Reduces Claude Code token usage by compressing large codebases and documents into compact context. It combines keyword and embedding search, splits code by syntax structure, and reranks results, running locally without an API.
@madhan230205Use this skill whenever the user needs to reduce context bloat, lower token usage, summarize large code/docs corpora, run FTS…
@madhan230205Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
@madhan230205Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient…
@madhan230205Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
@madhan230205Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation…
@madhan230205Build a compact context packet with preprocess, BM25-ranked FTS retrieval, adaptive vector fallback, reranked top-K chunks…
@madhan230205Fetches current, version specific documentation and code examples for a library, so the agent stops working from stale training…
@madhan230205Is this you? Claim your profilePut a plugin at the top of Plugins, from $9
