Borrowing it
Nothing to install: this file belongs to rubinsh/mcp-windows-screenshots. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/rubinsh/mcp-windows-screenshots/main/CLAUDE.mdgit clone --depth 1 https://github.com/rubinsh/mcp-windows-screenshotsWrote 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.
[](https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md)<a href="https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md"><img src="https://agentmods.dev/badge/instructions/rubinsh/mcp-windows-screenshots/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.
<a href="https://agentmods.dev/instructions/rubinsh/mcp-windows-screenshots/claude-md"><img src="https://agentmods.dev/badge/instructions/rubinsh/mcp-windows-screenshots/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00527 | $0.00527 |
| Opus 5 | $0.00264 | $0.00264 |
| Sonnet 5 | $0.00105 | $0.00105 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
mcp-windows-screenshots 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 9d 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.
What it actually says
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an MCP (Model Context Protocol) server that enables Claude to access Windows screenshots from WSL2 environments. It's designed to simplify screenshot sharing by eliminating the need for manual file path navigation.
Development Commands
# Install dependencies
npm install
# Build TypeScript to JavaScript
npm run build
# Development mode with auto-rebuild
npm run dev
# Test the server locally
node dist/index.js
MCP Server Architecture
- Transport: stdio-based communication
- Tools Provided:
list_screenshots: Lists recent screenshots with metadataget_screenshot: Retrieves a specific screenshot (path or base64 content)list_directories: Shows all configured screenshot directories
- Entry Points:
cli.js: NPX entry point that spawns the serversrc/index.ts: Main server implementation
Testing the MCP Server
To test changes locally before publishing:
# Build and test with Claude Code
npm run build
claude mcp add windows-screenshots-dev node /path/to/project/dist/index.js
# Remember to remove test server after testing
claude mcp remove windows-screenshots-dev
Publishing to NPM
# Bump version in package.json
npm version patch # or minor/major
# Publish (build runs automatically via prepublishOnly)
npm publish
# Test the published version
npx mcp-windows-screenshots@latest
Common Development Tasks
- Adding new screenshot directories: Modify
getScreenshotDirectories()in src/index.ts - Changing file patterns: Update the glob patterns in
list_screenshotstool - Adding new MCP tools: Follow the pattern in
server.setRequestHandler() - Debugging MCP communication: Errors go to stderr, use
console.error()for debugging
Important Notes
- This is an MCP server meant to be installed via
claude mcp addcommand - Users install it with:
claude mcp add windows-screenshots -- npx mcp-windows-screenshots@latest - Environment variables (WINDOWS_USERNAME, MCP_SCREENSHOT_DIRS) are passed via
-eflags during installation - The server runs as a subprocess of Claude Code and communicates via stdio
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.
- 9d ago First seen · 66 lines · 527 tokens per session scan A c682c51c0d53
mcp-windows-screenshots CLAUDE.md is an instructions file published in the GitHub repository rubinsh/mcp-windows-screenshots (6 stars, last pushed 1y ago), licensed MIT. It adds 527 tokens to every session, about $0.0026 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 2026-08-31.
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.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.