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/getopenscreen/openscreen/agents-mdgit clone --depth 1 https://github.com/getopenscreen/openscreenWhat 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 | $0.05627 | $0.05627 |
| Opus 5 | $0.02814 | $0.02814 |
| Sonnet 5 | $0.01125 | $0.01125 |
| Haiku 4.5 | $0.00563 | $0.00563 |
Grade A, and why
openscreen 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
OpenScreen is a free, open-source screen recorder and video editor (Electron + React + TypeScript + Pixi.js) maintained as a continuation of the original v1.5.0 release. This file is the canonical guide for any AI coding agent working in this repo.
Setup commands
- Install deps:
npm install(Node 22.22.1, npm 10.9.4 — seepackage.json#engines) - Start dev:
npm run dev(Vite dev server; Electron window opens viavite-plugin-electron) - Build:
npm run build(TypeScript check + Vite build + electron-builder) - Typecheck:
npx tsc --noEmit— app code only. CI also runsnpx tsc -p tsconfig.test.json --noEmitin a separate job ("Typecheck (tests)"), so run both: test files are invisible to the root config, and a type error in a*.test.tsfails CI while the root check stays green. - Test (unit):
npx vitest --run <path>while you work,npm run testonce at the end — see Testing instructions - Test (e2e):
npm run test:e2e(Playwright) - Lint:
npm run lint(Biome 2.4) - Format:
npm run format(Biome, tabs, double quotes, 100-col) - i18n check:
npm run i18n:check(validates the 13 locale files)
Use npm, not bun/pnpm/yarn/Deno. Not a style preference. Node native modules are rebuilt against Electron's ABI by electron-builder + @electron/rebuild, which resolve the tree through package-lock.json. Another package manager writes a different lockfile, so that rebuild breaks. packageManager + engines in package.json pin the versions; CI installs with npm ci. Note what this does not cover: the standalone Swift (macOS) and C++ (Windows) capture helpers are separate executables, built by npm run build:native:<platform> and only copied into the package as extraResources — build:win even passes --config.npmRebuild=false. Nothing in a normal build compiles them.
Development principles
- Prefer the simplest solution that stays readable — no abstraction for hypothetical needs (YAGNI).
- No mandated app-stack choice yet. Contributors pick their own state/data library. Don't impose one across the codebase and don't refactor existing code onto a different one — keep each addition self-contained and consistent within its own module. A single choice may be enforced later.
- Don't optimize for line count. A dense one-liner that hides control flow is worse than the explicit version.
- Match the surrounding code's idiom rather than introducing a new pattern next to it.
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 · 171 lines · 5,627 tokens per session scan A 92f6add04279
openscreen AGENTS.md is an instructions file published in the GitHub repository getopenscreen/openscreen (2,185 stars, last pushed 2d ago), licensed MIT. It adds 5,627 tokens to every session, about $0.0281 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
WeftCut AGENTS.md
Instructions for WeftCut/WeftCut, covering weftcut — agent instructions, agent skills, issue tracker, domain docs and testing.
palmier-pro-windows AGENTS.md
AGENTS.md instructions for MadeNavaneeth/palmier-pro-windows, covering palmier pro windows agent guide, mandatory upstream check, upstream dispositions, translation rules and required finish checks.
WeftCut CLAUDE.md
Instructions for WeftCut/WeftCut, covering weftcut — agent instructions, agent skills, issue tracker, domain docs and testing.
erm AGENTS.md
Instructions for dougcalobrisi/erm, covering agents.md — erm, install, fallback (no uv on path), use — the iterate loop and tune — five knob clusters.
movi-player AGENTS.md
Instructions for MrUjjwalG/movi-player, covering agents.md — movi-player for ai coding assistants, 1. what this is, 2. package entry points, 3. architecture map and 4. the web component .
leclap CLAUDE.md
Instructions for heristop/leclap: This repository's agent guidance lives in AGENTS.md — read it first; it is the single source of truth for structure, commands, and conventions.