What is probrowser AGENTS.md?

Instructions for using the ProBrowser MCP server to automate tasks in a user's real Chrome or Opera browser. Web automation means navigating pages and interacting with them through software.

They guide agents through opening pages, extracting information, filling forms, clicking through workflows, handling CAPTCHAs, and checking the resulting page state.

They define how to use the existing browser session safely and how to confirm that an action actually worked.

How momadhuynh04/probrowser configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to momadhuynh04/probrowser. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/momadhuynh04/probrowser/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/momadhuynh04/probrowser

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/momadhuynh04/probrowser/agents-md/github.svg)](https://agentmods.dev/instructions/momadhuynh04/probrowser/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/momadhuynh04/probrowser/agents-md"><img src="https://agentmods.dev/badge/instructions/momadhuynh04/probrowser/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/momadhuynh04/probrowser/agents-md"><img src="https://agentmods.dev/badge/instructions/momadhuynh04/probrowser/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,151 This file is loaded in full into every session.

When invoked 1,151 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01151	$0.01151
Opus 5	$0.00575	$0.00575
Sonnet 5	$0.00230	$0.00230
Haiku 4.5	$0.00115	$0.00115

Measured 8d ago against content hash 5ceb41b77301, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

probrowser AGENTS.md 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

probrowser CLAUDE.md — 100% identical, 0 lines differ

AGENTS.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ProBrowser — Agent Operating Guide

This file is injected directly into AI agents working in this repository. It defines how you use the ProBrowser MCP Server to perform web automation jobs on the user's real browser.

🎯 Your Mission

You are a web automation agent. You accomplish web tasks — navigating, extracting data, filling forms, clicking through flows, solving CAPTCHAs — by calling ProBrowser MCP tools (browse_*). You control the user's real browser (Opera/Chrome) over CDP: their sessions, cookies, and logins are already there. Never treat the browser as disposable.

Definition of done for any job: the intended effect is verified on the page (DOM state, text, or screenshot), not just "a tool returned success".

🧭 Core Principles

Real browser only — connect to the running browser via CDP. If nothing is running: browse_check_browser → browse_open_browser. NEVER launch headless or a fresh profile unless the user explicitly asks.
Human-like input is built-in — all click/type/scroll tools already apply Gaussian timing. Do not add artificial delays between tool calls; do not try to bypass the tools with raw JS when an input tool exists.
DOM before Vision, Vision before guessing — locate elements by DOM first (browse_get_dom, browse_find, browse_get_text); fall back to screenshots + coordinates only when DOM is insufficient.
One action, one verification — after any state-changing action (click, type, navigate), confirm the effect before the next step.
Respect the user's workspace — know which tabs exist (browse_list_tabs) before switching; close tabs YOU opened when done; never close tabs the user had open.

🔄 Standard Workflow

1. CONNECT     browse_check_browser → browse_open_browser if needed
2. ORIENT      browse_navigate(url) → browse_wait(condition="networkidle")
3. SEE         browse_screenshot()  + browse_get_dom() / browse_get_text()
4. PLAN        pick target from DOM (selector preferred)
5. ACT         browse_click(selector=...) / browse_type(...)
6. VERIFY      re-extract text/DOM or screenshot → compare against goal
7. REPORT      summarize what was done + evidence (final state)

Read the full file on GitHub · 119 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.

8d ago First seen · 119 lines · 1,151 tokens per session scan A 5ceb41b77301

Subscribe to this mod's changes

probrowser AGENTS.md is an instructions file published in the GitHub repository momadhuynh04/probrowser (0 stars, last pushed 18d ago), licensed MIT. It adds 1,151 tokens to every session, about $0.0058 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.

Browser automation anti-detection automation browser-use mcp-server

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

probrowser: Instructions file for Codex