inoio/agents-sandbox
Sandbox for AI coding agents (Claude Code, opencode, pi): runs each project in an isolated microVM with host-side secret injection. Linux/KVM & macOS.
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
$ git clone --depth 1 https://github.com/inoio/agents-sandbox MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit inoio/agents-sandbox/.agents/skills/bare-worktrees .claude/skills/bare-worktrees $ npx degit inoio/agents-sandbox/.agents/skills/compacting-context .claude/skills/compacting-context $ npx degit inoio/agents-sandbox/.agents/skills/greptile-review .claude/skills/greptile-review $ npx degit inoio/agents-sandbox/.agents/skills/handle-pr-feedback .claude/skills/handle-pr-feedback $ npx degit inoio/agents-sandbox/.agents/skills/maintain .claude/skills/maintain $ npx degit inoio/agents-sandbox/.agents/skills/opencode2-probe .claude/skills/opencode2-probe $ npx degit inoio/agents-sandbox/.agents/skills/opencode2-self-management .claude/skills/opencode2-self-management $ npx degit inoio/agents-sandbox/.agents/skills/pr .claude/skills/pr $ npx degit inoio/agents-sandbox/.agents/skills/rebase-status .claude/skills/rebase-status $ npx degit inoio/agents-sandbox/.agents/skills/release .claude/skills/release $ npx degit inoio/agents-sandbox/.agents/skills/terminal-reset .claude/skills/terminal-reset $ npx degit inoio/agents-sandbox/.agents/skills/upstream-drift .claude/skills/upstream-drift
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 16.2k rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(./.env.*)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(git push --force:*)",
"Read(**/*.pem)",
"Read(.env)",
"Read(~/.aws/**)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Bash(rm -rf *)",
"Bash(sudo *)",
"Bash(sudo:*)",
"Bash(rm -rf /)",
"Bash(git push -f:*)",
"Read(.env.*)",
"Bash(git reset --hard*)",
"Bash(rm -rf /*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(gh pr merge *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(gh pr merge:*)",
"Bash(gh pr create *)",
"Bash(git reset --hard:*)",
"Bash(npm publish:*)",
"Bash(git rebase *)"
]
}
} Skills (12)
Similar rigs
devoxx/DevoxxGenieIDEAPlugin
DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Devel
Pragmatist 3.4k tok · · Q0
sam-at-luther/claude-config
Common Claude Code configuration, skills, and guidance
Pragmatist 2.0k tok · · Q11
slopus/happy
Happy is the open-source desktop app for Claude Code, Codex, and Grok, with an iOS and Android app to control your coding agents from anywhere.
Pragmatist 9.7k tok · · Q23
RemiMyrset/roots
A GitHub template for pnpm + Turborepo TypeScript monorepos that AI coding agents can work in safely from day one.
Skill Collector 3.4k tok · · Q28