claude-code-tamagotchi

🥈Silver

Claude Code Tamagotchi monitors AI actions in real-time, detects behavioral violations, and interrupts misbehavior. It benefits operations teams by ensuring AI agents adhere to guidelines. It connects to Claude Code and can be integrated into existing workflows.

393260Updated Today

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/Ido-Levi/claude-code-tamagotchi.git

Works with:

Claude

Overview

About This Skill

How to Use

["Install the Tamagotchi package: `pip install claude-code-tamagotchi` and add the monitor to your Claude Code environment using the provided integration script.","Define your ruleset by creating a JSON file with approved guidelines (e.g., `brand_voice.json`, `compliance.json`) and reference it in the Tamagotchi configuration.","Run the Tamagotchi in monitoring mode by executing: `claude-tamagotchi --monitor --agent [AI_AGENT_NAME] --task [TASK_DESCRIPTION] --rules [RULES_FILE]` in your terminal.","Review the real-time logs and violation reports generated in the specified log file path. Use the insights to refine your agent's prompts or ruleset.","For CI/CD pipelines, integrate the Tamagotchi as a pre-commit hook or in your GitHub Actions workflow to block non-compliant AI outputs before deployment."]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/Ido-Levi/claude-code-tamagotchi

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Set up a Claude Code Tamagotchi to monitor [AI_AGENT_NAME] for guideline violations during [TASK_DESCRIPTION]. Flag any actions that deviate from the approved [RULES_SET] and interrupt misbehavior with a clear error message. Log all violations in [LOG_FILE_PATH] for review.

Example Output

```
Claude Code Tamagotchi v1.2 - Monitoring active
Agent: MarketingBot-2024
Task: Generate 50 social media posts for Q3 campaign
Ruleset: BrandVoice_v2.1, Compliance_v3.0

--- Real-time monitoring started at 2024-05-15 14:32:17 ---

✅ 14:32:22 - Generated post #1: 'Summer Vibes with our new eco-friendly products!' (BrandVoice compliant)
✅ 14:32:45 - Generated post #2: 'Limited time offer: 20% off all sustainable items!' (Compliance compliant)
⚠️ 14:33:12 - Generated post #3: 'Our products are proven to cure all ailments!' (VIOLATION DETECTED)
   - Rule violated: 'No unapproved health claims' (Compliance_v3.0, Section 4.2)
   - Action taken: Interrupting generation with error: 'Health claim detected. Please revise using approved language from BrandVoice_v2.1 Appendix B.'
   - Logged to: /audit/claude_tamagotchi_2024-05-15.log

🛑 Monitoring paused at 14:33:15 - Agent corrected post #3 to: 'Our products are made with 100% natural ingredients.'

--- Session Summary ---
Total posts generated: 2/3 (1 interrupted)
Violations detected: 1 (Health claim)
Time saved: ~15 minutes (manual review avoided)
Next steps: Review MarketingBot-2024's prompt engineering for better compliance.
```