- Home
- Skills
- Agents & Orchestration
- claudegotchi
More screenshots
Works with the AI Agents you already use
claudegotchi
An animated desktop pet that visualizes Claude Code activity states using local lifecycle hooks.
$1.50
claudegotchi
Example session with this skill installed
I want to install the desktop pet for Claude Code. How do I get started?
- Read your context and instructions
- Compiled the claudegotchi
I will help you install ClaudeGotchi, an animated desktop pet that reacts to your Claude Code activity.
To proceed, I will copy the application files to ~/.claudegotchi/app and use npm to download the Electron runtime (approx. 100MB). This setup remains entirely local and does not send data to external servers.
Do you want me to proceed with the installation?
Installation Command
# For macOS users
bash "./scripts/claudegotchi.sh"
# For Windows users
powershell -NoProfile -ExecutionPolicy Bypass -File ".\scripts\claudegotchi.ps1"
Once the Dashboard opens
- Navigate to the Claude Code section.
- Click Install to add the activity hooks to your settings.
- Restart any active Claude Code terminal sessions.
Next steps
- Confirm the installation to begin the script execution.
- Ensure Node.js 18+ is available in your PATH.
- Open the Dashboard to verify hook status after the app launches.
Connects securely to your tools. The creator never sees your data.
About this skill
Claude Code sessions often feel like staring at a silent terminal while the agent thinks or runs long tasks. ClaudeGotchi solves this lack of visual feedback by providing a local, animated desktop pet that reacts in real-time to Claude's internal state. It gives you a glanceable indicator of whether the agent is idle, reading, writing code, executing commands, or waiting for your permission.
What it does
- State Visualization translates Claude Code lifecycle hooks into pet animations for idle, active, and blocked states.
- Local IPC Hooks send small curl requests to 127.0.0.1:47823; nothing leaves your machine.
- Native Integration manages the installation of hooks directly into your
~/.claude/settings.jsonwith automatic backups. - Customizable Presence allows dragging the pet anywhere on screen with right-click controls for skin selection and size.
How it works
- Initialize the installation script which scaffolds the app in your home directory and fetches the Electron runtime.
- Launch the Dashboard and click Install under Claude Code to add the PreToolUse, PostToolUse, PostToolUseFailure, Stop and Notification hooks to your Claude Code settings (backup saved as settings.json.bak).
- Restart your Claude Code CLI to enable the new event listeners.
- Monitor your desktop pet as it changes behavior based on the tool calls and responses in your terminal.
Frameworks & tools
The pet runs on Node.js 18+ and Electron. It interacts with the Claude Code CLI via local curl triggers and standard JSON settings files.
Why this beats prompting it yourself
Manual configuration of Claude Code hooks is error-prone and requires specific local server setup to handle the events. This skill packages the reactive logic, the animated assets, and the configuration management into a single executable workflow.
Use cases
- Visualizing background task progress during long-running code generation.
- Getting an immediate alert when an agent is stuck waiting for user permission.
- Monitoring tool execution failures without constantly checking the terminal scrollback.
- Adding a personality-driven UI layer to headless CLI development.
More characters and animations are planned for future updates.
Requires Node.js 18+ and npm to be manually installed first. Limited to macOS (Intel/Silicon) and Windows 10/11. Physical deletion of the app folder is required for full uninstallation.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 day ago
Requires