Madhan230205

Madhan230205/token-reducer

Plugin Claude Code

Plugin marketplace listing 1 plugin: claude-token-reducer.

Madhan230205/token-reducer

Plugin Claude Code

Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.

Madhan230205/token-reducer

Agent

Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.

Madhan230205/token-reducer

Agent

Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.

Madhan230205/token-reducer

Agent

Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.

Madhan230205/token-reducer

Agent

Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.

Madhan230205/token-reducer

Command

Build a compact context packet with preprocess, BM25-ranked FTS retrieval, adaptive vector fallback, reranked top-K chunks (default 3 from settings), relevance-floor filtering, and compression.

Madhan230205/token-reducer

Hook

Runs when you submit a prompt, before the agent sees it, executing userprompt_guard.py via python. From Madhan230205/token-reducer.

Madhan230205/token-reducer

Skill Claude CodeCodex

Use this skill whenever the user needs to reduce context bloat, lower token usage, summarize large code/docs corpora, run FTS plus embeddings retrieval, rerank top chunks, and produce compact context packets before implementation work. Also trigger when users say context is too long, reduce tokens, optimize prompt…