Juicebox Install AuthSAFE

Model-agnostic agent-skills platform with a harness-free canonical layer, verified adapters, and the ccpi package manager. Explore at tonsofskills.com.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: juicebox-install-auth
description: 'Install and configure Juicebox PeopleGPT API authentication.

  Use when setting up people search or initializing Juicebox.

  Trigger: "install juicebox", "setup juicebox", "juicebox auth".

  '
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(pip:*), Grep
version: 1.16.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- recruiting
- juicebox
compatibility: Designed for Claude Code
---
# Juicebox Install & Auth

## Overview

Set up Juicebox PeopleGPT API for AI-powered people search across 800M+ professional profiles.

## Prerequisites

- Juicebox account at [app.juicebox.ai](https://app.juicebox.ai)
- API key from Dashboard > Settings > API Keys
- Node.js 18+ or Python 3.8+

## Instructions

### Step 1: Install SDK

```bash
npm install @juicebox/sdk
# or: pip install juicebox-sdk
```

### Step 2: Configure Authentication

```bash
export JUICEBOX_API_KEY="jb_live_..."
echo 'JUICEBOX_API_KEY=jb_live_your-key' >> .env
```

### Step 3: Verify Connection

```typescript
import { JuiceboxClient } from '@juicebox/sdk';
const client = new JuiceboxClient({ apiKey: process.env.JUICEBOX_API_KEY });

const results = await client.search({ query: 'engineer', limit: 1 });
console.log(`Connected! ${results.total} profiles available`);
```

```python
from juicebox import JuiceboxClient
client = JuiceboxClient(api_key=os.environ['JUICEBOX_API_KEY'])
results = client.search(query='engineer', limit=1)
print(f'Connected! {results.total} profiles')
```

## Error Handling

| Error | Code | Solution |
|-------|------|----------|
| Invalid API key | 401 | Verify at app.juicebox.ai/settings |
| Plan limit exceeded | 403 | Upgrade plan or check quota |
| Rate limited | 429 | Check `Retry-After` header |

## Output

Produce a redacted authentication receipt with environment, secret-reference status, least-privilege scope, sandbox fixture classification, source/destination approval, suppression and `contacts_exported=0` checks, owner approval, and cleanup confirmation. Never include API keys, identities, or contact data.

## Examples

`env=staging; credential=secret-reference; scope=read-sandbox; fixture=synthetic; suppression=pass; contacts_exported=0; cleanup=verified` is a safe connection-check result.

## Resources

- [Juicebox Docs](https://docs.juicebox.work)
- [PeopleGPT](https://juicebox.ai/peoplegpt)

## Next Steps

After auth, proceed to `juicebox-hello-world`.

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.