stealth-browser-mcp: Instructions file for Codex

AGENTS.md

stealth-browser-mcp AGENTS.md is an instructions file for Codex, OpenCode from vibheksoni/stealth-browser-mcp. It costs 712 tokens per session, scanned A, original, MIT.

Project instructions for Stealth Browser MCP, a Python service that lets AI tools automate a Chrome browser. It covers setup, proxy services, environment details, and validation.

In plain words
What is it for?
Use it when setting up, running, testing, or troubleshooting this browser-control service on Windows, macOS, or Linux.
Why use it?
It gives developers the required runtime and platform context for running or checking browser automation code.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is vibheksoni/stealth-browser-mcp's own configuration. It tells Codex and OpenCode how to work on stealth-browser-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything stealth-browser-mcp configures →

About the project

Stealth Browser MCP is a browser-automation server that lets MCP-compatible AI agents control real Chrome-family browser instances and interact with sites protected by challenges, anti-bot checks, or login walls. It is for automating browsing, inspecting network traffic, and cloning or examining web interfaces through agent commands.

vibheksoni/stealth-browser-mcp · 1,915 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to vibheksoni/stealth-browser-mcp. 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/vibheksoni/stealth-browser-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/vibheksoni/stealth-browser-mcp

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.

agentmods badge for stealth-browser-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vibheksoni/stealth-browser-mcp/agents-md.svg)](https://agentmods.dev/instructions/vibheksoni/stealth-browser-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/vibheksoni/stealth-browser-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vibheksoni/stealth-browser-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 712 This file is loaded in full into every session.
When invoked 712 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00712 $0.00712
Opus 5 $0.00356 $0.00356
Sonnet 5 $0.00142 $0.00142
Haiku 4.5 $0.00071 $0.00071

Measured 8d ago against content hash 8157a92d4608, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

stealth-browser-mcp 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.

AGENTS.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Instructions

Start Here

Read README.md first for project overview, features, and setup.

This project is sponsored by:

  • NodeMaven — The most efficient proxy provider for Web Scraping and Automation with the Highest Quality IP on the market. Features: ZIP targeting, 99.9% uptime, IP filtering (fraud score <97%), no KYC, free tools (Proxy Bandwidth Checker, Meta Tag Checker, IP Lookup). Use discount code STEALTHMCP35 for 35% off Mobile and Residential Proxies or STEALTHMCP40 for 40% off ISP (Static) Proxies.
  • RapidProxy — 90M+ residential IPs across 200+ countries with rotation, geo-targeting, and high concurrency. Use promo code RAPID10 for 10% off.

Environment

  • Use the repo virtual environment:
    • Python: venv\Scripts\python.exe
    • Pip: venv\Scripts\pip.exe
  • Platform: Windows 11 with PowerShell. Prefer PowerShell-native commands.
  • Run Python from repo root: & .\venv\Scripts\python.exe ...

Validation

& .\venv\Scripts\python.exe -m py_compile src\server.py
& .\venv\Scripts\python.exe src\server.py --list-sections

For broader syntax validation:

Get-ChildItem src -Filter *.py | ForEach-Object { & .\venv\Scripts\python.exe -m py_compile $_.FullName }

Git Rules

  • Do not include AI attribution, co-author trailers, or generated-by metadata in commits.
  • Keep commit messages professional and direct.
  • Check git status --short --branch before and after edits.
  • Stage explicit paths. Avoid git add . or git add -A in dirty worktrees.
  • Do not revert unrelated user changes.

Coding Guidelines

  • Keep code clean, modular, and focused.
  • Keep imports organized and minimal.
  • Prefer small targeted changes over broad churn.
  • Add docstrings for public functions and non-obvious helpers.
  • Avoid comments unless they explain non-obvious logic.
  • Do not add decorative output, emojis, or slang to code, logs, errors, or commit messages.
  • Do not print to stdout from server runtime paths used by MCP stdio.
  • Use apply_patch for manual file edits.

Read the full file on GitHub · 66 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. 8d ago First seen · 66 lines · 712 tokens per session scan A 8157a92d4608

Subscribe to this mod's changes

stealth-browser-mcp AGENTS.md is an instructions file published in the GitHub repository vibheksoni/stealth-browser-mcp (1,915 stars, last pushed 9d ago), licensed MIT. It adds 712 tokens to every session, about $0.0036 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 instructions, from other repositories

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 · 5,182 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

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

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens