usage with agents

* fix session cmd

* address feedback

README.md

@@ -403,6 +403,50 @@ The daemon starts automatically on first command and persists between commands f
 | Linux x64 | ✅ Native Rust | Node.js |
 | Windows | - | Node.js |
 
+## Usage with AI Agents
+
+### Just ask the agent
+
+The simplest approach - just tell your agent to use it:
+
+```
+Use agent-browser to test the login flow. Run agent-browser --help to see available commands.
+```
+
+The `--help` output is comprehensive and most agents can figure it out from there.
+
+### AGENTS.md / CLAUDE.md
+
+For more consistent results, add to your project or global instructions file:
+
+```markdown
+## Browser Automation
+
+Use `agent-browser` for web automation. Run `agent-browser --help` for all commands.
+
+Core workflow:
+1. `agent-browser open <url>` - Navigate to page
+2. `agent-browser snapshot -i` - Get interactive elements with refs (@e1, @e2)
+3. `agent-browser click @e1` / `fill @e2 "text"` - Interact using refs
+4. Re-snapshot after page changes
+```
+
+### Claude Code Skill
+
+For Claude Code, a [skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices) provides richer context:
+
+```bash
+cp -r node_modules/agent-browser/skills/browsing-web .claude/skills/
+```
+
+Or download:
+
+```bash
+mkdir -p .claude/skills/browsing-web
+curl -o .claude/skills/browsing-web/SKILL.md \
+  https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/browsing-web/SKILL.md
+```
+
 ## License
 
 Apache-2.0

cli/Cargo.lock

@@ -9,6 +9,7 @@ dependencies = [
  "libc",
  "serde",
  "serde_json",
+ "windows-sys",
 ]
 
 [[package]]
@@ -107,6 +108,79 @@ version = "1.0.22"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
 
+[[package]]
+name = "windows-sys"
+version = "0.52.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "282be5f36a8ce781fad8c8ae18fa3f9beff57ec1b52cb3de0789201425d9a33d"
+dependencies = [
+ "windows-targets",
+]
+
+[[package]]
+name = "windows-targets"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b724f72796e036ab90c1021d4780d4d3d648aca59e491e6b98e725b84e99973"
+dependencies = [
+ "windows_aarch64_gnullvm",
+ "windows_aarch64_msvc",
+ "windows_i686_gnu",
+ "windows_i686_gnullvm",
+ "windows_i686_msvc",
+ "windows_x86_64_gnu",
+ "windows_x86_64_gnullvm",
+ "windows_x86_64_msvc",
+]
+
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "32a4622180e7a0ec044bb555404c800bc9fd9ec262ec147edd5989ccd0c02cd3"
+
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "09ec2a7bb152e2252b53fa7803150007879548bc709c039df7627cabbd05d469"
+
+[[package]]
+name = "windows_i686_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8e9b5ad5ab802e97eb8e295ac6720e509ee4c243f69d781394014ebfe8bbfa0b"
+
+[[package]]
+name = "windows_i686_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0eee52d38c090b3caa76c563b86c3a4bd71ef1a819287c19d586d7334ae8ed66"
+
+[[package]]
+name = "windows_i686_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "240948bc05c5e7c6dabba28bf89d89ffce3e303022809e73deaefe4f6ec56c66"
+
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "147a5c80aabfbf0c7d901cb5895d1de30ef2907eb21fbbab29ca94c5b08b1a78"
+
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24d5b23dc417412679681396f2b49f3de8c1473deb516bd34410872eff51ed0d"
+
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.52.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "589f6da84c646204747d1270a2a5661ea66ed1cced2631d546fdfb155959f9ec"
+
 [[package]]
 name = "zmij"
 version = "1.0.12"

cli/Cargo.toml

@@ -12,6 +12,9 @@ serde_json = "1.0"
 [target.'cfg(unix)'.dependencies]
 libc = "0.2"
 
+[target.'cfg(windows)'.dependencies]
+windows-sys = { version = "0.52", features = ["Win32_System_Threading", "Win32_Foundation"] }
+
 [profile.release]
 opt-level = 3
 lto = true

cli/src/main.rs

@@ -6,14 +6,93 @@ mod output;
 
 use serde_json::json;
 use std::env;
+use std::fs;
 use std::process::exit;
 
+#[cfg(unix)]
+use libc;
+
+#[cfg(windows)]
+use windows_sys::Win32::Foundation::CloseHandle;
+#[cfg(windows)]
+use windows_sys::Win32::System::Threading::{OpenProcess, PROCESS_QUERY_LIMITED_INFORMATION};
+
 use commands::{gen_id, parse_command, ParseError};
 use connection::{ensure_daemon, send_command};
 use flags::{clean_args, parse_flags};
 use install::run_install;
 use output::{print_help, print_response};
 
