What is blockout AGENTS.md?

Project instructions for Blockout, a desktop application for filmmakers to plan rough 3D scenes. It uses Electron, TypeScript, React, and Three.js to place actors and cameras on a timeline and export motion references for AI video tools.

Use them when developing or testing scene staging, camera and actor animation, timeline features, video or depth exports, and the macOS packaging workflow.

They explain the application structure, required tools, and checks needed for reliable scene exports. This gives an agent the context to change the app without breaking rendering, packaging, or export validation.

How wassermanproductions/blockout configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to wassermanproductions/blockout. 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/wassermanproductions/blockout/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/wassermanproductions/blockout

Made for: Codex, OpenCode.

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/wassermanproductions/blockout/agents-md/github.svg)](https://agentmods.dev/instructions/wassermanproductions/blockout/agents-md)

Your own site

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

Per session 3,571 This file is loaded in full into every session.

When invoked 3,571 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	$0.03571	$0.03571
Opus 5.5	$0.01428	$0.01428
Sonnet 5.5	$0.00714	$0.00714
Haiku 4.5	$0.00357	$0.00357

Measured 2mo ago against content hash a0481d6df926, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

blockout 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 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.

AGENTS.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — running & modifying Blockout with an AI agent

This file is the single source of truth for AI coding agents (Claude Code, Codex, Hermes, OpenClaw, …) working on this repo. CLAUDE.md points here.

What this app is

Electron + TypeScript + React + Three.js desktop previs tool. Filmmakers stage grey-box scenes, choreograph camera/actor marks on a timeline, and export deterministic motion-reference packages (MP4 + depth pass + stills + prompt) for AI video generators. Full product spec: docs/DESIGN.md.

Commands

npm install            # once; Node 22+; ffmpeg needed for exports (brew install ffmpeg)
npm run dev            # run the app with hot reload
npm run build          # production build into out/
npm start              # run the production build
npm run typecheck      # strict TS, two projects (renderer+engine, main+e2e)
npm run lint           # ESLint (zero warnings allowed on main)
npm test               # Vitest engine unit tests (fast, no GPU)
npm run smoke          # build + Playwright end-to-end: real export, ffprobe-verified
npm run package:mac    # download+audit pinned FFmpeg pair, then current-architecture macOS DMG
                       # (add: npm run prepare:ffmpeg:mac -- --build-from-source to rebuild from source)
npm run package:win    # Windows x64 NSIS installer (run after npm ci on Windows)

Definition of done for any change: npm run typecheck && npm run lint && npm test green, and npm run smoke green if you touched engine/, export/, main/, or SceneManager.

Repo map

src/engine/     PURE TypeScript. No DOM, no three.js, no Electron imports — ever.
                The deterministic core: state(t) evaluator, camera math, paths,
                easing, rig noise, gaits, schema, prompts, generator profiles.
                All logic changes here need unit tests in tests/unit/.
src/main/       Electron main process: window, IPC, ffmpeg spawning, file I/O.
src/preload/    Typed IPC bridge (window.blockout). Keep in sync with main.
src/renderer/   React UI. store.ts (zustand; ALL doc mutations go through
                store.mutate for undo), panels/, viewport/ (SceneManager owns
                three.js), export/ (frame loop → ffmpeg, glTF, ComfyUI).
tests/unit/     Vitest (engine only). tests/e2e/ Playwright (smoke + screenshots).
assets/         (profiles as code in engine/profiles.ts; 3D assets are procedural)

Read the full file on GitHub · 145 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 · 145 lines · 3,571 tokens per session scan A a0481d6df926

Subscribe to this mod's changes

blockout AGENTS.md is an instructions file published in the GitHub repository wassermanproductions/blockout (188 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 3,571 tokens to every session, about $0.0143 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 2026-08-30.

Game development

blockout AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
blockout AGENTS.mdwassermanproductions/blockout	Instructions file	188	3mo ago	Apache-2.0	A	3,571	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

blockout: Instructions file for Codex