Show HN: Plainspeak, make AI agents write like a human

Plainspeak, a new open-source plugin, bans AI-typical words like 'delve' and 'leverage', filler phrases, and em dashes from AI agent responses to make them sound human. The tool, available via npm and for opencode, Claude Code, and Codex, was announced on Hacker News.

plainspeak Make AI agents write like a person, not a bot. You know the voice. Every reply opens with "Certainly " or "Let's dive in". Em dashes land in every other line. Plainspeak turns that off. What should be simple stays simple. Without plainspeak Let me walk you through a robust, comprehensive solution that leverages cutting-edge technology to seamlessly streamline your workflow. With plainspeak Here is a simple way to save time. What it does 01 Bans the AI words delve, leverage, robust, seamless, utilize, moreover, and more. 02 Bans the filler phrases No "Let's dive in", no "It's important to note", no "I hope this helps". 03 Bans em dashes Split the sentence with a period or a comma. Or write two sentences. Install npm npm i plainspeak opencode { "plugin": "plainspeak" } claude code /plugin install plainspeak@plainspeak codex codex plugin add plainspeak@plainspeak