agent-browser

agent-browser is a skill for Claude Code from Suge8/Bao. It costs 19 tokens per session (3,152 once invoked), scanned A, original, MIT.

A guide and command workflow for controlling a web browser. It covers opening pages, inspecting interactive elements, clicking, filling forms, taking screenshots, testing websites, and scraping content.

In plain words
What is it for?
Use it for browser automation, form filling, screenshots, web testing, and scraping.
Why use it?
It provides a consistent way to perform browser tasks that require interacting with pages rather than only reading their source.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for browser automation, form filling, screenshots, web testing, and scraping.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/suge8/bao/agent-browser
View source ↗ Suge8/Bao
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Suge8/Bao --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/Suge8/Bao

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/suge8/bao/agent-browser/github.svg)](https://agentmods.dev/skills/suge8/bao/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/suge8/bao/agent-browser"><img src="https://agentmods.dev/badge/skills/suge8/bao/agent-browser/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for agent-browser

Your own site · 80×15
<a href="https://agentmods.dev/skills/suge8/bao/agent-browser"><img src="https://agentmods.dev/badge/skills/suge8/bao/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.03152
Opus 5.5 $0.00008 $0.01261
Sonnet 5.5 $0.00004 $0.00630
Haiku 4.5 $0.00002 $0.00315

Measured 1mo ago against content hash a08ad64bd5a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-browser scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 3 executable files (templates/authenticated-session.sh, templates/capture-workflow.sh, templates/form-automation.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

bao/skills/agent-browser/SKILL.md · 391 lines

How it starts

The opening of the file, as written. The whole thing — 391 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Automation with agent-browser

Preferred path in Bao

If agent_browser is present in ## Available Now, use that tool instead of composing shell commands yourself.

Use this skill to understand the workflow and command vocabulary behind the tool, or to debug the underlying CLI behavior when needed.

Runtime

Bao desktop builds should prefer the bundled managed browser runtime.

Source / CLI environments can still use this workflow, but they must provide a browser runtime explicitly for Bao to call. The recommended testing path is to point BAO_BROWSER_RUNTIME_ROOT at a prepared runtime directory instead of assuming a global agent-browser binary on PATH.

Quick start

Preferred Bao tool call shape:

{"action":"open","args":["https://example.com"]}
{"action":"snapshot"}
{"action":"click","args":["@e1"]}
{"action":"fill","args":["@e2","hello"]}
{"action":"close"}

Underlying CLI equivalent:

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 to the page.
  2. Snapshot the page structure and interactive refs.
  3. Interact using refs from the latest snapshot.
  4. Re-snapshot after navigation or significant DOM changes.

In Bao, the same loop maps naturally to:

  1. agent_browser(action="open", args=[url])
  2. agent_browser(action="snapshot")
  3. agent_browser(action="click"|"fill"|..., args=[...])
  4. agent_browser(action="snapshot") again when the page changed

Commands

Navigation

agent-browser open <url>      # Navigate to URL (aliases: goto, navigate)
                              # Supports: https://, http://, file://, about:, data://
                              # Auto-prepends https:// if no protocol given
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser (aliases: quit, exit)
agent-browser connect 9222    # Connect to browser via CDP port

Read the full file on GitHub · 391 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago First seen · 391 lines · 19 tokens per session scan A a08ad64bd5a1

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository Suge8/Bao (23 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 3,152 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

interactive-login

Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.

yc-software/qm · 46 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

azure-messaging-webpubsub-java

Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.

microsoft/skills · 43 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

open-design-browser

Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…

compozy/compozy · 56 tokens