A Claude Code plugin rewrites Claude’s answers in plain English

Developer Mike Gvozdev has published claudish-to-english on GitHub, an MIT-licensed open source plugin for Claude Code. It shows a simplified version of every Claude message, generated locally by a model running through Ollama. The default is Gemma 4 at 26 billion parameters, roughly a 17 GB download. Gvozdev calls the project a working prototype.
The hook fires on the MessageDisplay event and hands the finished message text to the local model. Everything it changes is cosmetic: reasoning, tool calls, and the saved transcript keep the original wording, and if Ollama is unreachable or the request hangs, Claude Code just shows the original text.
The plugin has been submitted for review to Anthropic’s community marketplace. Until it clears, you install it straight from the author’s repo.
Up next
OpenAI halts some internal work with its unreleased Astra model
OpenAI has halted some internal work with Astra, an unreleased model, over concerns about the cyber threat it could pose. High-capability models now run in isolated test environments with added monitoring and detection tooling.
Related stories
- Tokendoctor cut its author’s Claude Code cost 38%
- memsaga gives Claude Code’s memory files a git history
- Intent-lens spells out Claude Code calls before they run
- Codedict cuts Claude Code tokens 63%, but cost only 26%
- claude-files-pane shows Claude Code’s file reads live
- lcc cut one Claude Code session 49.5% without a summary
Comments
No comments yet. Be the first.
Join the conversation
Sign in to leave a comment. It appears after moderation.

