How do I install the Agent Browser skill?

Run npx skillmds@latest add markusstrasser/agent-browser in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Agent Browser safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Agent Browser?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Agent Browser free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Agent Browser?

markusstrasser (@markusstrasser) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Agent Browser by markusstrasser — Agent Skill

Name: Agent Browser
Rating: 4.2 (5 reviews)
Author: markusstrasser

Agent Browser

Headless/scripted browser automation from Bash (Vercel Labs CLI, Rust/CDP). Use for navigating pages, filling forms, clicking, screenshots, scraping JS-rendered pages, testing web apps, Electron apps, or any programmatic web interaction — especially in subagents, scouts, launchd jobs, and autonomous runs where claude-in-chrome MCP is unavailable. NOT for the operator's logged-in Chrome session (use claude-in-chrome) or static fetches (WebFetch/Firecrawl).

File contents

agent-browser

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs (~200-400 tokens vs 3-5K for DOM dumps). Installed via brew (2026-07-20); headless by default, --headed for visible.

Lane routing (ours, overrides the vendor's "prefer over everything")

Need	Tool
Operator's logged-in Chrome, SSO sites, real tabs	claude-in-chrome MCP (interactive sessions only)
Static page fetch / crawl at scale	WebFetch / Firecrawl
Scripted or headless automation, JS-rendered pages, web-app verification, subagent/scout/launchd/autonomous contexts	agent-browser

Start here

This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the workflow content from the CLI itself — it always matches the installed version:

agent-browser skills get core             # workflows, common patterns, troubleshooting
agent-browser skills get core --full      # + full command reference and templates

Specialized skills (CLI-served)

agent-browser skills list                  # everything on the installed version
agent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack             # Slack workspace automation
agent-browser skills get dogfood           # Exploratory testing / QA / bug hunts

Core loop

agent-browser open https://example.com
agent-browser snapshot -i        # @e1 [heading] … @e2 [link] …
agent-browser click @e2
agent-browser get url
agent-browser close

Also: eval <js> · set viewport <w> <h> / set device <name> · network requests · console · react tree / vitals (web-dev) · --session <name> isolation · connect <port> CDP-attach · cookies set --curl <file> for auth.

Gotchas

Bundled-Chrome download (agent-browser install) can time out; system-Chrome fallback works — don't block on it.
Interactive and JSON snapshots can omit state attributes even when the page exposes them. If a decision depends on state such as aria-pressed, query the principal value directly (agent-browser get attr @eN aria-pressed) instead of inferring it from the snapshot.
close closes the browser pages, but the session daemon may remain active. In session info --json, distinguish daemon active from runtime.browserLaunched and pageCount; use close --all only when every session should be reset.
Observability dashboard on port 4848 (independent of sessions).

Calibration history: references/calibration.md.

---name: agent-browserdescription: Headless/scripted browser automation from Bash (Vercel Labs CLI, Rust/CDP). Use for navigating pages, filling forms, clicking, screenshots, scraping JS-rendered pages, testing web apps, Electron apps, or any programmatic web interaction — especially in subagents, scouts, launchd jobs, and autonomous runs where claude-in-chrome MCP is unavailable. NOT for the operator's logged-in Chrome session (use claude-in-chrome) or static fetches (WebFetch/Firecrawl).---# agent-browserFast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact `@eN` element refs (~200-400 tokens vs 3-5K for DOM dumps). Installed via brew (2026-07-20); headless by default, `--headed` for visible.## Lane routing (ours, overrides the vendor's "prefer over everything")| Need | Tool ||---|---|| Operator's logged-in Chrome, SSO sites, real tabs | claude-in-chrome MCP (interactive sessions only) || Static page fetch / crawl at scale | WebFetch / Firecrawl || Scripted or headless automation, JS-rendered pages, web-app verification, subagent/scout/launchd/autonomous contexts | **agent-browser** |## Start hereThis file is a discovery stub, not the usage guide. Before running any `agent-browser` command, load the workflow content from the CLI itself — it always matches the installed version:```bashagent-browser skills get core # workflows, common patterns, troubleshootingagent-browser skills get core --full # + full command reference and templates```## Specialized skills (CLI-served)```bashagent-browser skills list # everything on the installed versionagent-browser skills get electron # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)agent-browser skills get slack # Slack workspace automationagent-browser skills get dogfood # Exploratory testing / QA / bug hunts```## Core loop```bashagent-browser open https://example.comagent-browser snapshot -i # @e1 [heading] … @e2 [link] …agent-browser click @e2agent-browser get urlagent-browser close```Also: `eval <js>` · `set viewport <w> <h>` / `set device <name>` · `network requests` · `console` · `react tree` / `vitals` (web-dev) · `--session <name>` isolation · `connect <port>` CDP-attach · `cookies set --curl <file>` for auth.## Gotchas- Bundled-Chrome download (`agent-browser install`) can time out; system-Chrome fallback works — don't block on it.- Interactive and JSON snapshots can omit state attributes even when the page exposes them. If a decision depends on state such as `aria-pressed`, query the principal value directly (`agent-browser get attr @eN aria-pressed`) instead of inferring it from the snapshot.- `close` closes the browser pages, but the session daemon may remain active. In `session info --json`, distinguish daemon `active` from `runtime.browserLaunched` and `pageCount`; use `close --all` only when every session should be reset.- Observability dashboard on port 4848 (independent of sessions).Calibration history: [references/calibration.md](references/calibration.md).

Frequently asked questions