+fn run_session(args: &[String], session: &str, json_mode: bool) {
+    let subcommand = args.get(1).map(|s| s.as_str());
+
+    match subcommand {
+        Some("list") => {
+            let tmp = env::temp_dir();
+            let mut sessions: Vec<String> = Vec::new();
+
+            if let Ok(entries) = fs::read_dir(&tmp) {
+                for entry in entries.flatten() {
+                    let name = entry.file_name().to_string_lossy().to_string();
+                    // Look for socket files (Unix) or pid files
+                    if name.starts_with("agent-browser-") && name.ends_with(".pid") {
+                        let session_name = name
+                            .strip_prefix("agent-browser-")
+                            .and_then(|s| s.strip_suffix(".pid"))
+                            .unwrap_or("");
+                        if !session_name.is_empty() {
+                            // Check if session is actually running
+                            let pid_path = tmp.join(&name);
+                            if let Ok(pid_str) = fs::read_to_string(&pid_path) {
+                                if let Ok(pid) = pid_str.trim().parse::<u32>() {
+                                    #[cfg(unix)]
+                                    let running = unsafe { libc::kill(pid as i32, 0) == 0 };
+                                    #[cfg(windows)]
+                                    let running = unsafe {
+                                        let handle = OpenProcess(PROCESS_QUERY_LIMITED_INFORMATION, 0, pid);
+                                        if handle != 0 {
+                                            CloseHandle(handle);
+                                            true
+                                        } else {
+                                            false
+                                        }
+                                    };
+                                    if running {
+                                        sessions.push(session_name.to_string());
+                                    }
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+
+            if json_mode {
+                println!(
+                    r#"{{"success":true,"data":{{"sessions":{}}}}}"#,
+                    serde_json::to_string(&sessions).unwrap_or_default()
+                );
+            } else if sessions.is_empty() {
+                println!("No active sessions");
+            } else {
+                println!("Active sessions:");
+                for s in &sessions {
+                    let marker = if s == session { "→" } else { " " };
+                    println!("{} {}", marker, s);
+                }
+            }
+        }
+        None | Some(_) => {
+            // Just show current session
+            if json_mode {
+                println!(r#"{{"success":true,"data":{{"session":"{}"}}}}"#, session);
+            } else {
+                println!("{}", session);
+            }
+        }
+    }
+}
+
 fn main() {
     let args: Vec<String> = env::args().skip(1).collect();
     let flags = parse_flags(&args);
@@ -31,6 +110,12 @@ fn main() {
         return;
     }
 
+    // Handle session separately (doesn't need daemon)
+    if clean.get(0).map(|s| s.as_str()) == Some("session") {
+        run_session(&clean, &flags.session, flags.json);
+        return;
+    }
+
     let cmd = match parse_command(&clean, &flags) {
         Ok(c) => c,
         Err(e) => {

cli/src/output.rs

@@ -215,6 +215,10 @@ Debug:
   errors [--clear]           View page errors
   highlight <sel>            Highlight element
 
+Sessions:
+  session                    Show current session name
+  session list               List active sessions
+
 Setup:
   install                    Install browser binaries
   install --with-deps        Also install system dependencies (Linux)

package.json

@@ -7,7 +7,8 @@
   "files": [
     "dist",
     "bin",
-    "scripts"
+    "scripts",
+    "skills"
   ],
   "bin": {
     "agent-browser": "./bin/agent-browser"

skills/browsing-web/SKILL.md

@@ -0,0 +1,143 @@
+---
+name: browsing-web
+description: Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
+---
+
+# Browser Automation with agent-browser
+
+## 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 "user@test.com"
+```
+
+## 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 "user@example.com"
+agent-browser fill @e2 "password123"
+agent-browser click @e3
+agent-browser wait --load networkidle
+agent-browser snapshot -i  # Check result
+```
+
+## Example: Authentication with saved state
+
+```bash
+# Login once
+agent-browser open https://app.example.com/login
+agent-browser snapshot -i
+agent-browser fill @e1 "username"
+agent-browser fill @e2 "password"
+agent-browser click @e3
+agent-browser wait --url "**/dashboard"
+agent-browser state save auth.json
+
+# Later sessions: load saved state
+agent-browser state load auth.json
+agent-browser open https://app.example.com/dashboard
+```
+
+## Sessions (parallel browsers)
+
+```bash
+agent-browser --session test1 open site-a.com
+agent-browser --session test2 open site-b.com
+agent-browser session list
+```
+
+## JSON output (for parsing)
+
+Add `--json` for machine-readable output:
+```bash
+agent-browser snapshot -i --json
+agent-browser get text @e1 --json
+```
+
+## Debugging
+
+```bash
+agent-browser open example.com --headed  # Show browser window
+agent-browser console                    # View console messages
+agent-browser errors                     # View page errors
+```