# Codebase Indexing

> Build and maintain scalable repository indexes for lexical, structural, symbol, and semantic retrieval with bounded context.

- Skill: `nafeeur/codebase-indexing` (Agent Skill)
- Install (CLI): `npx skillmds@latest add nafeeur/codebase-indexing`
- Raw SKILL.md: https://api.skillmd.com/api/skills/nafeeur/codebase-indexing/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: nafeeur (https://skillmd.com/u/nafeeur)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/nafeeur/codebase-indexing

---


# Codebase Indexing

- Use tracked-file discovery and repository ignore rules before reading content.
- Skip binaries, generated outputs, dependency trees, and oversized artifacts by default.
- Chunk on language structure when available, with bounded line overlap and source coordinates.
- Store content hashes for incremental refresh and preserve path/language metadata.
- Combine lexical FTS, symbol/navigation tools, and optional embeddings rather than relying on one retrieval method.
- Evaluate retrieval on real tasks: entry-point discovery, call-chain tracing, correct edit location, and related tests.