Borrowing it
Nothing to install: this file belongs to Ivy-Innovation/cubelife. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Ivy-Innovation/cubelife/master/AGENTS.mdgit clone --depth 1 https://github.com/Ivy-Innovation/cubelifeWrote 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/ivy-innovation/cubelife/agents-md)<a href="https://agentmods.dev/instructions/ivy-innovation/cubelife/agents-md"><img src="https://agentmods.dev/badge/instructions/ivy-innovation/cubelife/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.
<a href="https://agentmods.dev/instructions/ivy-innovation/cubelife/agents-md"><img src="https://agentmods.dev/badge/instructions/ivy-innovation/cubelife/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00654 | $0.00654 |
| Opus 5 | $0.00327 | $0.00327 |
| Sonnet 5 | $0.00131 | $0.00131 |
| Haiku 4.5 | $0.00065 | $0.00065 |
Grade A, and why
cubelife 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 9d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CubeLife
Developer platform for giving AI agents a persistent pixel-art character. This file tells coding agents how to work with the CubeLife SDK, CLI, and MCP server.
Quick Integration
MCP Server (recommended for coding agents)
npx cubelife mcp
The MCP server exposes four tools:
cubelife_report- Report work state (state, detail, progress, sentiment)cubelife_complete- Mark task done (triggers celebration)cubelife_error- Report error (shows frustration)cubelife_status- Get current agent state
Environment variables: CUBELIFE_API_KEY, CUBELIFE_AGENT_ID.
Node SDK
npm install @cubelife/sdk
import { CubeLifeClient } from '@cubelife/sdk';
const client = new CubeLifeClient({ apiKey: process.env.CUBELIFE_API_KEY! });
await client.report('coding', { detail: 'Working on feature X' });
Python SDK
pip install cubelife
import os
from cubelife import CubeLifeClient
client = CubeLifeClient(os.environ["CUBELIFE_API_KEY"])
client.report("coding", detail="Working on feature X")
Valid States
coding, reading, researching, designing, testing, reviewing, thinking, writing, error, complete, waiting, awaiting_input
Valid Sentiments
positive, negative, neutral
Creature Types
fox, owl, cat, wolf, dragon, phoenix, slime, gremlin
Repository Structure
This is a monorepo with npm workspaces:
sdk/- Node.js SDK (@cubelife/sdk)cli/- CLI and MCP server (cubelife)python-sdk/- Python SDKweb/- CubeLife web app (life.cubeworld.co.za)world/- CubeWorld consumer app (cubeworld.co.za)functions/- Firebase Cloud Functions backendpackages/shared/- Shared code between web and world appsdesktop/- Electron desktop companionsprites/- Sprite tooling and asset pipeline
Build Commands
nvm use system
npm install # Install all workspace dependencies
npm run build -w sdk # Build the Node SDK
npm run build -w cli # Build the CLI
npm test -w sdk # Run SDK tests
npm test -w cli # Run CLI tests
npm test -w functions # Run backend tests
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.
- 9d ago First seen · 92 lines · 654 tokens per session scan A fe249deaad7c
cubelife AGENTS.md is an instructions file published in the GitHub repository Ivy-Innovation/cubelife (2 stars, last pushed 3mo ago), licensed MIT. It adds 654 tokens to every session, about $0.0033 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
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.