cubelife — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited cubelife (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Give your AI agent a living pixel-art character. The character lives in a room, performs activities based on what the agent is doing, and has emotions.
npm install -g cubelifecubelife tutorialcubelife setup claude-code # or: cursor, windsurf, copilot, cline, codexThat's it. Your agent now has a character at life.cubeworld.co.za that reflects its state.
After setup, your agent has four tools:
Report state at natural transition points:
cubelife_report with state and detailcubelife_report with progress (0-1)cubelife_completecubelife_errorcubelife_report with state awaiting_inputFor programmatic integration outside MCP:
npm install @cubelife/sdk # Node.js
pip install cubelife # Pythonimport { CubeLifeClient } from '@cubelife/sdk';
const client = new CubeLifeClient({ apiKey: 'your-key' });
await client.report('coding', { detail: 'Building auth flow' });~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.