agentsclimarketplace

Sindoq

Skill HappyHackingSpace/skills/skills/sindoq

Execute code in sandboxed environments using Docker, Podman, Wasmer, gVisor, Firecracker, Kubernetes, or cloud providers. Use when the user needs to safely run untrusted code, build AI code execution pipelines, or set up isolated sandbox environments.From its SKILL.md

Install
npx -y skills add HappyHackingSpace/skills --skill sindoq

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • reads credentialsReads from 2 credential sources: `VERCEL_TOKEN` and 1 more.
  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 1 command, including `go get github.com/happyhackingspace/sindoq`.

SKILL.md

3.2 KB, 836 tokens by cl100k_base, as published. Nobody here has run it

sindoq - AI Sandbox

sindoq (means "box" in Kurdish) is a Go SDK for sandboxed code execution. One API, any provider.

Installation

go get github.com/happyhackingspace/sindoq

Quick Start

One-liner Execution

result, err := sindoq.Execute(ctx, `print("Hello, World!")`)
fmt.Println(result.Stdout) // Hello, World!

With Specific Provider

sb, err := sindoq.Create(ctx, sindoq.WithProvider("docker"))
if err != nil {
    log.Fatal(err)
}
defer sb.Stop(ctx)

result, err := sb.Execute(ctx, `console.log("Hello")`, sindoq.WithLanguage("JavaScript"))
fmt.Println(result.Stdout)

Streaming Output

sb, err := sindoq.Create(ctx, sindoq.WithProvider("docker"))
defer sb.Stop(ctx)

err = sb.ExecuteStream(ctx, code, func(e *executor.StreamEvent) error {
    if e.Type == executor.StreamStdout {
        fmt.Print(e.Data)
    }
    return nil
})

Async Execution

results, err := sb.ExecuteAsync(ctx, code)
// Do other work...
result := <-results
fmt.Println(result.Stdout)

Providers

ProviderTypeUse Case
dockerLocalDevelopment, CI/CD
podmanLocalRootless containers
wasmerLocalCross-platform WASM sandbox (Linux, macOS, Windows)
nsjailLocalUltra-fast process isolation (~5ms, Linux only)
gvisorLocalStrong isolation, syscall filtering (Linux only)
firecrackerLocalMaximum isolation (microVMs, Linux only)
landlockLocalKernel-level sandboxing via Landlock LSM (Linux 5.13+)
seatbeltLocalKernel-level sandboxing via sandbox-exec (macOS)
kubernetesCloudScalable workloads
vercelCloudServerless execution
e2bCloudAI code interpreter

Provider Configuration

// Docker
sb, _ := sindoq.Create(ctx, sindoq.WithDockerConfig(sindoq.DockerConfig{
    Host: "unix:///var/run/docker.sock",
}))

// Vercel
sb, _ := sindoq.Create(ctx, sindoq.WithVercelConfig(sindoq.VercelConfig{
    Token: os.Getenv("VERCEL_TOKEN"),
}))

// E2B
sb, _ := sindoq.Create(ctx, sindoq.WithE2BConfig(sindoq.E2BConfig{
    APIKey: os.Getenv("E2B_API_KEY"),
}))

// Wasmer (cross-platform)
sb, _ := sindoq.Create(ctx, sindoq.WithWasmerConfig(sindoq.WasmerConfig{
    WasmerPath: "wasmer",
    TimeLimit:  30,
}))

// Seatbelt (macOS)
sb, _ := sindoq.Create(ctx, sindoq.WithSeatbeltConfig(sindoq.SeatbeltConfig{
    EnableNetwork: false,
}))

Features

  • Multi-provider support: Docker, Podman, Wasmer, nsjail, gVisor, Firecracker, Landlock, Seatbelt, Kubernetes, Vercel, E2B
  • Auto language detection: Automatically detects programming language from code
  • Streaming output: Real-time stdout/stderr streaming
  • Async execution: Non-blocking execution with channels
  • Resource limits: Control CPU, memory, and execution time
  • File system access: Read/write files in sandbox environments

References

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most containers cloud skills give in 836 tokens

Counted across 607 of the 705 authors here whose files we hold, read 2026-09-06

  • Run as non-root userin 34 of 607, across 27 files
  • Use multi-stage buildsin 29 of 607
  • Set resource requests and limitsin 24 of 607, across 20 files
  • Configure liveness and readiness probesin 18 of 607, across 14 files
  • Use named volumes for persistent datain 14 of 607, across 9 files
  • Pin base image versionsin 14 of 607
  • Set up environment variablesin 14 of 607, across 10 files
  • Pin provider versionsin 14 of 607
  • Apply least privilege RBAC permissionsin 10 of 607, across 7 files
  • Create a dockerignore filein 10 of 607
  • Use remote state with lockingin 9 of 607
  • Pin base images by digestin 9 of 607, across 8 files

Said here and by no other author read

  • Run untrusted code safely
  • Set up isolated sandbox environments
  • Build AI code execution pipelines

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.