skills.rest
MEDICALCOR
MEDICALCOROFFICIAL
Explore all skills by this author →
GitHub

claude-settings-expert

Configure Claude Code settings.json permissions, sandbox options, and hooks.

Updated Aug 23, 2026
Search Tags:#security#claude code#hooks#permissions#configuration#environment variables#sandbox#settings.json
One-click install
npx skills add https://github.com/MEDICALCOR/medicalcor-core --skill claude-settings-expert-medicalcor
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: claude-settings-expert
Source: https://github.com/MEDICALCOR/medicalcor-core/tree/main/.claude/skills/anthropic/claude-settings-expert
Command: npx skills add https://github.com/MEDICALCOR/medicalcor-core --skill claude-settings-expert-medicalcor

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Managing Claude Code's behavior, permissions, and environment through settings.json can be intricate due to its hierarchy, sandbox options, and hook configurations. This Skill provides clear, expert guidance, ensuring you maintain control and security over your AI agent.

Core Features & Use Cases

  • Comprehensive Settings Guidance: Understand settings.json hierarchy (user, project, local, enterprise) and how to apply configurations effectively.
  • Permission Management: Configure granular allow, deny, and ask rules for tools like Bash, Read, Write, and WebFetch, enhancing security.
  • Sandbox & Environment Control: Enable filesystem isolation, configure network access, and set environment variables for secure and consistent operations.
  • Use Case: "I need to restrict Claude Code from accessing sensitive .env files and prevent it from running rm -rf commands, while still allowing git status. How do I configure settings.json for this?"

Quick Start

Show me how to set up settings.json to deny Claude Code from reading any .env files in my project.