Agent skill

Agent Browser

by infometa in infometa/workbuddyskills

A skill your agent uses when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows.

No licenceAuto-check passedProductivity & Automation

Install Agent Browser

skills CLI
$ npx skills add infometa/workbuddyskills --skill agent-browser -a claude-code

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

GitHub CLI
$ gh skill install infometa/workbuddyskills agent-browser --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/infometa/workbuddyskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codebuddy-plugins-official/plugins/agent-browser .claude/skills/agent-browser && 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
agent-browser
GitHub stars
342
Token cost
~2.1k tokens
SKILL.md length
899 words
Files
8 (incl. scripts, references)
Skills in repo
235
Repo updated
First seen
Licence
None found

At a glance

A skill your agent uses when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows.

  • Works in 5 steps: Open target URL. → Wait for page load when needed. → Inspect page with snapshot or snapshot -i. → …
  • The user needs browser automation
  • SKILL.md covers Platform Support, Prerequisites, Installation and Required Command Sequence, plus 7 more sections
  • Runs Shell and PowerShell scripts from its folder; calls npm, node and npx

What it does

Agent Browser is an agent skill from infometa/workbuddyskills. Use this skill when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows. This skill uses the open source vercel-labs/agent-browser CLI and supports macOS, Linux, and Windows x64.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 11 other files, including scripts and reference files (for example `.codebuddy-plugin/plugin.json`, `README.md` and `references/troubleshooting.md`).

It sits in Productivity & Automation, covering Browser automation. It works with Linux, macOS and Vercel. The repository describes itself as: WorkBuddy skills / connectors / experts archive for offline study.

When your agent uses it

  • The user needs browser automation
  • Including opening web pages
  • Taking screenshots
  • Extracting page content

Example prompts

  • “/agent-browser”

Requirements

  • Node.js
  • A Bash shell
  • PowerShell

Workflow steps

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

  1. Open target URL.
  2. Wait for page load when needed.
  3. Inspect page with snapshot or snapshot -i.
  4. Interact with the page.
  5. Close browser when done.

What it can do on your machine

Read from SKILL.md and the folder at commit 9830caf. 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

    Ships 1 file in scripts/ (Shell and PowerShell), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • node
    • npx
    • curl

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

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    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

Agent Browser loads about 2.1k tokens when it runs, and up to ~3.1k if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 899 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~76
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.1k

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 passed

The automated check found no risky patterns in SKILL.md.

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 899 words (~2,056 tokens).

“Use agent-browser CLI for full browser automation tasks. It is suitable when a page needs JavaScript rendering, real browser interaction, screenshots, or form automation.”

— opening of SKILL.md by infometa
name
agent-browser
version
1.3.0

Read the full SKILL.md on GitHub

Files

SKILL.md and 7 other files (scripts, references) in plugins/codebuddy-plugins-official/plugins/agent-browser of infometa/workbuddyskills.

  • SKILL.md
  • .codebuddy-plugin/plugin.json
  • README.md
  • references/troubleshooting.md
  • references/windows-support.md
  • scripts/setup.sh
  • templates/install-unix.sh
  • templates/install-windows.ps1

Open the folder on GitHubat commit 9830caf

Compare with similar skills

Agent Browser 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.

Agent Browser compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agent Browser this skillinfometa/workbuddyskills342—~2.1kAutomated safety check: PassNone
Browser MCP Agentantibrow/anti-detect-browser-skills9141 repos~4.2kAutomated safety check: WarnMIT
Drive Screencoleam00/skills670—~5.4kAutomated safety check: PassMIT
Computer Usexuzhougeng/wisp-science1k—~2.9kAutomated safety check: PassAGPL-3.0
Vercel Token Setupvellum-ai/vellum-assistant1.4k—~2.4kAutomated safety check: PassMIT
Agent Browser CLIvercel-labs/agent-browser44k24 repos~864Automated safety check: PassApache-2.0

Similar skills

  • Browser MCP Agent

    antibrow/anti-detect-browser-skills

    Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so…

    914 GitHub starsUsed in 1 repo~4.2k tokens
    Productivity & AutomationAuto-check: warnings
  • Drive Screen

    coleam00/skills

    Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals.

    670 GitHub stars~5.4k tokensUpdated 20 days ago
    Productivity & AutomationAuto-check passed
  • Computer Use

    xuzhougeng/wisp-science

    Use Cua Driver through MCP to inspect and operate the user's native desktop apps on Windows, macOS, or Linux.

