Claude Code Mod Builder

What it does

Provides the structure and safety rules for building Claude Code mods written as in-process TypeScript hooks: custom panes, prompt suggestions, slash commands, and automatic follow-ups. Includes type-checking and common API traps to avoid.

When to use it

• When you want to customize your team's Claude Code workflow.
• When you need a repeatable slash command or pane for a frequent task.
• When you're distributing an extension and need it tested before installing.

Steps

1. Define what kind of mod you need: pane, slash command, or automatic follow-up.
2. The assistant builds the TypeScript skeleton with the correct hook shape.
3. Type-checking runs against the generated mod.
4. It's tested in an isolated environment before install.
5. You review the behavior and request adjustments if something's off.
6. Only you decide to install the mod into your real Claude Code setup.

The skill

---
name: claude-code-mod-builder
description: Designs, tests, and installs Claude Code extensions: panes, prompt suggestions, slash commands, and automatic follow-ups as TypeScript hooks.
---

# Claude Code Mod Builder

## 1. What it does

- Provides the structure and safety rules for building Claude Code mods written as in-process TypeScript hooks: custom panes, prompt suggestions, slash commands, and automatic follow-ups. Includes type-checking and common API traps to avoid.

## 2. When to use it

- When you want to customize your team's Claude Code workflow.
- When you need a repeatable slash command or pane for a frequent task.
- When you're distributing an extension and need it tested before installing.

## 3. Step by step

- Define what kind of mod you need: pane, slash command, or automatic follow-up.
- The assistant builds the TypeScript skeleton with the correct hook shape.
- Type-checking runs against the generated mod.
- It's tested in an isolated environment before install.
- You review the behavior and request adjustments if something's off.
- Only you decide to install the mod into your real Claude Code setup.

## 4. Safety rules

- Safety rules: everything ships as a draft first; nothing is sent, published, or paid for without your explicit approval; no data, numbers, or results are ever invented; no credentials or secrets are typed into chat.

## 5. Best practices

- Always review the full draft before approving any send, publish, or payment.
- If real information (data, numbers, results) is missing, ask for it to be flagged as pending instead of invented.
- Keep credentials and keys out of chat; set them in environment variables or your secrets manager.

## 6. GoHighLevel integration

- Where relevant, results can be saved as contacts, tags, tasks, or notes inside your GoHighLevel sub-account.
- No automation inside GHL (workflow, campaign, trigger) activates without your review first.

For Claude Code, save it as ~/.claude/skills/claude-code-mod-builder/SKILL.md. In Cursor, ChatGPT or another assistant, paste it as project instructions.