Halting reviews every AI-suggested command or code snippet before it runs — giving you a plain-English risk summary and a risk level so you can make an informed decision.
How it works
Automatic command analysis (Claude Code hooks)
Once set up, Halting intercepts every Bash and PowerShell command that Claude Code tries to run and shows you a risk analysis in the terminal before it executes:
🛑 Halting — Pre-flight Analysis
─────────────────────────────────────
⚠️ Risk: Warning
📋 This command installs packages from the npm registry and modifies node_modules/. It does not delete files or access the network beyond npm.
─────────────────────────────────────
On-demand analysis (editor panel)
Highlight any code or command in the editor, press Ctrl+Shift+S (Cmd+Shift+S on Mac), and Halting opens a side panel with a full risk breakdown.
Getting started
Halting walks you through setup automatically on first launch:
Command modifies files or installs packages — review before proceeding
🚫 Dangerous
Command deletes files, alters system config, or has high destructive potential
Privacy
Your code and commands are sent to OpenRouter for analysis. Your API key is stored in your OS keychain (Windows Credential Manager / macOS Keychain) and is never written to any settings file.
