browseros-neo

A persistent browser for agents with the user's saved logins and active accounts. It is intended for website tasks that require a real browser session.

In plain words
What is it for?
Opening, reading, and using websites; filling forms; signing in when needed; downloading files; and verifying results.
Why use it?
It lets agents use authenticated websites without asking the user to sign in again for every task.

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/browseros-ai/browseros/browserclaw
Any agent
npx skills add browseros-ai/BrowserOS --skill browserclaw
Clone the repo
git clone --depth 1 https://github.com/browseros-ai/BrowserOS

Made for: Claude Code, Codex.

Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 717 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 $0.00119 $0.00717
Opus 5 $0.00060 $0.00358
Sonnet 5 $0.00024 $0.00143
Haiku 4.5 $0.00012 $0.00072

Measured 3d ago against content hash a9799eef96e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

browseros-neo 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.

packages/browseros-agent/resources/skills/browserclaw/SKILL.md · 44 lines

The source is not reproduced here

Licensed AGPL-3.0

The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

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 · 44 lines · 119 tokens per session scan A a9799eef96e3

Subscribe to this mod's changes

browseros-neo is a skill published in the GitHub repository browseros-ai/BrowserOS (13,451 stars, last pushed today), licensed AGPL-3.0. It adds 119 tokens to every session and 717 once invoked, about $0.0006 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

browser

Automate web browsers — navigate sites, fill forms, click buttons, extract data, take screenshots, and run multi-step web workflows.

thewolffish/wolffish-app · 28 tokens

web-navigator

Web 浏览器自动化路由规则。通过 webnavigator 将 Web 场景路由到 Playwright MCP 或 mcp-chrome。.

Plocr/Reasonix-computer-use · 30 tokens

browser-extension

Open, read and drive any web page in the user's real browser — logins, paywalls and JS-heavy sites included. Reaches what webfetch cannot, and acts as well as reads — navigate, click, fill forms, screenshot, scrape, manage tabs, run JavaScript. Chrome, Edge, Brave, Firefox, several at once.

thewolffish/wolffish-app · 72 tokens

agent-computer-use

REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the agent-cu CLI commands (open, snapshot, click, type, key…

kortix-ai/agent-computer-use · 216 tokens

computer-use

Desktop automation — see the screen and control mouse/keyboard with a verified-aim loop. Screenshots, native-resolution zoom for precise targeting, clicks that return a magnified proof of where they landed, typing, shortcuts, scrolling, drag-and-drop.

thewolffish/wolffish-app · 53 tokens

jina-reader

Fetch a webpage as clean, structured Markdown via the jina.ai reader (r.jina.ai) instead of raw HTML — use whenever you need to read web content and want to save tokens, or when a normal fetch is blocked (HTTP 403/401), returns messy/boilerplate HTML, or the page is JavaScript-rendered (SPA, docs sites, wikis like…

Hawkynt/ClaudeCodePortable · 132 tokens