Codebase search and context retrieval using hybrid semantic/lexical search with neural reranking

GitHub stars
402

Install

/plugin install context-engine@context-engine-skills

Run it inside Claude Code after adding the marketplace with /plugin marketplace add Context-Engine-AI/Context-Engine.

Contents

Discovered from source

Skills 1

Context Engine

When the context-engine MCP server is connected, this workspace is indexed: for any question about the codebase, call repo_search FIRST, before ls/find/Grep/Read, and again whenever you move to a new area; for how/why questions that span several files use context_answer. Results are verified source with exact line ranges: treat them as already read. Use Grep only to confirm an exact literal in a file you already know, or to count. For questions asking for every/all sites, run one repo_search per distinct pattern (queries=[...]) and follow the refs. If the tools are listed as deferred, load them with ToolSearch first.

NeedTool
Find code by behavior, concept, error text or identifierrepo_search (queries=[...] for several at once; under, language, path_glob to narrow)
Explain how/why across several files, with citationscontext_answer
Definition, callers, callees, importers, references of a symbolsymbol_graph (several names: A|B|C)
Multi-hop impact before a changegraph_query
Code that may live in another indexed repocross_repo_search

Before editing, fetch every involved symbol in one call; before a rename or signature change, get every site with symbol_graph query_type=references. Search again only after learning something new.

Sponsors

Details

Marketplace
Context-Engine-AI/Context-Engine
Category
Community