hapo:agent-browser

A browser automation skill that uses compact page snapshots to help an AI operate websites. It supports long-running sessions, self-checking workflows, video recording, and cloud browser testing through Browserbase.

In plain words
What is it for?
Use it to automate browser workflows, test websites in a cloud browser, run extended sessions, verify results, and record browser activity.
Why use it?
It reduces the amount of page information the agent must process and helps verify that automated browser tasks completed correctly.

Skill for Claude CodeCodex

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.

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

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.00039 $0.02277
Opus 5 $0.00019 $0.01138
Sonnet 5 $0.00008 $0.00455
Haiku 4.5 $0.00004 $0.00228

Measured 2d ago against content hash a90cc03056e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

hapo: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 2d ago.

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.

packages/spec/src/claude/skills/agent-browser/SKILL.md · 301 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 2d ago First seen · 301 lines · 39 tokens per session scan A a90cc03056e2

Subscribe to this mod's changes

hapo:agent-browser is a skill published in the GitHub repository haposoft/cafekit (54 stars, last pushed 3d ago), with no licence file. It adds 39 tokens to every session and 2,277 once invoked, about $0.0002 per session on Opus 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

menu-visibility

Track which react-horizontal-scrolling-menu items are on screen: useIsVisible(itemId | 'first' | 'last', defaultValue), useLeftArrowVisible/useRightArrowVisible, the options prop (ratio, rootMargin, threshold), items.getVisible()/subscribe/unsubscribe, and the async IntersectionObserver truth model (items must be seen…

asmyshlyaev177/react-horizontal-scrolling-menu · 112 tokens

Agent Browser Automation

Fast Rust-based headless browser automation CLI with Node.js fallback for AI agents, featuring navigation, clicking, typing, snapshots, and structured commands optimized for agent workflows.

PramodDutta/qaskills · 37 tokens

Browser Automation

Use Home23's live browser controller for screenshots, navigation checks, and page extraction.

notforyou23/home23 · 20 tokens

screenclaw

用“截图 + 坐标网格”的方式操作任意桌面软件:截带网格的图,让任意多模态大模型读出目标的坐标数字,再调用点击/输入/按键等 API ,模拟人类视觉化操作软件。还能录制一次操作并沉淀成可复用的场景模板,下次直接复用。不依赖目标软件提供 API 或 CLI。 出现以下情况时使用: - 自动化操作 Windows 桌面软件(微信、风控严格的网页如小红书/抖音、手机模拟器、游戏、任意 Windows 程序),尤其是 Playwright/CDP/CLI/应用 API 无法覆盖的软件或元素(如隐藏按钮、游戏画面、验证码等) - 用户说“帮我操作/点/输入 XX”“自动操作…

GinSing1226/ScreenClaw · 298 tokens

fuse-browser-usage

Use when about to call any mcpfuse-browser tool. Routes fetch/crawl/SERP vs live browser session vs screenshot capture, and enforces the 4 ZERO-TOLERANCE rules -- read BEFORE the tool call.

fusengine/agents · 55 tokens

guide

Open the showreel visual setup guide, or walk the user through installing the plugin's dependencies. Use when the user asks how to set up showreel, install its dependencies, pre-warm the capture motor, install vhs, or says "showreel guide", "setup guide", "como instalar o showreel".

HeyRenan/showreel · 70 tokens