A new plugin, Terse, has been developed for Claude Code to mitigate the AI's tendency to produce overly long and conversational responses. The creator noted consistent issues with Claude generating essays filled with slogans, metaphors, and unnecessary recaps, even when using Claude's built-in 'concise' mode or system prompts.
The Terse plugin specifically targets and removes various stylistic elements identified as 'filler'. These include figurative language (metaphors), comparative reframes ('X, not Y'), vague principles (slogans), rhythmic phrasing (cadence), sentences adding no new facts (bloat), and first-person narration. The plugin applies these writing rules across all Claude outputs, including replies, documents, commits, and subagents.
Testing against 20 prompts on a real codebase showed significant reductions. For Claude Fable 5.1, the plugin resulted in 46% fewer words and a 51% lower cost. With Claude Opus 5.5, word count decreased by 54% and cost by 32%. These metrics indicate the plugin's effectiveness in streamlining AI communication and potentially reducing operational expenses associated with token usage.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
A new Claude Code plugin named Terse has been released, designed to reduce the length of Claude's responses by removing conversational filler, metaphors, and slogans. This plugin reportedly halves reply length and lowers token costs, addressing user frustration with verbose AI output.