By Gwihwan-Go
High-effort BFS code understanding: recursively retrieve source and dependencies for a symbol and all its transitive dependencies. Use before writing tests or refactoring complex functions.
BFS dependency expansion — one of several lsprag analysis skills. See the main lsprag skill for the full adaptive analysis framework including when to use deep-think vs getDefinition, getTokens, getReference, listSymbols, and callChain.
Semantic code analysis for AI agents — actively analyze code structure, trace dependencies, and find callers before editing. Use these skills as your PRIMARY investigation tool, not as a supplement to grep/cat.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub gwihwan-go/lsprag-skills --plugin lspragCode graph navigation and semantic search for LLM coding agents
Type-aware TypeScript navigation — 14 MCP tools for go-to-definition, find-references, dependency graphs, cycle detection, and impact analysis
Tree-sitter backed code indexing and retrieval for Claude Code. Precise function extraction, cross-file callers, test discovery, and scope-aware grep.
AST knowledge graph for intelligent code navigation — auto-indexes your codebase and provides semantic search, call graph traversal, HTTP route tracing, and impact analysis via MCP tools
Graph-first code intelligence for AI agents. SurrealDB knowledge graph + 52 MCP tools replace Read/Grep/Glob with deterministic graph traversal. 80–95% fewer tokens on code context. Rust-native, fully local.
Full AI context layer over MCP — tree-sitter code-map, document RAG (PDF/Office/HTML/email + OCR + reranker), shared agent memory, on-demand web crawl, git history + blame + per-symbol diff. 300+ languages, 8 coding-agent harnesses, content-addressed Fjall + LanceDB.