What is brosh CLAUDE.md?

Project instructions for brosh, a Python browser-screenshot tool that uses Playwright to capture scrolling webpages.

Use them to install brosh, install its Playwright browsers, understand its source files, and run its screenshot or related tools.

They document the package layout, installation requirements, command-line tools, and how to run the project during development.

How twardoch/brosh configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to twardoch/brosh. 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/twardoch/brosh/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/twardoch/brosh

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/twardoch/brosh/claude-md/github.svg)](https://agentmods.dev/instructions/twardoch/brosh/claude-md)

Your own site

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

Per session 2,368 This file is loaded in full into every session.

When invoked 2,368 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	$0.02368	$0.02368
Opus 5.5	$0.00947	$0.00947
Sonnet 5.5	$0.00474	$0.00474
Haiku 4.5	$0.00237	$0.00237

Measured 2mo ago against content hash ab6fa3ca2aa3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brosh 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.

CLAUDE.md · 223 lines

How it starts

The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.

=== USER INSTRUCTIONS ===

brosh is a browser screenshot tool that captures scrolling screenshots of webpages using Playwright's async API. The tool has been refactored from a monolithic script into a modular Python package with the following structure:

src/brosh/
├── __init__.py      # Package exports
├── __main__.py      # CLI entry point
├── api.py           # Public API functions (sync and async)
├── cli.py           # Fire-based CLI interface
├── tool.py          # Main BrowserScreenshotTool class
├── browser.py       # Browser management utilities
├── capture.py       # Screenshot capture logic
├── image.py         # Image processing utilities
├── models.py        # Data models and enums
├── mcp.py           # MCP server functionality
└── texthtml.py      # HTML/text processing utilities

Legacy implementation:

brosh_sel.py: Selenium-based synchronous implementation (deprecated)

Commands

Installation

# Install the package in development mode
pip install -e .
# Or install from PyPI (when published)
pip install brosh
# Install Playwright browsers
playwright install

Running the Tools

The package provides two command-line tools:

brosh: Main CLI for screenshot capture
brosh-mcp: MCP server for AI tool integration

Primary Tool (brosh)

# Basic usage
brosh shot "https://example.com"
# Start browser in debug mode
brosh --app chrome run
# Take screenshots with options
brosh --app chrome --width 1920 --height 1080 shot "https://example.com" --scroll_step 80 --format png
# Run MCP server
brosh mcp
# Or use the dedicated command
brosh-mcp

Development Mode

# Run from source during development
python -m brosh shot "https://example.com"
# Or use the development script (if maintaining the monolithic version)
./brosh.py shot "https://example.com"

Architecture

Module Structure

The project has been refactored into a modular architecture:

api.py: Public API with capture_webpage (sync) and capture_webpage_async (async) functions
browser.py: BrowserManager class handles browser detection, launching, and connection
capture.py: CaptureManager class handles screenshot capture and scrolling logic
image.py: ImageProcessor class handles image scaling, conversion, and APNG creation
tool.py: BrowserScreenshotTool orchestrates the other modules
cli.py: BrowserScreenshotCLI provides the Fire-based command interface
mcp.py: FastMCP server implementation for AI tool integration
models.py: Data models including ImageFormat enum and MCP-specific types
texthtml.py: DOMProcessor for HTML compression and text extraction

Read the full file on GitHub · 223 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 · 223 lines · 2,368 tokens per session scan A ab6fa3ca2aa3

Subscribe to this mod's changes

brosh CLAUDE.md is an instructions file published in the GitHub repository twardoch/brosh (3 stars, last pushed 2mo ago), licensed MIT. It adds 2,368 tokens to every session, about $0.0095 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 2026-08-31.

Browser automation Claude Code LLM browser-screenshot mcp mcp-server

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 · 9,715 tokens

brosh: Instructions file for Claude Code