    1k GitHub stars~2.9k tokensUpdated today
    Productivity & AutomationAuto-check passed
  • Vercel Token Setup

    vellum-ai/vellum-assistant

    Set up a Vercel API token for publishing apps using browser automation

    1.4k GitHub stars~2.4k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed
  • Agent Browser CLI

    vercel-labs/agent-browser

    Official

    Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking…

    44k GitHub starsUsed in 24 repos~864 tokens
    Productivity & AutomationAuto-check passed
  • Before And After

    sanity-io/sanity

    Official

    Add existing screenshots or screen recordings to a GitHub pull request as a before/after or preview block.

    6.4k GitHub starsUsed in 1 repo~2.1k tokens
    Productivity & AutomationAuto-check passed

More from infometa/workbuddyskills

All 235 skills in this repo
  • Campus Event Playbook

    infometa/workbuddyskills

    This skill should be used when planning, coordinating, running, or reviewing student-led campus events, including club recruitment, freshman mixers, welcome activities, small talks, competitions…

    342 GitHub stars~861 tokensUpdated yesterday
    Auto-check passed
  • Teachany

    infometa/workbuddyskills

    K-12 interactive courseware creation. An agent skill from infometa/workbuddyskills.

    342 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check: notes
  • Weight Management HTML

    infometa/workbuddyskills

    A skill your agent uses when the adult weight-management MCP needs to be installed/set up in WorkBuddy (connector) or its result must be rendered as a standalone Chinese HTML plan.

    342 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • AI Research Radar

    infometa/workbuddyskills

    定时任务:每日研究简报。漏掉重要论文和行业报告?每天帮你盯着,关键信息一条不漏 This skill should be used when the user asks about 定时任务:每日研究简报.

    342 GitHub stars~438 tokensUpdated yesterday
    Auto-check passed
  • Check Deck

    infometa/workbuddyskills

    Investment banking presentation quality checker. An agent skill from infometa/workbuddyskills.

    342 GitHub stars~687 tokensUpdated yesterday
    Auto-check passed
  • Cos Vectors

    infometa/workbuddyskills

    腾讯云 COS 向量桶全功能管理技能。覆盖向量桶、索引、向量数据的全生命周期管理,包括创建/删除/查询向量桶、创建/管理索引、插入/查询/搜索/删除向量数据、策略管理等 16 个核心能力。Trigger phrases: vector bucket, vector index, vector search, 向量桶, 向量索引, 向量搜索, 向量存储, 插入向量, 相似度搜索, COS…

    342 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed

Questions about Agent Browser

What does Agent Browser do?

A skill your agent uses when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows. Agent Browser is an agent skill from infometa/workbuddyskills. Use this skill when the user needs browser automation, including opening web pages, taking screenshots, extracting page content, clicking elements, filling forms, or testing web flows.

When should I use Agent Browser?

Agent Browser fits situations like: the user needs browser automation; including opening web pages; taking screenshots; extracting page content.

How do I install Agent Browser in Claude Code?

Run `npx skills add infometa/workbuddyskills --skill agent-browser -a claude-code`. Or copy the skill folder (plugins/codebuddy-plugins-official/plugins/agent-browser in infometa/workbuddyskills) into .claude/skills/agent-browser in your project. Claude Code loads it when a task matches its description.

How do I install Agent Browser in Codex?

Run `npx skills add infometa/workbuddyskills --skill agent-browser -a codex`. Or copy the skill folder (plugins/codebuddy-plugins-official/plugins/agent-browser in infometa/workbuddyskills) into .agents/skills/agent-browser in your project. Codex loads it when a task matches its description.

Can I use Agent Browser 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 infometa/workbuddyskills --skill agent-browser -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-browser, .gemini/skills/agent-browser, .github/skills/agent-browser and .opencode/skills/agent-browser in your project.

What does Agent Browser need to run?

Going by SKILL.md and its folder, Agent Browser needs a shell and PowerShell for the scripts in its folder and the command-line tools its instructions call (npm, node, npx and curl). Our summary lists: Node.js; A Bash shell; PowerShell.

Does Agent Browser access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Agent Browser safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agent Browser use?

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

How many tokens does Agent Browser use?

About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1k tokens, read only when the agent opens those files.

What are the alternatives to Agent Browser?

Skills that share tags, products or a category with Agent Browser: Browser MCP Agent (antibrow/anti-detect-browser-skills, 914 stars), Drive Screen (coleam00/skills, 670 stars), Computer Use (xuzhougeng/wisp-science, 1k stars) and Vercel Token Setup (vellum-ai/vellum-assistant, 1.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Browser?

infometa (a GitHub user) maintains it in infometa/workbuddyskills, which has 342 GitHub stars. The repository holds 235 skills in this directory. The repository was last updated on October 6, 2026.

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