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.
npx skills add oxylabs/agent-skills --skill agent-browsergit clone --depth 1 https://github.com/oxylabs/agent-skillsWrote 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.
[](https://agentmods.dev/skills/oxylabs/agent-skills/agent-browser)<a href="https://agentmods.dev/skills/oxylabs/agent-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/oxylabs/agent-skills/agent-browser/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/oxylabs/agent-skills/agent-browser"><img src="https://agentmods.dev/badge/skills/oxylabs/agent-skills/agent-browser.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00156 | $0.04047 |
| Opus 5.5 | $0.00062 | $0.01619 |
| Sonnet 5.5 | $0.00031 | $0.00809 |
| Haiku 4.5 | $0.00016 | $0.00405 |
Grade A, and why
agent-browser 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`new URL()` or `urllib.parse`: they percent-encode the password and authentication fails. How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oxylabs Agent Browser
Remote Chrome sessions in a managed browser environment with proxy rotation and geo-targeting built in.
Nothing runs locally: you connect over a WebSocket, drive the browser with the CDP library you already
use, and close the session when done. This file holds the rules; the detail lives next to it:
scripts/ (copyable templates), parameters.md, errors.md, examples.md, targets.md, challenges.md.
1. Connect
| Item | Value |
|---|---|
| Endpoint | wss://USERNAME:[email protected] |
| Credentials | OXY_AB_USERNAME / OXY_AB_PASSWORD |
| Options | URL query parameters only, e.g. ?p_cc=US&session_name=job-42 (see parameters.md) |
| Browser engine | Default engine with the oxyfp_win browser profile; p_src=oxybrowser selects the new engine (see parameters.md) |
| Libraries | Playwright chromium.connectOverCDP (recommended), Puppeteer puppeteer.connect, any CDP client |
| Dashboard / support | https://hb.oxylabs.io/dashboard · [email protected] |
Rules that prevent the most common 401:
- Use
wss://. Plainws://is accepted but sends your password unencrypted. - Build the URL by string concatenation with the raw password. Do not pass the finished URL through
new URL()orurllib.parse: they percent-encode the password and authentication fails. - Use the full username exactly as shown in the dashboard, including any suffix such as
_ab12. - A password containing
:cannot be sent in the URL. Ask for a new password or send theAuthorization: Basicheader yourself (seeexamples.md). - Authentication is checked before parameters: fix a
401before looking at anything else.
2. Quick start
Minimal shape (Playwright, JavaScript):
const { chromium } = require("playwright");
const url = `wss://${process.env.OXY_AB_USERNAME}:${process.env.OXY_AB_PASSWORD}@hb.oxylabs.io?p_cc=US`;
const browser = await chromium.connectOverCDP(url, { timeout: 60000 });
try {
const page = await browser.contexts()[0].newPage(); // default context: backed by the device configuration, proxy, o_profile
await page.goto("https://example.com", { waitUntil: "domcontentloaded", timeout: 30000 });
console.log(await page.content());
} finally {
await browser.close(); // always: an unclosed session keeps its concurrency slot
}
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago Changed · +44 lines · +41 tokens per session 3c39a3abf5cc
- 20d ago First seen · 180 lines · 115 tokens per session scan A 90e3bbdce3a6
agent-browser is a skill published in the GitHub repository oxylabs/agent-skills (876 stars, last pushed 5d ago), licensed MIT. It adds 156 tokens to every session and 4,047 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-10-01.
Other skills, from other repositories
safari-extension-control-workflow
Guide macOS Safari integration decisions across Safari Web Extensions, Safari Web Inspector Extensions, Safari App Extensions, SafariServices APIs, content blockers, extension messaging, and app-to-Safari control surfaces. Use when the user wants a Mac app to extend, message, open, inspect, debug, or coordinate with…
safari-mcp-workflow
Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
nexus-browser-fleet
Headless browser fleet orchestration and management. Use when you need to coordinate multiple headless browser instances for automated web auditing, scraping, or testing at scale using tools like Pinchtab. Detects and corrects unstable fleets that fail audit coverage.
add-tavily-tool
Add Tavily Search and Extract as keyless remote MCP tools for selected NanoClaw agent groups. Use when installing Tavily web search or URL extraction without an API key.
skill-zhihu-answer
An automation workflow for publishing original answers on Zhihu, a Chinese question-and-answer website. It can search for suitable questions, check whether an answer can be posted, and publish the response through a browser.
skill-xhs-publisher
A browser-based publisher for posting image-and-text notes or videos to Xiaohongshu, a Chinese social media platform. It supports saved login sessions and checks that uploads and publishing complete.