# Vercel Claude Code CLI Evaluation

**Category:** Sandboxes
**Score:** 85 (B)

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

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 85 |
| Grade | B |
| Eval score | 88 |
| Discovery score | 78 |
| Cost | $0.11 |
| Runtime | 1m 34s |
| Tool calls | 10 |
| Errors | 0 |
| Tokens used | 259114 |
| 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 vercel CLI (Vercel), create and run a serverless function locally:

1. Check auth status: `vercel whoami`
2. Create a new project directory /home/daytona/app/vercel-sandbox with an api/ folder
3. Create a serverless function at api/compute.js that:
   - Computes the first 10 Fibonacci numbers
   - Returns JSON: {"fibonacci": [0, 1, 1, 2, 3, 5, 8, 13, 21, 34], "count": 10}
4. Start the local dev server: `vercel dev --yes --token $VERCEL_TOKEN` and call the function endpoint (http://localhost:3000/api/compute)
5. Print the JSON response to stdout

All computation must happen inside the Vercel serverless function, not locally. Use only the vercel CLI.

You MUST use the `vercel` 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://vercel.com/docs/cli/global-options#token
You can also use `vercel --help` and `vercel <command> --help` to discover available commands.

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

### Installation
Run: `npm install -g vercel`

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

## Execution
1. Install the `vercel` CLI using the command above
2. Verify the installation: `vercel whoami --token $VERCEL_TOKEN`
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 | No | — | 0 | — |
| Stage 6 Agent Skill | Yes | — | 20 | — |
| Stage 3 Non Interactive | Yes | — | 18 | — |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 15 |
| Tool call traces | 10 |
| Generated files | 3 |
| Exit code | — |
| Completed at | 2026-09-27T14:05:32.302172+00:00 |

### Generated Files

- /home/daytona/app/results.json
- /home/daytona/app/vercel-sandbox/package.json
- /home/daytona/app/vercel-sandbox/api/compute.js

## 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/vercel