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/wassermanproductions/blockout/agents-mdgit clone --depth 1 https://github.com/wassermanproductions/blockoutWrote 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/wassermanproductions/blockout/agents-md)<a href="https://agentmods.dev/instructions/wassermanproductions/blockout/agents-md"><img src="https://agentmods.dev/badge/instructions/wassermanproductions/blockout/agents-md.svg" alt="Measured on agentmods" 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 | $0.03571 | $0.03571 |
| Opus 5 | $0.01785 | $0.01785 |
| Sonnet 5 | $0.00714 | $0.00714 |
| Haiku 4.5 | $0.00357 | $0.00357 |
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 5d 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 — 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)
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.
- 5d ago First seen · 145 lines · 3,571 tokens per session scan A a0481d6df926
blockout AGENTS.md is an instructions file published in the GitHub repository wassermanproductions/blockout (120 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,571 tokens to every session, about $0.0179 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
GameDesignOS AGENTS.md
Instructions for DY-2026/GameDesignOS, covering gamedesignos agent 入口, 默认接法, agent 执行规则, 什么时候用整个项目 and 每个 skill 单独怎么用.
claudemon CLAUDE.md
Instructions for zamarrowski/claudemon, covering ai agent guidelines, project shape, general guidelines, general rules and guards & defensive code.
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
codex-game-studio AGENTS.md
AGENTS.md instructions for merlinhu1/codex-game-studio, covering codex game studio template, project goal, engine, commands and context bootstrap.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.