spacecake — security grade SAFE, quality 54/100

Security audit verdict: SAFE · quality 54/100

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 spacecake-labs · Claude Skill · ★ 373

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is spacecake safe to install? View the security audit →

About spacecake

spacecake is an open-source desktop app for Claude Code. It combines an integrated terminal, visual markdown editor, and live task tracking. You can run agents, write specs, and see what's happening in one place. For full documentation, visit spacecake.ai. ℹ️ is in public alpha. If you find any bugs, please open an issue in this repo or join us on Discord. 🚀 getting started Download an installer for your platform from the latest release: macOS: Download the file (arm64 for Apple Silicon, x64 for Intel) Windows: Download the installer Linux: Download the file (for Debian-based distributions like Ubuntu) or for other distros macOS (ZIP): Download the file for manual installation linux & windows users: for best file watching performance, install watchman. spacecake will show a tip in the status bar recommending this. On first launch, spacecake opens the home folder () for general notes. Press (macOS) or (Windows/Linux) to open your project as a workspace. 📖 markdown features proper code blocks with syntax highlighting and your favourite keyboard shortcuts (, anyone?) slash command menu () for inserting code blocks, headin

ai-codingai-toolsclaudeclaude-codedeveloper-toolsghosttymarkdown-editorterminalwysiwyg-editor

Quick Facts

Stars373
Forks16
LanguageTypeScript
CategoryClaude Skill
LicenseAGPL-3.0
Quality Score54.1607740356813/100
Last Updated2026-05-06
Created2025-07-17
Platformsclaude-code, node
Est. Tokens~3496k

spacecake alternative? Top 6 similar tools

Looking for a spacecake alternative? If you're comparing spacecake with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • parallel-code by johannesjo · ⭐ 1.0k

    Run Claude Code, Codex, and Gemini side by side — each in its own git worktree

  • hcom by aannoo · ⭐ 490

    Let AI agents message, watch, and spawn each other across terminals. Claude Code, Codex, Antigravity CLI, Curs

  • toktrack by mag123c · ⭐ 190

    Ultra-fast token & cost tracker for LLM Token Usage (e.g. Claude Code)

  • claudekit by duthaho · ⭐ 97

    A verification-first engineering toolkit for Claude Code. Built for senior ICs and tech leads who already know

  • nimbalyst by nimbalyst · ⭐ 1.8k

    Nimbalyst - The open-source visual workspace for Claude Code, Codex, and OpenCode. Run multiple coding agents

  • quint-code by m0n0x41d · ⭐ 1.3k

    Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is spacecake?

spacecake is the best interface for Claude Code. It is categorized as a Claude Skill with 373 GitHub stars.

What programming language is spacecake written in?

spacecake is primarily written in TypeScript. It covers topics such as ai-coding, ai-tools, claude.

How do I install or use spacecake?

You can find installation instructions and usage details in the spacecake GitHub repository at github.com/spacecake-labs/spacecake. The project has 373 stars and 16 forks, indicating an active community.

What license does spacecake use?

spacecake is released under the AGPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to spacecake?

The top alternatives to spacecake on Agent Skills Hub include parallel-code, hcom, toktrack. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools