agent-browser

A command-line browser automation tool for AI agents. It can control Chrome or Chromium through page navigation, accessible element references, form entry, clicks, screenshots, and data extraction.

In plain words
What is it for?
Use it to test web apps, fill in online forms, navigate sites, capture screenshots, or extract information from pages. Specialized workflows also cover Electron apps, Slack, and exploratory testing.
Why use it?
It lets an agent work with real websites and web applications instead of only reading source code. Accessibility-tree snapshots provide a compact way to identify page elements.

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/tam159/next-role/agent-browser
Any agent
npx skills add tam159/next-role --skill agent-browser
Clone the repo
git clone --depth 1 https://github.com/tam159/next-role

Made for: Claude Code, Codex.

Per session 200 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 620 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00200 $0.00620
Opus 5 $0.00100 $0.00310
Sonnet 5 $0.00040 $0.00124
Haiku 4.5 $0.00020 $0.00062

Measured yesterday against content hash 47bbe450ca09, 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 yesterday.

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.

Origin

This is a copy

86% identical to agent-browser — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/agent-browser/SKILL.md · 52 lines

What it actually says

agent-browser

Fast browser automation CLI for AI agents. Chrome/Chromium via CDP with accessibility-tree snapshots and compact @eN element refs.

The CLI is already installed on this machine. Do not run npm i -g agent-browser or agent-browser install.

Start here

This file is a discovery stub, not the usage guide. Before running any agent-browser command, load the actual workflow content from the CLI:

agent-browser skills get core             # start here — workflows, common patterns, troubleshooting
agent-browser skills get core --full      # include full command reference and templates

The CLI serves skill content that always matches the installed version, so instructions never go stale. The content in this stub cannot change between releases, which is why it just points at skills get core.

Specialized skills

Load a specialized skill when the task falls outside browser web pages:

agent-browser skills get electron          # Electron desktop apps (VS Code, Slack, Discord, Figma, ...)
agent-browser skills get slack             # Slack workspace automation
agent-browser skills get dogfood           # Exploratory testing / QA / bug hunts
agent-browser skills get vercel-sandbox    # agent-browser inside Vercel Sandbox microVMs
agent-browser skills get agentcore         # AWS Bedrock AgentCore cloud browsers

Run agent-browser skills list to see everything available on the installed version.

Why agent-browser

  • Fast native Rust CLI, not a Node.js wrapper
  • Works with any AI agent (Cursor, Codex, Codex, Continue, Windsurf, etc.)
  • Chrome/Chromium via CDP with no Playwright or Puppeteer dependency
  • Accessibility-tree snapshots with element refs for reliable interaction
  • Sessions, authentication vault, state persistence, video recording
  • Specialized skills for Electron apps, Slack, exploratory testing, cloud providers
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. yesterday First seen · 52 lines · 200 tokens per session scan A 47bbe450ca09

Subscribe to this mod's changes

agent-browser is a skill published in the GitHub repository tam159/next-role (48 stars, last pushed 2d ago), licensed MIT. It adds 200 tokens to every session and 620 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to agent-browser, differing in 22 lines, and is treated as a copy.

Related

Other skills, from other repositories

textual-screenshot

Capture a Textual terminal UI as an SVG using its headless test harness. Use when asked to make, attach, or preview a screenshot of deepagents-code/dcode or another Textual app, visually verify a TUI state, or render a modal, screen, or widget without a desktop or browser.

langchain-ai/deepagents · 67 tokens

scrape

Finds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with /add-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, /scrape.

MadsLorentzen/ai-job-search · 67 tokens

gsd-add-tests

Generate tests for a completed phase based on UAT criteria and implementation.

open-gsd/gsd-core · 18 tokens

best-practices

Apply modern web development best practices for security, compatibility, and code quality. Use when asked to "apply best practices", "security audit", "modernize code", "code quality review", or "check for vulnerabilities".

open-gsd/gsd-pi · 49 tokens

agentlas

Single entry point for every Agentlas command: /agentlas network, /agentlas build, /agentlas storm, /agentlas graph, /agentlas one, /agentlas upload, /agentlas cloud, /agentlas hub, /agentlas local, /agentlas browser, /agentlas call, /agentlas search, /agentlas connect.

agentlas-ai/Agentlas-OS · 77 tokens

aidd-dev:02:assert

Assert features work as intended — general assertions, architecture conformance, and frontend UI validation.

ai-driven-dev/framework · 26 tokens