# Sandboxd Code Run – Shell Command Executor

> Sandboxd Code Run – Shell Command Executor is a paid API for AI agents from sandboxd-code-run.saastemly.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-10).

Runs an arbitrary shell command in an isolated one-shot sandbox and returns stdout, stderr, exit code, and optional output files

## Facts

- Endpoint: POST https://sandboxd-code-run.saastemly.com/v1/execute-command?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sandboxd-code-run-shell-command-executor-f85a6076
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7PveTyrj09vsmr9ODWg6A

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability sandboxd-code-run-shell-command-executor-f85a6076 -d '<json body>'
```

Example prompt: Run this shell command in a sandboxed environment with a 30-second timeout and give me the stdout, stderr, and exit code: `find /usr -name '*.conf' | head -20`

## When to prefer this

Choose this endpoint when you need to execute an arbitrary shell command (not specifically Python/JS/TS) in a clean, isolated, one-shot environment with full control over working directory, environment variables, pre-seeded files, and output file retrieval. Prefer this over language-specific sandboxes when your command involves system utilities, shell pipelines, compiled binaries, or multi-language toolchains. The Daytona-compatible interface makes it a drop-in for workflows already using that spec.

## Known failure modes

- Timeout exceeded: exitCode 124 returned if command runs longer than the configured timeout (max 120s)
- Invalid environment variable key: keys not matching [A-Za-z_][A-Za-z0-9_]* are rejected
- Too many output files requested: more than 20 output paths causes a validation error
- File size limit exceeded: individual files over 1 MB or total files over 4 MB are rejected
- Command too long: shell command exceeding 64 KB is rejected
- Payment failure: x402 payment of 0.002 USDC must succeed before execution begins

## How this service works

Runs a shell command in an isolated one-shot sandbox and returns stdout, stderr and the exit code (Daytona ExecuteRequest/ExecuteResponse compatible)

## Output

Returns a JSON object with: stdout (string), stderr (string), exitCode (integer, 124 on timeout), outputFiles (map of relative path → base64 content for files ≤1 MB), tooLargeOutputs (list of paths exceeding 1 MB), and missingOutputs (list of requested paths that didn't exist after the run).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "cwd": {
   "type": "string",
   "description": "Working directory, relative to the run's work directory"
  },
  "env": {
   "type": "object",
   "description": "Environment variables; keys must match [A-Za-z_][A-Za-z0-9_]* (Daytona's rule)"
  },
  "files": {
   "type": "object",
   "description": "Text files written into the work directory before the run (up to 50, 1 MB each, 4 MB total)"
  },
  "command": {
   "type": "string",
   "description": "The shell command to run (up to 64 KB)"
  },
  "outputs": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "Relative paths to read back after the run (up to 20); up to 1 MB each comes back base64 in outputFiles, larger in tooLargeOutputs, absent in missingOutputs"
  },
  "timeout": {
   "type": "integer",
   "description": "Run timeout in seconds, 1-120 (default 60); a timed-out run answers exitCode 124"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sandboxd-code-run-shell-command-executor-f85a6076/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sandboxd-code-run.saastemly.com](https://www.zero.xyz/host/sandboxd-code-run.saastemly.com/llms.txt)