What is smart-screen CLAUDE.md?

A project guide for Smart Screen, a desktop app built with Electron, React, and TypeScript for recording screen demonstrations and turning them into walkthrough videos. It describes the commands, two-process design, and flow between recording, analysis, and editing.

Use it when building or testing screen recording, mouse and keyboard tracking, transcription, AI or local analysis, the timeline editor, or the Electron-to-interface connection.

It helps the coding agent keep privileged desktop work, such as recording and secret storage, separate from the user interface, reducing architectural mistakes.

How varaprasadreddy9676/smart-screen configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to varaprasadreddy9676/smart-screen. 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/varaprasadreddy9676/smart-screen/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/varaprasadreddy9676/smart-screen

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/varaprasadreddy9676/smart-screen/claude-md/github.svg)](https://agentmods.dev/instructions/varaprasadreddy9676/smart-screen/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/varaprasadreddy9676/smart-screen/claude-md"><img src="https://agentmods.dev/badge/instructions/varaprasadreddy9676/smart-screen/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/varaprasadreddy9676/smart-screen/claude-md"><img src="https://agentmods.dev/badge/instructions/varaprasadreddy9676/smart-screen/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 927 This file is loaded in full into every session.

When invoked 927 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	$0.00927	$0.00927
Opus 5	$0.00464	$0.00464
Sonnet 5	$0.00185	$0.00185
Haiku 4.5	$0.00093	$0.00093

Measured 8d ago against content hash b9ffbe853087, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

smart-screen 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 8d 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

npm run dev              # Start Electron + Vite dev server
npm run build            # Full production build (native tools + TS + Vite + Electron Builder)
npm run lint             # Check code with Biome
npm run lint:fix         # Auto-fix linting issues
npm run format           # Auto-format with Biome
npm test                 # Run Vitest test suite once
npm run test:watch       # Run tests in watch mode

To run a single test file:

npx vitest run src/smart-demo/timelineAnalyzer.test.ts

Architecture

This is an Electron + React + TypeScript desktop app for recording screen demos and creating polished walkthrough videos with AI or local heuristic analysis.

Process Model

Two distinct processes — keep their responsibilities separate:

Main Process (/electron/) — privileged: recording lifecycle, native macOS telemetry (click/keyboard monitors), transcription pipeline, AI provider calls, secure secret storage
Renderer Process (/src/) — React UI: HUD overlay, source selector, timeline editor
IPC Bridge (/electron/preload.ts, /electron/ipc/handlers.ts) — 50+ contextBridge channels connect the two
Shared Types (/shared/) — cross-process TypeScript contracts; changes here affect both sides

Key Data Flow

Recording → cursor sampled at 10 Hz → .webm video + .webm.cursor.json sidecar
Load → IPC retrieves telemetry sidecar
Local Smart Demo (/src/smart-demo/) → deterministic heuristics detect clicks, typing, navigation, silence
Optional AI (/electron/ai/) → BYOK OpenAI or local Ollama; request built in renderer (/src/lib/ai/), executed in main
Edit → apply zooms, trims, captions, annotations in timeline editor
Export → decode video frames → render overlays (Pixi.js/Canvas) → re-encode MP4 or GIF

Operating Modes

The app is offline-first — fully functional without any AI provider:

Offline — local Smart Demo heuristics only
Hybrid — local heuristics + optional BYOK AI refinement (OpenAI)
Local AI — Ollama for on-device LLM

Read the full file on GitHub · 93 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.

8d ago First seen · 93 lines · 927 tokens per session scan A b9ffbe853087

Subscribe to this mod's changes

smart-screen CLAUDE.md is an instructions file published in the GitHub repository varaprasadreddy9676/smart-screen (5 stars, last pushed 5mo ago), licensed MIT. It adds 927 tokens to every session, about $0.0046 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.

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 · 5,153 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

smart-screen: Instructions file for Claude Code