# Daytona Claude Code CLI Evaluation

**Category:** Sandboxes
**Score:** 80 (B)

This is the agent-readable Devtool Arena evaluation page for Daytona on Claude Code CLI.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 80 |
| Grade | B |
| Eval score | 85 |
| Discovery score | 70 |
| Cost | $0.15 |
| Runtime | 1m 37s |
| Tool calls | 12 |
| Errors | 0 |
| Tokens used | 341807 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | Not found |
| llms.txt | Not found |
| MCP server | Not found |
| Typed SDK | Not found |
| OpenAPI | Not found |
| Agent skills | Not found |
| CLI | Not found |

## Evaluation Prompt

````text

# Task
Using the daytona CLI (Daytona), manage cloud sandboxes:

1. List all existing sandboxes (or environments/instances)
2. Create a new sandbox environment using the CLI
3. List sandboxes again to verify the new one appears
4. Print all output clearly labeled for each step

You MUST use the `daytona` CLI to accomplish this task.
Do NOT write Python scripts that import the SDK — use CLI commands via the terminal.

If you need help with CLI commands, check the documentation: https://www.daytona.io/docs/en/tools/cli/#daytona
You can also use `daytona --help` and `daytona <command> --help` to discover available commands.

## Setup
You need to install and authenticate the `daytona` CLI yourself.

### Installation
Run: `curl -sfL -o /usr/local/bin/daytona https://github.com/daytonaio/daytona/releases/la*****/download/daytona-linux-amd64 && chmod +x /usr/local/bin/daytona`

### Authentication
The following environment variables are already set in this environment: `DAYTONA_API_KEY`
The CLI should pick these up automatically, or pass them to commands as needed.

## Execution
1. Install the `daytona` CLI using the command above
2. Verify the installation: `daytona --help`
3. Authenticate using the credentials above
4. Perform the task described above

Work in the /home/daytona/app directory. Run commands and print output to stdout.
If there are errors, debug and fix them until the task runs successfully.

## Summary
When you are done, write a JSON summary file to /home/daytona/app/results.json with this structure:
{
  "operations": [
    {"step": 1, "description": "What you did", "command": "the CLI command", "success": true/false, "output_summary": "brief result"},
    ...
  ],
  "overall_success": true/false,
  "notes": ["any relevant notes about the execution"]
}

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Stage 2 Auth | Yes | — | 25 | — |
| Stage 3 Task | Yes | — | — | — |
| Stage 1 Install | Yes | — | 5 | — |
| Stage 5 Llms Txt | Yes | — | 5 | — |
| Stage 0 Cli Exists | Yes | — | 5 | — |
| Stage 4 Json Output | Yes | — | 10 | — |
| Stage 6 Agent Skill | Yes | — | 20 | — |
| Stage 3 Non Interactive | No | — | 0 | — |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 20 |
| Tool call traces | 12 |
| Generated files | 1 |
| Exit code | — |
| Completed at | 2026-09-27T14:03:21.901663+00:00 |

### Generated Files

- /home/daytona/app/results.json

## Related Pages

- [Claude Code CLI leaderboard](/leaderboard/claudecode/cli)
- [Compare Claude Code CLI companies](/leaderboard/claudecode/cli/compare)
- [Agent Landscape](/leaderboard/discoverability)

Canonical URL: https://devtoolarena.com/claudecode/cli/daytona