using-fleet-browser

using-fleet-browser is a skill for Claude Code, Codex from metahub-tech/agent-fleet. It costs 93 tokens per session (1,791 once invoked), scanned A, original, Apache-2.0.

Instructions for controlling a real Chrome browser on a remote agent-fleet computer through Playwright, a browser automation tool. It covers navigating pages, reading content, entering data, clicking controls, and end-to-end testing.

In plain words
What is it for?
Use it to inspect websites, automate browser tasks, collect page information, or run end-to-end tests through an isolated browser profile.
Why use it?
It explains which browser setup to use and what it can safely access, especially when automation traces or separate browser profiles matter.

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/metahub-tech/agent-fleet/using-fleet-browser
Any agent
npx skills add metahub-tech/agent-fleet --skill using-fleet-browser
Clone the repo
git clone --depth 1 https://github.com/metahub-tech/agent-fleet

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 using-fleet-browser

README.md
[![agentmods](https://agentmods.dev/badge/skills/metahub-tech/agent-fleet/using-fleet-browser.svg)](https://agentmods.dev/skills/metahub-tech/agent-fleet/using-fleet-browser)
Your own site
<a href="https://agentmods.dev/skills/metahub-tech/agent-fleet/using-fleet-browser"><img src="https://agentmods.dev/badge/skills/metahub-tech/agent-fleet/using-fleet-browser.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,791 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 $0.00093 $0.01791
Opus 5 $0.00046 $0.00896
Sonnet 5 $0.00019 $0.00358
Haiku 4.5 $0.00009 $0.00179

Measured 3d ago against content hash 77d4b7ffa716, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

using-fleet-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.

platforms/common/skills/using-fleet-browser/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Using agent_browser

agent_browser is a proxied capability: an agent-fleet device server (e.g. mac-device) grafts Playwright MCP and drives real, headed Chrome on that host. Discover it via list_capabilities (origin proxied, status enabled); load the tools you need by name.

agent-fleet never runs headless — each browser is a real window on the host's GUI session, suitable for end-to-end testing. (It drives via CDP, so it does NOT need the screen to be awake.)

agent_browser vs human_browser (routing)

  • agent_browser (this skill): DOM/semantic control via Playwright. Fast, precise, token-efficient. Has automation traces (CDP / navigator.webdriver) and runs in an isolated profile (~/.fleet/agent-browser-profile, NOT the user's identity/login). Use for: end-to-end web testing, scraping/reading, browsing to learn, automation where traces are fine.
  • human_browser (separate capability): drives the host's real Chrome via OS-level input, zero automation traces, real logged-in identity; page localization via human_dom (DOM-precise) or screenshots. Use when acting as the human on real accounts.

★ Rule — real accounts → human_browser + human_dom, NEVER agent_browser (even to "just check"): if you log into a real account here in agent_browser, the login lands in the isolated profile, invisible to human_browser — so the operator's later human_browser runs are logged out and re-login forever (a real bug we hit). For a real account/identity, use human_browser + human_dom from the first navigation through every op (human_dom gives agent_browser-grade DOM precision without the traces; see using-human-browser / using-human-dom). agent_browser is for non-identity work on throwaway/isolated profiles.

Multi-profile + lease model (IMPORTANT — read before driving)

agent_browser supports multiple profiles running truly in parallel — each profile is a separate Chrome (own user-data-dir, own state/cookies/tabs). Every browser_* tool takes two extra params:

Read the full file on GitHub · 80 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 · 80 lines · 93 tokens per session scan A 77d4b7ffa716

Subscribe to this mod's changes

using-fleet-browser is a skill published in the GitHub repository metahub-tech/agent-fleet (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,791 once invoked, about $0.0005 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

bootstrap-repo-analysis

First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…

langchain-ai/open-swe · 73 tokens

browserwing-executor

Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.

MemTensor/MemOS · 42 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"…

MemTensor/MemOS · 84 tokens

browse

Use the browse CLI for Browserbase browser automation, Browserbase cloud APIs, Browserbase Functions, templates, web fetch/search, diagnostics, and Browse.sh skill discovery/installation. Use when the user asks to navigate pages, inspect browser state, run local or remote browser sessions, manage Browserbase…

rivet-dev/agentos · 109 tokens

browserwing-admin

Manage and operate BrowserWing — an intelligent browser automation platform. Install dependencies, configure LLM, create/manage/execute automation scripts, use AI-driven exploration to generate scripts, browse the script marketplace, and troubleshoot issues.

MemTensor/MemOS · 47 tokens

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

Intelligent-Internet/ii-agent · 108 tokens