sbx

sbx is a skill for Claude Code from vinnie357/claude-skills. It costs 76 tokens per session (1,713 once invoked), scanned A, original, MIT.

A guide to using Docker Sandboxes, which run AI coding agents inside isolated micro virtual machines with restricted networking.

In plain words
What is it for?
Use it to install and operate the sbx command-line tool, start and manage sandboxes, forward ports, and move files in or out.
Why use it?
It helps keep agent activity and credentials separated from the host while allowing the project workspace to be shared.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex; mentions OpenCode.

Part of the sbx plugin — 1 skill shipped together

Good fit Use it to install and operate the sbx command-line tool, start and manage sandboxes, forward ports, and move files in or out.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vinnie357/claude-skills/sbx
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add vinnie357/claude-skills --skill sbx
Clone the repo
git clone --depth 1 https://github.com/vinnie357/claude-skills

Made for: Claude Code.

Or install sbx, the plugin that ships this one along with the rest of its 1 skill.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for sbx

README.md
[![agentmods](https://agentmods.dev/badge/skills/vinnie357/claude-skills/sbx/github.svg)](https://agentmods.dev/skills/vinnie357/claude-skills/sbx)
Your own site
<a href="https://agentmods.dev/skills/vinnie357/claude-skills/sbx"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/sbx/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for sbx

Your own site · 80×15
<a href="https://agentmods.dev/skills/vinnie357/claude-skills/sbx"><img src="https://agentmods.dev/badge/skills/vinnie357/claude-skills/sbx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,713 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Tool Misuse · line 36
    Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.
    Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
  • medium Privilege Escalation · line 36
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 37
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01713
Opus 5 $0.00038 $0.00856
Sonnet 5 $0.00015 $0.00343
Haiku 4.5 $0.00008 $0.00171

Measured 6d ago against content hash 3944ae0f77d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

sbx scanned grade A with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

curl -fsSL https://get.docker.com | sudo REPO_ONLY=1 sh

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -fsSL https://get.docker.com | sudo REPO_ONLY=1 sh
plugins/tools/sbx/skills/sbx/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docker Sandboxes (sbx)

What is sbx?

Docker Sandboxes runs AI coding agents in microVMs backed by a KVM hypervisor. The binary is sbx — not docker sbx. Each sandbox gets its own kernel, its own Docker daemon, and an isolated network namespace. Only the workspace directory is mounted into the VM. A credential proxy injects API keys host-side so secrets never enter the VM filesystem.

Install

macOS (Apple silicon, Sonoma+)

Requires Homebrew.

brew install docker/tap/sbx

Windows 11

Requires Hypervisor Platform enabled in Windows Features.

winget install Docker.sbx

Ubuntu 24.04+

Requires KVM and user in the kvm group.

curl -fsSL https://get.docker.com | sudo REPO_ONLY=1 sh
sudo apt-get install docker-sbx

mise (macOS, Linux)

mise's github backend extracts the platform tarball, preserves the bin/sbx + libexec/ layout, and verifies SLSA provenance. See templates/mise.toml.

[tools]
"github:docker/sbx-releases" = "0.30.0"
mise install
sbx version

Apple silicon and Linux x86_64 are confirmed. Windows is not packaged as a tarball asset — use winget above.

Authenticate

sbx login

Prompts for an API key and stores credentials locally.

Run an agent

# Create and immediately run a sandbox with Claude Code
sbx run claude

Available agents: Claude Code, Codex, Copilot, Cursor, Droid, Gemini, Kiro, OpenCode, Docker Agent, Shell (agent-less).

Create a sandbox in the background without attaching:

sbx create claude

Branch isolation

--branch auto creates a Git worktree for the sandbox, keeping branch changes isolated from the main working tree. Worktrees live under .sbx/ in the repo root. Add .sbx/ to .gitignore (or global gitignore) to keep it out of git status.

# Auto-create a worktree branch (with trailing path)
sbx run claude --branch auto .

# Target an existing branch
sbx run claude --branch my-feature

# Suggested gitignore entry
echo '.sbx/' >> .gitignore

Read the full file on GitHub · 216 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 216 lines · 76 tokens per session scan A 3944ae0f77d2

Subscribe to this mod's changes

sbx is a skill published in the GitHub repository vinnie357/claude-skills (25 stars, last pushed today), licensed MIT. It adds 76 tokens to every session and 1,713 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens