mcp-camoufox: Instructions file for Codex

AGENTS.md

mcp-camoufox AGENTS.md is an instructions file for Codex, OpenCode from RobithYusuf/mcp-camoufox. It costs 4,338 tokens per session, scanned A, original, MIT.

A development guide for mcp-camoufox, an MCP server that gives an AI agent browser-control tools through Camoufox, a Firefox-based browser designed to reduce browser fingerprinting.

In plain words
What is it for?
Use it when developing or debugging Camoufox browser tools, shared browser state, page handling, screenshots, clicks, forms, paths, or authentication helpers.
Why use it?
It documents the repository structure, workflow, and constraints needed to change this browser server without breaking its architecture.

Instructions file for CodexOpenCode

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

This is RobithYusuf/mcp-camoufox's own configuration. It tells Codex and OpenCode how to work on mcp-camoufox 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 mcp-camoufox configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RobithYusuf/mcp-camoufox. 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/RobithYusuf/mcp-camoufox/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/RobithYusuf/mcp-camoufox

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 mcp-camoufox AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/robithyusuf/mcp-camoufox/agents-md.svg)](https://agentmods.dev/instructions/robithyusuf/mcp-camoufox/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/robithyusuf/mcp-camoufox/agents-md"><img src="https://agentmods.dev/badge/instructions/robithyusuf/mcp-camoufox/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,338 This file is loaded in full into every session.
When invoked 4,338 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 $0.04338 $0.04338
Opus 5 $0.02169 $0.02169
Sonnet 5 $0.00868 $0.00868
Haiku 4.5 $0.00434 $0.00434

Measured 7d ago against content hash c52897be269e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-camoufox 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 7d 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 · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-camoufox — Agent Guide

This guide applies to the entire repository and is the shared source of instructions for coding agents. Its purpose is not to govern every decision, but to preserve the workflows and invariants that are easy to miss — most of them were learned from a shipped bug. Developer requests may override working defaults; hard constraints may only be overridden when the developer explicitly asks for it.

Product and repository map

An MCP server (stdio JSON-RPC) that gives an agent a stealth browser: 133 tools over Camoufox, a Firefox build with C++-level anti-fingerprinting. Published on npm as mcp-camoufox.

npx -y mcp-camoufox → Node → camoufox-js → Playwright (Juggler) → Camoufox Firefox
                           └→ impit (Firefox JA4 TLS) → browserless HTTP path
  • src/index.ts — entry: connects stdio, imports the tool modules.
  • src/state.ts — the single mutable record S, page bookkeeping, shared capture buffers.
  • src/helpers.ts — refs, clicks, fills, snapshots, paths, TOTP.
  • src/server.ts — the McpServer instance and the regTool registry.
  • src/tools/*.ts — the tools, grouped by area; each registers itself on import.
  • scripts/test/ — the regression suites; scripts/*.mjs — release checks.
  • docs/TOOLS.md — the authoritative tool reference. README.md — the summary and the pitch.
  • docs/images/ — proof screenshots.
  • Runtime data lives outside the repo: ~/.camoufox-mcp/{profile,screenshots,sessions}.

Hard constraints

  • Never commit or print a credential. The npm token is set into ~/.npmrc immediately before npm publish and deleted immediately after; .npm-token and *.tgz stay ignored.
  • Never publish from the working tree alone. A release is only verified once npm run smoke:install has installed the published package and driven a real browser.
  • playwright-core must stay pinned <1.61.0. Playwright 1.61+ sends isMobile in Browser.setDefaultViewport, which Camoufox's Juggler schema rejects, and camoufox-js declares the peer as "*". Unpinning breaks browser_launch for every fresh install while this tree keeps working.
  • Do not weaken a security property to make a test pass: secret field values never leave the browser, credential files are written 0600, name parameters never escape their directory, and browser cookies are recomputed per redirect hop.
  • Do not add a tool that can fail silently. If an action may not have taken effect, the response says so — see the click/wait invariants below.
  • reset_profile, browser_recover and anything that deletes a profile need an explicit request; the shared profile holds the developer's real logins.

Read the full file on GitHub · 250 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. 7d ago First seen · 250 lines · 4,338 tokens per session scan A c52897be269e

Subscribe to this mod's changes

mcp-camoufox AGENTS.md is an instructions file published in the GitHub repository RobithYusuf/mcp-camoufox (19 stars, last pushed 18d ago), licensed MIT. It adds 4,338 tokens to every session, about $0.0217 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

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 · 5,182 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

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

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

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