Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/yahorbarkouski/screencap/agents-mdgit clone --depth 1 https://github.com/yahorbarkouski/screencapWhat 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 | $0.02067 | $0.02067 |
| Opus 5 | $0.01033 | $0.01033 |
| Sonnet 5 | $0.00413 | $0.00413 |
| Haiku 4.5 | $0.00207 | $0.00207 |
Grade A, and why
screencap AGENTS.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 2d 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.
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.
AGENTS.md
Guidance for Codex when working with this repository.
Project Overview
Screencap is a macOS Electron desktop app that captures screenshots on a schedule, classifies them using optional LLM analysis, and turns them into timelines, daily summaries ("Day Wrapped"), and journals. It tracks app/window context, browser activity, media playback, and IDE workspace info to help users understand where their time goes.
Key features:
- Scheduled screenshot capture with context detection (app, window title, browser URL, media, IDE workspace)
- Event timeline with automatic merging of similar captures
- LLM-based classification (local or cloud) with fallback strategies
- Daily journal entries and "Day Wrapped" tray widget
- Project tracking with Git integration
- Addiction tracking with confirmation/rejection workflow
- Privacy-focused: local-first with optional cloud AI (text-first, vision fallback)
Commands
Development
npm install # Install dependencies
npm run dev # Start dev server (rebuilds native modules)
npm run dev:fast # Start dev server (skip native rebuild)
npm test # Run tests (rebuilds for Node first)
npm run test:watch # Run tests in watch mode
Building
npm run build # Build for production
npm run preview # Preview production build
npx electron-builder --config electron-builder.yml # Package distributable
Code Quality
npm run lint # Check code with Biome
npm run lint:fix # Auto-fix linting issues
npm run typecheck # TypeScript type checking
Utilities
npm run rebuild:electron # Rebuild native modules for Electron
npm run rebuild:node # Rebuild native modules for Node (tests)
npm run generate:icon # Generate app icon from source
npm run eval:classification -- --limit=25 --strategies=vision,text,local
Single Test Execution
npm test -- electron/main/features/context/__tests__/resolvers.test.ts
npm test -- -t "spotifyResolver"
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.
- 2d ago First seen · 223 lines · 2,067 tokens per session scan A 949f579311bf
screencap AGENTS.md is an instructions file published in the GitHub repository yahorbarkouski/screencap (90 stars, last pushed 3mo ago), licensed MIT. It adds 2,067 tokens to every session, about $0.0103 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 2026-08-30.
Other instructions, from other repositories
vscode tree-widgets.instructions.md
Use when asked to consume workbench tree widgets in VS Code.
vscode accessibility.instructions.md
Use when implementing accessibility features, ARIA labels, screen reader support, accessible help dialogs, or keybinding scoping for accessibility. Covers AccessibleContentProvider, CONTEXTACCESSIBILITYMODEENABLED, verbosity settings, and announcement patterns.
vscode writing-tests.instructions.md
VS Code test writing guidelines — unit tests, integration tests, snapshot tests, and clean teardown patterns. Reference when writing or updating tests.
vscode interactive.instructions.md
Architecture documentation for VS Code interactive window component. Use when working in src/vs/workbench/contrib/interactive.
vscode notebook.instructions.md
Architecture documentation for VS Code notebook and interactive window components. Use when working in src/vs/workbench/contrib/notebook/.
vscode design-philosophy.instructions.md
VS Code design philosophy — the shared Values→Principles→Moves vocabulary for reasoning about UI in design terms rather than raw pixels. Use when creating, editing, or reviewing any visual surface (CSS, DOM, theming, icons, motion). Name the value/principle before reaching for a token.