What is on-device-browser-agent CLAUDE.md?

Project instructions for Nanobrowser, an open-source browser extension that runs AI web automation locally and supports several AI providers.

Use them when developing, checking, building, testing, or packaging the Nanobrowser Chrome extension.

They give coding agents the required package manager, development commands, build checks, and testing workflow for the extension.

How RunanywhereAI/on-device-browser-agent configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to RunanywhereAI/on-device-browser-agent. 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/RunanywhereAI/on-device-browser-agent/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/RunanywhereAI/on-device-browser-agent

Made for: Claude Code.

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/runanywhereai/on-device-browser-agent/claude-md/github.svg)](https://agentmods.dev/instructions/runanywhereai/on-device-browser-agent/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/runanywhereai/on-device-browser-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/runanywhereai/on-device-browser-agent/claude-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/runanywhereai/on-device-browser-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/runanywhereai/on-device-browser-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 2,693 This file is loaded in full into every session.

When invoked 2,693 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 100% copy Near-identical to another mod 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	$0.02693	$0.02693
Opus 5.5	$0.01077	$0.01077
Sonnet 5.5	$0.00539	$0.00539
Haiku 4.5	$0.00269	$0.00269

Measured 2mo ago against content hash 599d49d95a80, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

on-device-browser-agent CLAUDE.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 2mo 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

This is a copy

100% identical to nanobrowser CLAUDE.md — 293 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 292 lines

How it starts

The opening of the file, as written. The whole thing — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to AI coding assistants (e.g., Claude Code, GitHub Copilot, Cursor) when working with this repository.

Project Overview

Nanobrowser is an open-source AI web automation Chrome extension that runs multi-agent systems locally in the browser. It's a free alternative to OpenAI Operator with support for multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, etc.).

Development Commands

Package Manager: Always use pnpm (required, configured in Cursor rules)

Core Commands:

pnpm install - Install dependencies
pnpm dev - Start development mode with hot reload
pnpm build - Build production version
pnpm type-check - Run TypeScript type checking
pnpm lint - Run ESLint with auto-fix
pnpm prettier - Format code with Prettier

Testing:

pnpm e2e - Run end-to-end tests (builds and zips first)
pnpm zip - Create extension zip for distribution
pnpm -F chrome-extension test - Run unit tests (Vitest) for core extension
- Targeted example: pnpm -F chrome-extension test -- -t "Sanitizer"

Workspace Tips

Scope tasks to a single workspace to speed up runs:
- pnpm -F chrome-extension build
- pnpm -F packages/ui lint
Prefer workspace-scoped commands over root-wide runs when possible.

Targeted examples (fast path):

pnpm -F pages/side-panel build — build only the side panel
pnpm -F chrome-extension dev — dev-watch background/service worker
pnpm -F packages/storage type-check — TS checks for storage package
pnpm -F pages/side-panel lint -- src/components/ChatInput.tsx — lint a file
pnpm -F chrome-extension prettier -- src/background/index.ts — format a file

Cleaning:

pnpm clean - Clean all build artifacts and node_modules
pnpm clean:bundle - Clean just build outputs
pnpm clean:turbo - Clear Turbo state/cache
pnpm clean:node_modules - Remove dependencies in current workspace
pnpm clean:install - Clean node_modules and reinstall dependencies
pnpm update-version - Update version across all packages

Read the full file on GitHub · 292 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.

2mo ago First seen · 292 lines · 2,693 tokens per session scan A 599d49d95a80

Subscribe to this mod's changes

on-device-browser-agent CLAUDE.md is an instructions file published in the GitHub repository RunanywhereAI/on-device-browser-agent (305 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,693 tokens to every session, about $0.0108 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to nanobrowser CLAUDE.md, differing in 293 lines, and is treated as a copy.

on-device-browser-agent CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
on-device-browser-agent CLAUDE.mdRunanywhereAI/on-device-browser-agent	Instructions file	305	1mo ago	Apache-2.0	A	2,693	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

on-device-browser-agent: Instructions file for Claude Code