diff --git a/README.md b/README.md index f6f3b14..2d25c9b 100644 --- a/README.md +++ b/README.md @@ -327,6 +327,7 @@ agent-browser snapshot -i -c -d 5 # Combine options | `--user-agent ` | Custom User-Agent string (or `AGENT_BROWSER_USER_AGENT` env) | | `--proxy ` | Proxy server URL with optional auth (or `AGENT_BROWSER_PROXY` env) | | `--proxy-bypass ` | Hosts to bypass proxy (or `AGENT_BROWSER_PROXY_BYPASS` env) | +| `-p, --provider ` | Cloud browser provider (or `AGENT_BROWSER_PROVIDER` env) | | `--json` | JSON output (for agents) | | `--full, -f` | Full page screenshot | | `--name, -n` | Locator name filter | @@ -661,6 +662,16 @@ Use agent-browser to test the login flow. Run agent-browser --help to see availa The `--help` output is comprehensive and most agents can figure it out from there. +### AI Coding Assistants + +Add the skill to your AI coding assistant for richer context: + +```bash +npx skills add vercel-labs/agent-browser +``` + +This works with Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Goose, OpenCode, and Windsurf. + ### AGENTS.md / CLAUDE.md For more consistent results, add to your project or global instructions file: @@ -677,31 +688,6 @@ Core workflow: 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. - -**Plugin (recommended):** - -```bash -/plugin marketplace add vercel-labs/agent-browser -/plugin install agent-browser -``` - -**Manual install:** - -```bash -cp -r node_modules/agent-browser/skills/agent-browser .claude/skills/ -``` - -Or download directly: - -```bash -mkdir -p .claude/skills/agent-browser -curl -o .claude/skills/agent-browser/SKILL.md \ - https://raw.githubusercontent.com/vercel-labs/agent-browser/main/skills/agent-browser/SKILL.md -``` - ## Integrations ### Browserbase diff --git a/cli/src/output.rs b/cli/src/output.rs index 12c157d..45eb8b5 100644 --- a/cli/src/output.rs +++ b/cli/src/output.rs @@ -1535,6 +1535,7 @@ Options: e.g., --proxy "http://user:pass@127.0.0.1:7890" --proxy-bypass Bypass proxy for these hosts (or AGENT_BROWSER_PROXY_BYPASS) e.g., --proxy-bypass "localhost,*.internal.com" + -p, --provider Cloud browser provider (or AGENT_BROWSER_PROVIDER env) --json JSON output --full, -f Full page screenshot --headed Show browser window (not headless) @@ -1545,6 +1546,7 @@ Options: Environment: AGENT_BROWSER_SESSION Session name (default: "default") AGENT_BROWSER_EXECUTABLE_PATH Custom browser executable path + AGENT_BROWSER_PROVIDER Cloud browser provider AGENT_BROWSER_STREAM_PORT Enable WebSocket streaming on port (e.g., 9223) Examples: diff --git a/skills/agent-browser/SKILL.md b/skills/agent-browser/SKILL.md index 3028a83..5eda6a7 100644 --- a/skills/agent-browser/SKILL.md +++ b/skills/agent-browser/SKILL.md @@ -225,6 +225,7 @@ agent-browser --json ... # JSON output for parsing agent-browser --headed ... # Show browser window (not headless) agent-browser --full ... # Full page screenshot (-f) agent-browser --cdp ... # Connect via Chrome DevTools Protocol +agent-browser -p ... # Cloud browser provider (--provider) agent-browser --proxy ... # Use proxy server agent-browser --headers ... # HTTP headers scoped to URL's origin agent-browser --executable-path

# Custom browser executable @@ -248,6 +249,7 @@ agent-browser --proxy socks5://proxy.com:1080 open example.com AGENT_BROWSER_SESSION="mysession" # Default session name AGENT_BROWSER_EXECUTABLE_PATH="/path/chrome" # Custom browser path AGENT_BROWSER_EXTENSIONS="/ext1,/ext2" # Comma-separated extension paths +AGENT_BROWSER_PROVIDER="browserbase" # Cloud browser provider AGENT_BROWSER_STREAM_PORT="9223" # WebSocket streaming port AGENT_BROWSER_HOME="/path/to/agent-browser" # Custom install location (for daemon.js) ```