permission-analyzer

Analyze session logs to generate Claude Code permissions JSON.

19|6|Updated Aug 18, 2025

Search Tags:#automation #permissions #Claude Code #CLI #session #tools #analyze

One-click install

npx skills add https://github.com/ArjenSchwarz/agentic-coding --skill permission-analyzer

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: permission-analyzer
Source: https://github.com/ArjenSchwarz/agentic-coding/tree/main/claude/skills/permission-analyzer
Command: npx skills add https://github.com/ArjenSchwarz/agentic-coding --skill permission-analyzer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Generate Claude Code permissions config from actual tool usage in past sessions. This helps ensure you only grant what is actually needed and automatically avoid dangerous operations.

Core Features & Use Cases

Analyze session logs to extract Bash command prefixes and MCP tools actually used.
Produce a ready-to-merge permissions JSON structure under the "permissions" key.
Provide safe deny rules for dangerous commands and sensitive paths (e.g., .env, secrets/).
Merge into existing .claude/settings.json when present, preserving other settings.

Quick Start

Run the analysis: ~/.claude/skills/permission-analyzer/scripts/analyze_permissions.py Review the JSON output and use the tool to merge into your project’s .claude/settings.json if present.