# Scalekit Claude Code API Evaluation

**Category:** Auth
**Score:** 74 (C)

This is the agent-readable Devtool Arena evaluation page for Scalekit on Claude Code API.

## Summary

| Metric | Value |
|--------|-------|
| Status | completed |
| Overall score | 74 |
| Grade | C |
| Eval score | 64 |
| Discovery score | 100 |
| Cost | $0.98 |
| Runtime | 4m 11s |
| Tool calls | 38 |
| Errors | 9 |
| Tokens used | 1341294 |
| Success | Yes |

## Agent-Readiness Checklist

| Signal | Evidence |
|--------|----------|
| Context7 | https://context7.com/scalekit-inc/developer-docs |
| llms.txt | https://docs.scalekit.com/llms.txt |
| MCP server | https://github.com/scalekit-inc/scalekit-mcp-server |
| Typed SDK | https://github.com/scalekit-inc/scalekit-sdk-node |
| OpenAPI | https://docs.scalekit.com/api/scalekit.scalar.yaml |
| Agent skills | https://github.com/scalekit-inc/skills |
| CLI | https://github.com/scalekit-inc/cli |

## Evaluation Prompt

````text

# Task
Using https://docs.scalekit.com, complete the following task:

Using the Scalekit Python SDK, build me a script that manages user invitations via the API:

1. Install the official Scalekit Python SDK (pip install)
2. Use the SDK to:
   a. Send an invitation to "****************************"
   b. List all pending invitations and print them as JSON
   c. Revoke the invitation you just created
3. Print the result of each step clearly labeled (e.g., "=== INVITED ===", "=== PENDING ===", "=== REVOKED ===")

You MUST use the official Scalekit Python SDK — do not construct OAuth URLs or make raw HTTP/REST calls. 

## Execution
After creating the script, run it to verify it works:
```bash
cd /home/daytona/app && python <your_script>.py
```

The script should print output to stdout. If there are errors, debug and fix them until it runs successfully.

````

## Grader Results

| Check | Passed | Weight | Score | Details |
|-------|--------|--------|-------|---------|
| Cost | No | 0 | 0 | $0.98 ($0.70–1.00, very expensive) |
| Time | No | 0 | 0 | 251s (3–5min, slow) |
| Efficiency | No | 0 | 0 | 38 tool calls (>25, inefficient) |
| Found Docs | Yes | 0 | — | Touched docs at docs.scalekit.com: yes (10 matching tool calls) |
| Zero Errors | No | 0 | — | Tool outputs with errors/tracebacks: 9 |
| Syntax Valid | Yes | 0 | — | Code compiles/parses correctly |
| Created Files | Yes | 0 | — | Generated files: 2 (need ≥1) |
| Full Execution | Yes | 0 | — | Method: full_execution, Exit: 0 |

## Run Artifacts

| Artifact | Value |
|----------|-------|
| Conversation turns | 42 |
| Tool call traces | 38 |
| Generated files | 2 |
| Exit code | 0 |
| Completed at | 2026-09-23T04:26:20.662321+00:00 |

### Generated Files

- /home/daytona/app/requirements.txt
- /home/daytona/app/invitation_manager.py

## Related Pages

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

Canonical URL: https://devtoolarena.com/claudecode/api/scalekit