context-compressor
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
$ npx -y skills add Madhan230205/token-reducer --agent claude-codeShips with claude-token-reducer. Installing the plugin gets this agent.
How it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Compresses top retrieval chunks into citation-rich summary packets that preserve intent while cutting token usage.
⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST chunking, reranking. No API needed.
Repo: Madhan230205/token-reducer
Other agents on claude-token-reducer.
- hybrid-retriever
Runs hybrid retrieval with strict FTS-first policy, BM25 lexical ranking, vector merge, and top 3-5 reranking for token-efficient context selection.
Open agent - noise-chunker
Preprocesses large corpora by removing low-signal noise and creating overlap-aware chunks for retrieval indexing.
Open agent - se-ops-delegate
Delegates software engineering operations to focused subagents using compressed context packets to keep the main conversation lean.
Open agent