glincker/glin-profanity ? reverse-engineered prompt
Reverse engineered prompt
Build me an open source profanity and moderation tool that works offline and can be used in both JavaScript and Python.
I want it to catch obvious swear words, leetspeak, and weird Unicode lookalike tricks like f4ck or fυck, and it should also be able to help with related guardrails like basic PII and secret detection. It should be fast enough for real apps, support a bunch of languages, and have a simple API that feels easy to drop into chat apps or content moderation pipelines.
Please include a small React friendly hook or helper for frontend use, and an MCP server so AI assistants like Cursor or Claude can use it too. Make sure there is a clean demo page, good tests, and a benchmark setup so I can see how it performs. If you need to check current docs or package details online, go ahead and look them up.
Are you gonna build this?
make sure you review the code using coderabbit