agentrigs
+ submit rig
~ / rigs / HatriGt / agent-sandbox

HatriGt/agent-sandbox

A cloud sandbox for coding agents, on your own server. Start a run from the dashboard, from any agentic IDE (Cursor, Claude Code, Codex, VS Code), or from a script — it runs in an isolated KVM microVM and streams back live.

↗ GitHub ★ 0 Apache-2.0 updated today project Claude Code
share on X
ARCHETYPE
Pragmatist
A balanced, no-drama setup: some rules, some tools, nothing extreme.
CONTEXT TAX · EVERY TURN
~391 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit HatriGt/agent-sandbox/.claude ./rig-agent-sandbox  # inspect, then merge into .claude/

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 HatriGt/agent-sandbox/.claude/skills/12-principles-of-animation .claude/skills/12-principles-of-animation
$ npx degit HatriGt/agent-sandbox/.claude/skills/emil-design-eng .claude/skills/emil-design-eng
$ npx degit HatriGt/agent-sandbox/.claude/skills/fixing-accessibility .claude/skills/fixing-accessibility
$ npx degit HatriGt/agent-sandbox/.claude/skills/make-interfaces-feel-better .claude/skills/make-interfaces-feel-better
$ npx degit HatriGt/agent-sandbox/.claude/skills/playwright-cli .claude/skills/playwright-cli
$ npx degit HatriGt/agent-sandbox/.claude/skills/react-doctor .claude/skills/react-doctor
$ npx degit HatriGt/agent-sandbox/.claude/skills/shadcn .claude/skills/shadcn

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (7)

12-principles-of-animationemil-design-engfixing-accessibilitymake-interfaces-feel-betterplaywright-clireact-doctorshadcn

Similar rigs

jakubkrehel/make-interfaces-feel-better
An agent skill that helps make your interface feel better.
★ 3,557 project Claude CodeCodex 1 skills 1mo ago
Minimalist 487 tok ·
VoltAgent/voltagent
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
★ 10.7k project Claude CodeCodexCursor 2 skills 11d ago
Minimalist 522 tok ·
SalvadorCardona/ponos
Write the ticket, it comes back done. A self-hosted harness around Claude Code that runs your tasks — code, writing, external actions — each on its own git worktree. Works with Notion, GitHub, Telegram and Slack, or none of them.
★ 1 project Claude Code 1 mcp 2 skills today
Pragmatist 4.3k tok ·
molefrog/moi
💾 MOI: agent-agnostic generative UI workspace. Give your agent a skill and let it build software around itself.
★ 182 project Claude CodeCodex 4 skills 1 hooks 3d ago
Pragmatist 3.5k tok ·
copied ✓