A high-performance, polyglot code-analysis graph for coding agents — cross-language, cross-process, and dynamic-dispatch edges that grep and LSP can't follow. 100% local, MCP-native.
Skill Claude CodeCodex
Add tree-sitter language support to omniweave end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in omniweave.
Skill Claude CodeCodex
Benchmark OmniWeave retrieval quality on a real codebase by comparing agent behavior with vs without OmniWeave. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a omniweave version (the local dev build or a published npm version) against a language's repo.