Built a context firewall for AI coding tools over the weekend : here's why and how

Every time you paste a log file into Cursor, or ask Claude Code to debug a production error, you're probably leaking something you shouldn't. API keys. Patient emails. Bearer tokens. Production AWS credentials. They flow into prompts silently, by default, with no warning. I spent this weekend building ContextDuty to fix that. What it does ContextDuty is a local-first context firewall. It sits between your files and your AI assistant, scanning and redacting sensitive values before the prompt leav