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/elemarin/renderoni/agents-mdgit clone --depth 1 https://github.com/elemarin/renderoniWhat 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 | $0.01082 | $0.01082 |
| Opus 5 | $0.00541 | $0.00541 |
| Sonnet 5 | $0.00216 | $0.00216 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
renderoni 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 yesterday.
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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🍝 Renderoni Agent Guidelines (AGENTS.md)
Universal instructions for AI coding agents (Antigravity, Claude Code, Cursor, Windsurf, Copilot) working in the Renderoni codebase.
🏛️ Architecture & Kernel Rules
Renderoni is structured in 4 strict hierarchical layers:
- L0: Deterministic Kernel (
src/core/): Integer tick clock (clock.ts), seeded PRNG streams (prng.ts), dual-buffer transform pipeline (transform-buffer.ts), XXH3 state hashing (hashing.ts), resource ownership matrix (ownership.ts), and diagnostics (diagnostics.ts).- Rule 1: NEVER call
Math.random(),Date.now(),performance.now(), orrequestAnimationFrame()inside simulation logic or entity updates. Always useengine.prngandengine.clock.tick. - Rule 2: NEVER bypass the dual-buffer transform pipeline. Write physics transforms into canonical buffer slots, never directly into render scene graphs.
- Rule 1: NEVER call
- L1: Batteries & Subsystems (
src/presets/,src/animation/,src/audio/,src/vfx/,src/ui/,src/scene/): High-level declarative presets (body,sensor,light,kccPlayer,dynamicPlayer,proceduralModel) and compact scene inventories for prompt → img2threejs factories. - L2: Agent Tooling & MCP (
src/mcp/,src/testing/): Stdio Model Context Protocol server, custom Vitest matchers, and headless CLI verification. - L3: Web Application & Demos (
src/demo/,index.html): Interactive playground and multi-archetype web showcases.
📦 Subpath Exports & Import Conventions
Always use subpath imports rather than deep file path hacks:
import { createRenderoni, RenderoniEngine } from 'renderoni';
import { body, kccPlayer, sensor, light, definePreset, proceduralModel } from 'renderoni/presets';
import { mountSceneInventory, parseSceneInventory } from 'renderoni/scene';
import { audio } from 'renderoni/audio';
import { animation } from 'renderoni/animation';
import { vfx } from 'renderoni/vfx';
import { ui } from 'renderoni/ui';
import { createMCPServer } from 'renderoni/mcp';
import 'renderoni/testing/matchers';
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.
- yesterday First seen · 81 lines · 1,082 tokens per session scan A 18b2cfebc9d2
renderoni AGENTS.md is an instructions file published in the GitHub repository elemarin/renderoni (0 stars, last pushed 4d ago), licensed MIT. It adds 1,082 tokens to every session, about $0.0054 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.
Other instructions, from other repositories
fonline AGENTS.md
Instructions for cvet/fonline, covering fonline engine — ai maintainer guide, scope, before changing anything, documentation map and validation routing.
comedot AGENTS.md
Instructions for InvadingOctopus/comedot, covering agents.md, guidelines for the comedot project and repository, project overview, folder structure & module organization and subsystems.
ReignsAgent AGENTS.md
Instructions for Sisyphe42/ReignsAgent, covering reignsagent system specification & agent guidelines, 0. project goal, 1. core architecture (decoupled design), 2. extensibility specification and 3. maintenance protocols.
lattice AGENTS.md
Instructions for plausibleventures/lattice, covering lattice — how to work in this repo, the eleven non-negotiables, layout, commands and house style.
LittleJS-AI CLAUDE.md
Instructions for KilledByAPixel/LittleJS-AI: You are a helpful assistant for building playable LittleJS games with Claude.
summer-engine-agent AGENTS.md
Instructions for SummerEngine/summer-engine-agent, covering summer — agent context, what you're working with, critical rules, skill priority and mcp tool palette (project-matched local editor).