browser-use: Instructions file for Claude Code

CLAUDE.md

browser-use CLAUDE.md is an instructions file for Claude Code from browser-use/browser-use. It costs 796 tokens per session, scanned A, original, MIT.

A set of instructions for working on the browser-use Python library with Claude Code. It describes the library's main parts and how they work together to control browsers through Chrome DevTools Protocol, a standard way to communicate with Chrome.

In plain words
What is it for?
It helps with changes to agents, browser sessions, browser actions, page and HTML processing, and connections to language models.
Why use it?
It gives an agent the architectural context needed to change the right component and follow the project's event-driven design. It reduces the risk of changes that conflict with browser sessions, tools, or page processing.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is browser-use/browser-use's own configuration. It tells Claude Code how to work on browser-use 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 browser-use configures →

About the project

Browser Use is a Python library and related service that lets AI agents operate websites through a browser by opening pages, clicking controls, entering text, and extracting information. Developers use it to automate online tasks such as form completion and structured data collection. The catalogue entries help coding agents set up or use Browser Use.

browser-use/browser-use · 121,333 stars · on GitHub · browser-use.com

Reuse

Borrowing it

Nothing to install: this file belongs to browser-use/browser-use. 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/browser-use/browser-use/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/browser-use/browser-use

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.

agentmods badge for browser-use CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/browser-use/browser-use/claude-md/github.svg)](https://agentmods.dev/instructions/browser-use/browser-use/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/browser-use/browser-use/claude-md"><img src="https://agentmods.dev/badge/instructions/browser-use/browser-use/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.

agentmods 80×15 button for browser-use CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/browser-use/browser-use/claude-md"><img src="https://agentmods.dev/badge/instructions/browser-use/browser-use/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 796 This file is loaded in full into every session.
When invoked 796 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 $0.00796 $0.00796
Opus 5.5 $0.00318 $0.00318
Sonnet 5.5 $0.00159 $0.00159
Haiku 4.5 $0.00080 $0.00080

Measured 7d ago against content hash c22dcac11db3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

browser-use 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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for coding agents working in this repository (AGENTS.md has the same content).

Browser Use 1.0 is a browser agent on Pydantic AI. The model does not pick one action per step from a DOM dump: it writes Python in one persistent REPL that has the browser-harness helpers and raw CDP. The 0.x public API (Agent, Browser, Tools, run(), final_result()) is kept on top; MIGRATING.md lists every 0.x option and its 1.0 answer.

Architecture

Agent(task, llm, browser).run()                  browser_use/agent/service.py   0.x API, telemetry, lifecycle
  -> resolve_model(llm)                          browser_use/llm/__init__.py    bu-fast gateway default, ChatOpenAI/Anthropic/Google, model strings
  -> Browser.start() -> env for the worker       browser_use/browser/browser.py cloud (API v4, default) | 'chromium' (local.py) | 'chrome' (harness daemon) | cdp_url
  -> run(agent, task, Session)                   browser_use/agent/loop.py      Pydantic AI loop: python tool, finish / finish_from_repl,
                                                                                image pruning, delivery guards, budgets, partial results
       python(code) -> Repl.call()               browser_use/repl/session.py    parent side: spawns the worker, allowlisted env, redaction
                    -> worker process            browser_use/repl/worker.py     runs cells; helpers, screenshot, checkpoint, type_secret
                       mode='ultrafast' adds bu  browser_use/ax.py              accessibility-tree helpers (port of Browser Use Pi ax.ts)
  <- AgentHistoryList                            browser_use/agent/views.py     status, text/output, success, partial, usage, cost_usd, messages
  • The system prompt is browser_use/agent/prompt.py. It is evaluated; do not edit it casually.
  • The REPL worker is a child process in its own process group: a cell timeout kills the tree and restarts it. Files and browser state survive, Python variables do not.
  • Secrets (sensitive_data) are redacted from specific channels (listed in "Trust model" in MIGRATING.md), not sandboxed.
  • browser-use CLI and --cli-mcp (browser_use/cli.py, browser_use/mcp/) pipe Python to browser-harness.
  • browser_use/skills/ ships the browser-use agent skill and its installer.

Read the full file on GitHub · 51 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 Changed · -113 lines · -1,699 tokens per session c22dcac11db3
  2. 2mo ago First seen · 164 lines · 2,495 tokens per session scan A 8d6a85903545

Subscribe to this mod's changes

browser-use CLAUDE.md is an instructions file published in the GitHub repository browser-use/browser-use (121,333 stars, last pushed today), licensed MIT. It adds 796 tokens to every session, about $0.0032 per session on Opus 5.5. 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

browser-use CLAUDE.md compared with instructions from other repositories

browser-use CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
browser-use CLAUDE.mdbrowser-use/browser-useInstructions file121ktodayMITA796Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot