Integration guide for SawyerHood/dev-browser, a Claude Code plugin for browser automation. This skill enables agents to research, test web UIs, and interact with web applications using a headless browser.
Provides browser automation for research, testing web UIs, and interacting with dynamic pages. Activates when you ask to navigate, click, type, or verify elements on websites or localhost servers.
/plugin marketplace add b-open-io/prompts/plugin install bopen-tools@b-open-ioThis skill inherits all available tools. When active, it can use any tool Claude has access to.
dev-browser is a plugin for Claude Code that provides browser automation capabilities. It allows the agent to control a web browser to navigate pages, interact with elements, take screenshots, and extract information. This is essential for:
curl -fsSL https://bun.sh/install | bash
To install the dev-browser plugin in Claude Code:
Add the Marketplace (if not already added):
/plugin marketplace add sawyerhood/dev-browser
Install the Plugin:
/plugin install dev-browser@sawyerhood/dev-browser
Restart Claude Code: You must restart the Claude Code CLI for the changes to take effect.
Once installed, the dev-browser exposes tools that the agent can use. You generally do not need to call specific tool names manually; instead, you prompt the agent with natural language.
Navigation & Research:
Interaction:
Testing/Verification:
While the agent handles the specific tool calls, understanding the underlying capabilities helps in crafting better prompts:
goto(url), back(), forward()click(selector), type(selector, text), press(key)content(), screenshot()evaluate(javascript) - Run custom JS on the pagehttp://localhost:PORT to test local applications. Ensure the server is running before asking the browser to visit."Browser not found" / "Command failed"
/plugin list."Element not found"
Connection Refused (Localhost)
npm run dev, etc.).sawyerhood/dev-browserThis skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.