"text\"   # Fill input by ref\nagent-browser close             # Close browser"},{"language":"bash","snippet":"agent-browser open <url>      # Navigate to URL\nagent-browser back            # Go back\nagent-browser forward         # Go forward\nagent-browser reload          # Reload page\nagent-browser close           # Close browser"},{"language":"bash","snippet":"agent-browser snapshot            # Full accessibility tree\nagent-browser snapshot -i         # Interactive elements only (recommended)\nagent-browser snapshot -c         # Compact output\nagent-browser snapshot -d 3       # Limit depth to 3\nagent-browser snapshot -s \"#main\" # Scope to CSS selector"},{"language":"bash","snippet":"agent-browser click @e1           # Click\nagent-browser dblclick @e1        # Double-click\nagent-browser focus @e1           # Focus element\nagent-browser fill @e2 \"text\"     # Clear and type\nagent-browser type @e2 \"text\"     # Type without clearing\nagent-browser press Enter         # Press key\nagent-browser press Control+a     # Key combination\nagent-browser keydown Shift       # Hold key down\nagent-browser keyup Shift         # Release key\nagent-browser hover @e1           # Hover\nagent-browser check @e1           # Check checkbox\nagent-browser uncheck @e1         # Uncheck checkbox\nagent-browser select @e1 \"value\"  # Select dropdown\nagent-browser scroll down 500     # Scroll page\nagent-browser scrollintoview @e1  # Scroll element into view\nagent-browser drag @e1 @e2        # Drag and drop\nagent-browser upload @e1 file.pdf # Upload files"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: Agent Browser\ndescription: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.\nread_when:\n  - Automating web interactions\n  - Extracting structured data from pages\n  - Filling forms programmatically\n  - Testing web UIs\nmetadata: {\"clawdbot\":{\"emoji\":\"🌐\",\"requires\":{\"bins\":[\"node\",\"npm\"]}}}\nallowed-tools: Bash(agent-browser:*)\n---\n\n# Browser Automation with agent-browser\n\n## Installation\n\n### npm recommended\n\n```bash\nnpm install -g agent-browser\nagent-browser install\nagent-browser install --with-deps\n```\n\n### From Source\n\n```bash\ngit clone https://github.com/vercel-labs/agent-browser\ncd agent-browser\npnpm install\npnpm build\nagent-browser install\n```\n\n## Quick start\n\n```bash\nagent-browser open <url>        # Navigate to page\nagent-browser snapshot -i       # Get interactive elements with refs\nagent-browser click @e1         # Click element by ref\nagent-browser fill @e2 \"text\"   # Fill input by ref\nagent-browser close             # Close browser\n```\n\n## Core workflow\n\n1. Navigate: `agent-browser open <url>`\n2. Snapshot: `agent-browser snapshot -i` (returns elements with refs like `@e1`, `@e2`)\n3. Interact using refs from the snapshot\n4. Re-snapshot after navigation or significant DOM changes\n\n## Commands\n\n### Navigation\n\n```bash\nagent-browser open <url>      # Navigate to URL\nagent-browser back            # Go back\nagent-browser forward         # Go forward\nagent-browser reload          # Reload page\nagent-browser close           # Close browser\n```\n\n### Snapshot (page analysis)\n\n```bash\nagent-browser snapshot            # Full accessibility tree\nagent-browser snapshot -i         # Interactive elements only (recommended)\nagent-browser snapshot -c         # Compact output\nagent-browser snapshot -d 3       # Limit depth to 3\nagent-browser snapshot -s \"#main\" # Scope to CSS selector\n```\n\n### Interactions (use @refs from snapshot)\n\n```bash\nagent-browser click @e1           # Click\nagent-browser dblclick @e1        # Double-click\nagent-browser focus @e1           # Focus element\nagent-browser fill @e2 \"text\"     # Clear and type\nagent-browser type @e2 \"text\"     # Type without clearing\nagent-browser press Enter         # Press key\nagent-browser press Control+a     # Key combination\nagent-browser keydown Shift       # Hold key down\nagent-browser keyup Shift         # Release key\nagent-browser hover @e1           # Hover\nagent-browser check @e1           # Check checkbox\nagent-browser uncheck @e1         # Uncheck checkbox\nagent-browser select @e1 \"value\"  # Select dropdown\nagent-browser scroll down 500     # Scroll page\nagent-browser scrollintoview @e1  # Scroll element into view\nagent-browser drag @e1 @e2        # Drag and drop\nagent-browser upload @e1 file.pdf # Upload files\n```\n\n### Get information\n\n```bash\nagent-browser get text @e1        # Get element text\nagent-browser get html @e1        # Get innerHTML\nagent-browser get valu"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72ce44tqw8bnnnewrn1s5x3s7yz7sq\",\n  \"slug\": \"agent-browser\",\n  \"version\": \"0.2.0\",\n  \"publishedAt\": 1768882342488\n}"},{"path":"CONTRIBUTING.md","content":"# Contributing to Agent Browser Skill\n\nThis skill wraps the agent-browser CLI. Determine where the problem lies before reporting issues.\n\n## Issue Reporting Guide\n\n### Open an issue in this repository if\n\n- The skill documentation is unclear or missing\n- Examples in SKILL.md do not work\n- You need help using the CLI with this skill wrapper\n- The skill is missing a command or feature\n\n### Open an issue at the agent-browser repository if\n\n- The CLI crashes or throws errors\n- Commands do not behave as documented\n- You found a bug in the browser automation\n- You need a new feature in the CLI\n\n## Before Opening an Issue\n\n1. Install the latest version\n   ```bash\n   npm install -g agent-browser@latest\n   ```\n\n2. Test the command in your terminal to isolate the issue\n\n## Issue Report Template\n\nUse this template to provide necessary information.\n\n```markdown\n### Description\n[Provide a clear and concise description of the bug]\n\n### Reproduction Steps\n1. [First Step]\n2. [Second Step]\n3. [Observe error]\n\n### Expected Behavior\n[Describe what you expected to happen]\n\n### Environment Details\n- **Skill Version:** [e.g. 1.0.2]\n- **agent-browser Version:** [output of agent-browser --version]\n- **Node.js Version:** [output of node -v]\n- **Operating System:** [e.g. macOS Sonoma, Windows 11, Ubuntu 22.04]\n\n### Additional Context\n- [Full error output or stack trace]\n- [Screenshots]\n- [Website URLs where the failure occurred]\n```\n\n## Adding New Commands to the Skill\n\nUpdate SKILL.md when the upstream CLI adds new commands.\n- Keep the Installation section\n- Add new commands in the correct category\n- Include usage examples"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. Skill: Agent Browser Owner: TheSethRose Summary: A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands. Tags: automation:0.1.0, browser:0.1.0, headless:0.1.0, latest:0.2.0, web:0.1.0 Version history: v0.2.0 | 2026-01-20T04:12:22.488Z | auto **Big update: Expanded documentation and new contribution guidelines.","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":695,"uniquenessScore":60,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-04-15T00:45:39.800Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"agent-directory","verified":false,"confidence":"low","updatedAt":"2026-10-09T10:17:12.901Z","emptyReason":"No close protocol neighbors were found."},"items":[],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[]}}}