agent-browser
agent-browser enables you to script and automate browser-based workflows directly from the command line. Execute web interactions, navigate pages, and handle complex tasks without manual intervention. Built for developers who need reliable programmatic control over web automation.
agent-browser is a command-line tool that enables you to script and automate browser-based workflows directly from the CLI. It provides programmatic control over web interactions, allowing you to navigate pages, execute complex tasks, and handle automation without manual intervention. The tool is built for developers who need reliable, scriptable access to browser automation capabilities.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-04-13
agent-browser is a command-line tool that enables you to script and automate browser-based workflows directly from the CLI. It provides programmatic control over web interactions, allowing you to navigate pages, execute complex tasks, and handle automation without manual intervention. The tool is built for developers who need reliable, scriptable access to browser automation capabilities.
Use it when
- Yes, agent-browser supports automating form filling, login, and authentication workflows.
- agent-browser enables you to extract data and take screenshots from web pages as part of your automation workflows.
Verify before relying
Read SKILL.md below before installing (11 files). Open directory: indexed for reading, not audited.
Install
Intelligent-Internet/ii-agent/agent-browser · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is agent-browser and how does it automate browser interactions?
agent-browser is a command-line tool that enables you to script and automate browser-based workflows directly from the CLI. It provides programmatic control over web interactions, allowing you to navigate pages, execute complex tasks, and handle automation without manual intervention. The tool is built for developers who need reliable, scriptable access to browser automation capabilities.
Can agent-browser automate website interactions and fill forms programmatically?
Yes, agent-browser supports automating form filling, login, and authentication workflows. You can programmatically fill fields and click buttons to complete complex web interactions. This makes agent-browser ideal for automating repetitive tasks like account access, data entry, and multi-step web processes through CLI commands.
How does agent-browser help with web scraping and data extraction?
agent-browser enables you to extract data and take screenshots from web pages as part of your automation workflows. You can capture page content, retrieve specific data elements, and generate snapshots of web pages—all controlled programmatically through command-line commands. This functionality supports both content extraction and visual verification of web pages.
Is agent-browser suitable for testing web applications automatically?
Yes, agent-browser is designed to test web applications and verify page state changes. You can automate test scenarios, validate application behavior, and confirm that page elements respond correctly to interactions. This makes agent-browser a practical choice for web app testing automation and quality assurance workflows.
Does agent-browser support managing multiple parallel browser sessions?
agent-browser supports managing multiple parallel browser sessions for concurrent automation. This capability allows you to run simultaneous workflows across different browser instances, enabling efficient handling of large-scale automation tasks and concurrent web interactions from the command line.
What license does agent-browser use?
agent-browser is released under the Apache-2.0 license, which permits both commercial and non-commercial use with appropriate attribution and compliance with the license terms.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Browser Automation with agent-browser
Core Workflow
Every browser automation follows this pattern:
- Navigate:
agent-browser open <url> - Snapshot:
agent-browser snapshot -i(get element refs like@e1,@e2) - Interact: Use refs to click, fill, select
- Re-snapshot: After navigation or DOM changes, get fresh refs
```bash agent-browser open https://example.com/form agent-browser snapshot -i
Output: @e1 [input type="email"], @e2 [input type="password"], @e3 [button] "Submit"
agent-browser fill @e1 "user@example.com" agent-browser fill @e2
(truncated - see the full file via the links below)
File tree — 11 files
src/ii_agent/agents/skills/builtin/agent-browser/SKILL.md
src/ii_agent/agents/skills/builtin/agent-browser/references/authentication.md
src/ii_agent/agents/skills/builtin/agent-browser/references/commands.md
src/ii_agent/agents/skills/builtin/agent-browser/references/profiling.md
src/ii_agent/agents/skills/builtin/agent-browser/references/proxy-support.md
src/ii_agent/agents/skills/builtin/agent-browser/references/session-management.md
src/ii_agent/agents/skills/builtin/agent-browser/references/snapshot-refs.md
src/ii_agent/agents/skills/builtin/agent-browser/references/video-recording.md
src/ii_agent/agents/skills/builtin/agent-browser/templates/authenticated-session.sh
src/ii_agent/agents/skills/builtin/agent-browser/templates/capture-workflow.sh
src/ii_agent/agents/skills/builtin/agent-browser/templates/form-automation.sh
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Automate browser interactions and web tasks programmatically via CLI commands”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
agent-browser lets you orchestrate automated browser interactions through a remote HTTP interface, enabling your applications to navigate websites, populate forms, trigger actions, and harvest information at scale. Built for sandbox deployment, it provides streaming event handling and session management across multiple coding agent platforms.
Agent Browser equips Claude with the ability to visit web pages, extract content, and perform interactions like clicking and form submission—all through code. This skill transforms Claude into an autonomous web agent capable of gathering information and completing tasks across the internet without manual intervention.
Agent Browser equips your AI agents with the ability to explore web content and perform actions on live websites in real time. Perfect for automating research, data collection, and web-based tasks that require intelligent navigation and interaction.
agent-browser enables Claude Code to interact with web pages programmatically, handling clicks, form submissions, and navigation tasks. This skill bridges AI agents and browser automation, letting you build workflows that manipulate web content dynamically. Perfect for testing, data collection, and repetitive web tasks.
Agent Browser equips your agent with web navigation capabilities, allowing it to visit URLs, interact with page elements, and retrieve information from live websites. This skill bridges the gap between your agent and the open web, enabling research, data gathering, and automated web interactions without manual intervention.
agent-browser lets you script repetitive web interactions—form submissions, element clicks, page navigation—directly through Claude Code. Built for end-to-end encrypted access, it brings browser automation to your workflow without leaving SkillFed's environment.
More skills Agent Browser (NOASSERTION) · agent-browser (Apache-2.0) · Agent Browser (unlicensed) · Agent Browser (unlicensed) · Agent Browser (AGPL-3.0) · Agent Browser (unlicensed) · Agent Browser (unlicensed) · agent-browser (MIT)