Agent skill

Claude Bowser

by disler in disler/bowser

Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser.

No licenceAuto-check: warningsProductivity & Automation

Install Claude Bowser

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add disler/bowser --skill claude-bowser -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install disler/bowser claude-bowser --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/disler/bowser.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/claude-bowser .claude/skills/claude-bowser && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-bowser
GitHub stars
265
Token cost
~327 tokens
SKILL.md length
139 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser.

  • Works in 3 steps: Resize the browser window to 1440x900 → Execute the user's request using Chrome… → Report results back to the user
  • You need to browse websites
  • SKILL.md covers Purpose, Pre-flight Check, Workflow and Limitations
  • Calls claude

What it does

Claude Bowser is an agent skill from disler/bowser. Observable browser automation using Chrome MCP tools. Use when you need to browse websites, take screenshots, interact with web pages, or perform browser tasks in your current Chrome. Keywords - browse, screenshot, browser, chrome, bowser, ui testing, observable.

Its SKILL.md is about 330 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Productivity & Automation, covering Browser automation and MCP servers. It works with Model Context Protocol. The repository describes itself as: Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.

When your agent uses it

  • You need to browse websites
  • Take screenshots
  • Interact with web pages
  • Perform browser tasks in your current Chrome

Example prompts

  • “/claude-bowser”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Resize the browser window to 1440x900
  2. Execute the user's request using Chrome MCP tools (navigate, click, screenshot, etc.)
  3. Report results back to the user

What it can do on your machine

Read from SKILL.md and the folder at commit 26541ac. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Bowser loads about 327 tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 139 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~69
When it runs · the whole SKILL.md, loaded when a task matches
~327

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:10
    ed with `--chrome`. This uses your real Chrome browser — observable, with your existing profile, cookies, and extensions

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 139 words (~327 tokens).

“Automate browsing using Chrome MCP tools (mcpclaude_in_chrome*) available when Claude Code is started with --chrome. This uses your real Chrome browser — observable, with your existing profile, cookies, and extensions.”

— opening of SKILL.md by disler
name
claude-bowser

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .claude/skills/claude-bowser of disler/bowser.

Open the folder on GitHubat commit 26541ac

Compare with similar skills

Claude Bowser next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Bowser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Bowser this skilldisler/bowser265—~327Automated safety check: WarnNone
Zerotoken OpenclawAMOS144/ZeroToken4551 repos~2.9kAutomated safety check: PassMIT
AIPex Browser ControlAIPexStudio/AIPex1.3k—~1.8kAutomated safety check: PassMIT
Isolated Linux Agent Workspaceagent-sh/agent-workspace-linux186—~2.1kAutomated safety check: PassMIT
Altic Studioaltic-dev/altic-mcp174—~3.3kAutomated safety check: PassApache-2.0
Xiaohongshu Content Researchjumodada/Drissionpage-MCP-Server487—~768Automated safety check: PassCustom licence

Similar skills

  • Zerotoken Openclaw

    AMOS144/ZeroToken

    A skill your agent uses when using ZeroToken MCP via OpenClaw for browser automation, trajectory recording and low-token replay, especially for recurring or scheduled browser tasks.

    455 GitHub starsUsed in 1 repo~2.9k tokens
    Productivity & AutomationAuto-check passed
  • AIPex Browser Control

    AIPexStudio/AIPex

    Lets an agent drive Chrome through the AIPex extension and its MCP bridge: navigation, clicking, form filling, screenshots, tab management and downloads.

    1.3k GitHub stars~1.8k tokensUpdated 1 mo ago
    Productivity & AutomationAuto-check passed
  • Isolated Linux Agent Workspace

    agent-sh/agent-workspace-linux

    Drives a hidden, agent-owned Linux desktop and browser over MCP for GUI testing and web automation without touching the user's real desktop.

    186 GitHub stars~2.1k tokensUpdated 7 days ago
    Productivity & AutomationAuto-check passed
  • Altic Studio

    altic-dev/altic-mcp

    macOS automation skill for AppleScript actions and Chrome browser control via MCP CDP tools.

    174 GitHub stars~3.3k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • Xiaohongshu Content Research

    jumodada/Drissionpage-MCP-Server

    A skill your agent uses for authorized, read-only research on public Xiaohongshu content or the local Xiaohongshu-like playground fixture.

    487 GitHub stars~768 tokensUpdated 26 days ago
    Productivity & AutomationAuto-check passed
  • Oya Browser

    OyadotAI/oya-browser

    Drive real Chrome browsers through Oya Browser. An agent skill from OyadotAI/oya-browser.

    349 GitHub stars~2.1k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed

More from disler/bowser

  • Just

    disler/bowser

    Use just to save and run project-specific commands. An agent skill from disler/bowser.

    265 GitHub stars~792 tokensUpdated 7 mo ago
    Auto-check: notes
  • Playwright Bowser

    disler/bowser

    Headless browser automation using Playwright CLI. An agent skill from disler/bowser.

    265 GitHub stars~1.1k tokensUpdated 7 mo ago
    Auto-check: notes

Questions about Claude Bowser

What does Claude Bowser do?

Observable browser automation using Chrome MCP tools. An agent skill from disler/bowser. Claude Bowser is an agent skill from disler/bowser. Observable browser automation using Chrome MCP tools.

When should I use Claude Bowser?

Claude Bowser fits situations like: you need to browse websites; take screenshots; interact with web pages; perform browser tasks in your current Chrome.

How do I install Claude Bowser in Claude Code?

Run `npx skills add disler/bowser --skill claude-bowser -a claude-code`. Or copy the skill folder (.claude/skills/claude-bowser in disler/bowser) into .claude/skills/claude-bowser in your project. Claude Code loads it when a task matches its description.

How do I install Claude Bowser in Codex?

Run `npx skills add disler/bowser --skill claude-bowser -a codex`. Or copy the skill folder (.claude/skills/claude-bowser in disler/bowser) into .agents/skills/claude-bowser in your project. Codex loads it when a task matches its description.

Can I use Claude Bowser in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add disler/bowser --skill claude-bowser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-bowser, .gemini/skills/claude-bowser, .github/skills/claude-bowser and .opencode/skills/claude-bowser in your project.

What does Claude Bowser need to run?

Going by SKILL.md and its folder, Claude Bowser needs the command-line tools its instructions call (claude).

Does Claude Bowser access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claude Bowser safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Claude Bowser use?

No licence was found for Claude Bowser or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Claude Bowser use?

About 327 tokens (SKILL.md is roughly 1.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Bowser?

Skills that share tags, products or a category with Claude Bowser: Zerotoken Openclaw (AMOS144/ZeroToken, 455 stars), AIPex Browser Control (AIPexStudio/AIPex, 1.3k stars), Isolated Linux Agent Workspace (agent-sh/agent-workspace-linux, 186 stars) and Altic Studio (altic-dev/altic-mcp, 174 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Bowser?

disler (a GitHub user) maintains it in disler/bowser, which has 265 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on February 22, 2026.

Source: disler/bowser on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.