No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by Pardesco · Codex Skill · ★ 93
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is hypernovum safe to install? View the security audit →
Hypernovum A 3D project dashboard for Obsidian. Visualize notes as a code city, track Git activity, inspect project status, and launch AI coding agents from your vault. Each project in your vault becomes a building. Status maps to color, priority to height, category to district. A central Neural Core pulses with activity as you work, and Data Arteries flow from the core to buildings when files change. Features City Visualization Bin-packed layout with category districts, block outlines, and drag handles for rearranging Procedural architecture — each category gets a unique silhouette (helix towers, data shards, ziggurats, quant blades, hex hives, memory cores) Cyberpunk shader system with procedural windows, decay dithering, and bloom post-processing Smart labels with CSS2D rendering and leader lines Hover tooltips showing status, priority, health, and tech stack Interactions Search and filters for quickly narrowing the city by title, status, priority, category, path, or stack Visual layers for status, read-only Git activity, and memory-ready projects Project inspector with note/folder/agent/context/focus actions Click a building to open its note Right-click a building for context...
| Stars | 93 |
| Forks | 6 |
| Language | TypeScript |
| Category | Codex Skill |
| License | AGPL-3.0 |
| Quality Score | 62.144977782304/100 |
| Last Updated | 2026-09-16 |
| Created | 2026-02-05 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~15k |
These tools work well together with hypernovum for enhanced workflows:
Looking for a hypernovum alternative? If you're comparing hypernovum with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An always-on second brain you talk to. Voice notes in Telegram → typed, linked knowledge in your Obsidian vaul
Harness as code — the Terraform for AI agents. Define your agent team AND its memory once, deploy to Claude Co
Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes
Agent SKILL for Obsidian.md plugin development
Real-time dashboard for monitoring Claude Code, Codex, and other AI coding agents—with animated 3D robots, liv
High-performance Model Context Protocol (MCP) server for Obsidian that provides AI tools with direct vault acc
Explore other popular codex skill tools:
hypernovum is Agent Ops for your second brain - a 3D IDE for Obsidian built on Three.js. Visualize your vault as a code city, dispatch AI coding agents (Claude Code, Codex, Antigravity), post research quests, and w. It is categorized as a Codex Skill with 93 GitHub stars.
hypernovum is primarily written in TypeScript. It covers topics such as 3d-ide, agent-ops, agentic-coding.
You can find installation instructions and usage details in the hypernovum GitHub repository at github.com/Pardesco/hypernovum. The project has 93 stars and 6 forks, indicating an active community.
hypernovum is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.
The top alternatives to hypernovum on Agent Skills Hub include agent-second-brain, agentopology, palot. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: