Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks.
- ✓Actively maintained (<30d)
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- !No standard license detected
git clone https://github.com/Th0rgal/sandboxed.sh && cp sandboxed.sh/*.md ~/.claude/agents/6 items in this repository
Subagents overview
What people ask about sandboxed.sh
What is Th0rgal/sandboxed.sh?
+
Th0rgal/sandboxed.sh is subagents for the Claude AI ecosystem. Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets, and OKX read-only security checks. It has 451 GitHub stars and was last updated today.
How do I install sandboxed.sh?
+
You can install sandboxed.sh by cloning the repository (https://github.com/Th0rgal/sandboxed.sh) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is Th0rgal/sandboxed.sh safe to use?
+
Our security agent has analyzed Th0rgal/sandboxed.sh and assigned a Trust Score of 72/100 (tier: OK). See the full breakdown of passed checks and flags on this page.
Who maintains Th0rgal/sandboxed.sh?
+
Th0rgal/sandboxed.sh is maintained by Th0rgal. The last recorded GitHub activity is from today, with 14 open issues.
Are there alternatives to sandboxed.sh?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy sandboxed.sh to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/th0rgal-sandboxed-sh)<a href="https://claudewave.com/repo/th0rgal-sandboxed-sh"><img src="https://claudewave.com/api/badge/th0rgal-sandboxed-sh" alt="Featured on ClaudeWave: Th0rgal/sandboxed.sh" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Production-ready platform for agentic workflow development.
The agent engineering platform.
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.