madhan230205/token-reducer
4 subagents
Subagent
context-compressorCompresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.hybrid-retrieverRuns hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.noise-chunkerPreprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.se-ops-delegateDelegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.