browser-ops

browser-ops is a skill for Claude Code, Codex from buildoak/fieldwork-skills. It costs 29 tokens per session (5,125 once invoked), scanned A, original, Apache-2.0.

A browser-automation guide for controlling Chrome or Chromium with Playwright, a tool that performs actions such as opening pages, clicking controls, and reading content.

In plain words
What is it for?
Use it to navigate websites, fill forms, click elements, inspect page content, manage browser sessions, and automate workflows that require a browser login.
Why use it?
It lets an AI coding tool test or operate websites through a real browser instead of relying only on direct code or HTTP requests. It also explains common web concepts such as the page structure and login authorization.

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/buildoak/fieldwork-skills/browser-ops
Any agent
npx skills add buildoak/fieldwork-skills --skill browser-ops
Clone the repo
git clone --depth 1 https://github.com/buildoak/fieldwork-skills

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 browser-ops

README.md
[![agentmods](https://agentmods.dev/badge/skills/buildoak/fieldwork-skills/browser-ops.svg)](https://agentmods.dev/skills/buildoak/fieldwork-skills/browser-ops)
Your own site
<a href="https://agentmods.dev/skills/buildoak/fieldwork-skills/browser-ops"><img src="https://agentmods.dev/badge/skills/buildoak/fieldwork-skills/browser-ops.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00029 $0.05125
Opus 5 $0.00015 $0.02563
Sonnet 5 $0.00006 $0.01025
Haiku 4.5 $0.00003 $0.00513

Measured 5d ago against content hash 65d0fd565323, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

browser-ops scanned grade A with 1 finding 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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/agentmail.sh, scripts/browser-check.sh, scripts/mailbox.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**Rule of thumb:** If you can get the data with `curl`, you don't need a browser.
skills/browser-ops/SKILL.md · 431 lines

How it starts

The opening of the file, as written. The whole thing — 431 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Browser Ops

Browser automation via agent-browser. 25 tools wrapping Playwright for navigation, interaction, observation, and session management. Validated on two benchmark suites: 12/15 pass on a 15-task suite (100% excluding external blockers), 9/10 on a 10-task progressive suite. Standout: Notion end-to-end signup with AgentMail OTP verification.

Terminology used in this file:

  • Playwright: A browser automation framework that lets tools control Chromium/Chrome.
  • a11y tree: The accessibility tree (screen-reader-friendly page structure) used by browser_snapshot.
  • DOM: Document Object Model, the browser's structured representation of page elements.
  • CSS selector: A rule for targeting specific DOM elements (for example .price or #submit).
  • OAuth: A standard login/authorization flow that redirects through an identity provider (for example, "Sign in with GitHub").

Setup

npm install -g @anthropic-ai/agent-browser
agent-browser start
  • Claude Code: copy this skill folder into .claude/skills/browser-ops/
  • Codex CLI: append this SKILL.md content to your project's root AGENTS.md

For the full installation walkthrough (prerequisites, verification, troubleshooting), see references/installation-guide.md.

Staying Updated

This skill ships with an UPDATES.md changelog and UPDATE-GUIDE.md for your AI agent.

After installing, tell your agent: "Check UPDATES.md in the browser-ops skill for any new features or changes."

When updating, tell your agent: "Read UPDATE-GUIDE.md and apply the latest changes from UPDATES.md."

Follow UPDATE-GUIDE.md so customized local files are diffed before any overwrite.


Quick Start

The simplest possible browser flow: navigate, inspect, capture.

browser_navigate(url="https://example.com")
browser_snapshot(mode="interactive")
browser_screenshot(path="/tmp/example.png")
browser_close()

Read the full file on GitHub · 431 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. 5d ago First seen · 431 lines · 29 tokens per session scan A 65d0fd565323

Subscribe to this mod's changes

browser-ops is a skill published in the GitHub repository buildoak/fieldwork-skills (15 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 5,125 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

x402

Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — "just use it" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing…

browser-use/browser-use · 175 tokens

browser-use

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

browser-use/browser-use · 26 tokens

remote-browser

Controls an isolated Browser Use Cloud browser from a sandboxed machine with the current Browser Use CLI.

browser-use/browser-use · 22 tokens

cloud

Documentation reference for using Browser Use Cloud — the hosted API and SDK for browser automation. Use this skill whenever the user needs help with the Cloud REST API (v2, v3, or v4), browser-use-sdk (Python or TypeScript), X-Browser-Use-API-Key authentication, cloud sessions, browser profiles, profile sync, CDP…

browser-use/browser-use · 177 tokens

opencli-browser

Use when an agent needs to drive a real Chrome window via opencli — inspect a page, fill forms, click through logged-in flows, or extract data ad-hoc. Covers the selector-first target contract, compound form fields, stale-ref handling, network capture, and the agent-native envelopes the CLI returns. Not for writing…

jackwener/OpenCLI · 80 tokens

opencli-adapter-author

Use when writing an OpenCLI adapter for a new site or adding a new command to an existing site. Guides end-to-end from first recon through field decoding, adapter coding, and verify. Replaces opencli-oneshot / opencli-explorer. For ad-hoc browser driving (no adapter), see opencli-browser instead; for a top-level…

jackwener/OpenCLI · 88 tokens