agent-browser

agent-browser is a skill for Claude Code, Codex from S3YED/appie-kit. It costs 69 tokens per session (543 once invoked), scanned A, original, MIT.

A command-line tool for controlling web browsers with compact text output designed for AI agents. It supports navigation, forms, screenshots, network controls, and other browser actions using stable references to page elements.

In plain words
What is it for?
Use it to navigate websites, inspect pages, submit forms, capture screenshots, control network requests, and test browser-based applications from a shell.
Why use it?
It gives an agent the information needed for browser tasks without returning the entire page structure, which can be difficult to read. References help actions target the exact link, button, or field found in the page snapshot.

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/s3yed/appie-kit/agent-browser
Any agent
npx skills add S3YED/appie-kit --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/S3YED/appie-kit

Made for: Claude Code, Codex.

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/s3yed/appie-kit/agent-browser.svg)](https://agentmods.dev/skills/s3yed/appie-kit/agent-browser)
Your own site
<a href="https://agentmods.dev/skills/s3yed/appie-kit/agent-browser"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/agent-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 543 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00069 $0.00543
Opus 5 $0.00034 $0.00271
Sonnet 5 $0.00014 $0.00109
Haiku 4.5 $0.00007 $0.00054

Measured 3d ago against content hash a07edc80f057, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

skills/automation/agent-browser/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-browser - fleet default for browser automation

A native-Rust browser-automation CLI designed for AI agents. Compact text output minimises context usage. Use it instead of heavier browser stacks for shell-driven web tasks.

Install

npm install -g agent-browser      # all platforms
# or: brew install agent-browser  # macOS
agent-browser install             # download Chrome (first run only)
# try without installing:
npx agent-browser open example.com

Core loop (ref-based)

agent-browser open example.com
agent-browser snapshot -i          # accessibility tree with refs: heading "..." [ref=e1], link "..." [ref=e2]
agent-browser click @e2            # act on a ref from the snapshot
agent-browser screenshot page.png
agent-browser close

Why refs (the context win)

snapshot returns a compact accessibility tree where each element has a ref (@e1, @e2):

  • Context-efficient: ~200-400 tokens vs ~3000-5000 for full DOM.
  • Deterministic: a ref points to the exact element from the snapshot (no fragile selectors).
  • Fast: no DOM re-query. AI-friendly: text output parses naturally.

What it covers (50+ commands)

Navigation, forms, screenshots, network control, storage/cookies/auth-state, file upload/download, tabs, frames, debugging. Built-in: video recording, streaming, profiler, diffing. First-class docs for React/Web Vitals, init scripts, and Next.js + Vercel. Stateful: sessions, profiles, proxy, security controls - good for long-running agents.

Architecture

Client-daemon: a Rust CLI talks to a native Rust daemon that drives Chrome over CDP. The daemon starts automatically and persists between commands.

When to use vs other tools

  • Default for shell-driven browser work (cheapest context, deterministic).
  • Use Playwright/Stagehand only when you need their specific ecosystem features.
  • Cross-platform: macOS (arm64/x64), Linux (arm64/x64), Windows (x64).

Works with: Claude Code, Cursor, Copilot, Codex, Gemini, opencode, and any agent that runs shell commands.

Read the full file on GitHub · 46 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. 3d ago First seen · 46 lines · 69 tokens per session scan A a07edc80f057

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 8d ago), licensed MIT. It adds 69 tokens to every session and 543 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

jni-type-conversion

How to use @JniType annotations for ergonomic JNI. Relevant for Java files that use @NativeMethods or @CalledByNative.

chromium/chromium · 32 tokens

lint-sync

Add missing LINT.IfChange(...) / LINT.ThenChange(...) guards to enums in C++/Java and XML to keep them in sync. Trigger this skill ONLY when a contributor explicitly asks to add lint guards or synchronize enums using LINT guards.

chromium/chromium · 53 tokens

dev-browser

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website"…

SawyerHood/dev-browser · 84 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

behat-skill

Generates Behat BDD tests for PHP with Gherkin feature files and MinkContext for browser testing. Use when user mentions "Behat", "PHP BDD", "Mink", "behat.yml". Triggers on: "Behat", "PHP BDD", "Mink", "behat.yml", "FeatureContext PHP".

LambdaTest/agent-skills · 76 tokens

laravel-dusk-skill

Generates Laravel Dusk browser tests in PHP. Chrome-based E2E testing for Laravel apps. Use when user mentions "Dusk", "Laravel Dusk", "$browser->visit", "DuskTestCase". Triggers on: "Laravel Dusk", "Dusk test", "$browser->visit", "DuskTestCase".

LambdaTest/agent-skills · 76 tokens