By kcem
Fast, precise codebase exploration via universal-ctags — symbol search, outlines, and exact code retrieval without reading whole files
Fast, precise codebase exploration via universal-ctags. A pure skill plugin that teaches AI coding agents to search symbols, browse outlines, and retrieve exact code ranges — instead of reading whole files. No MCP server, no runtime dependencies beyond the ctags binary.
ctags to generate a standard .ctags tags fileThe agent decides autonomously when to index, re-index, or search — no manual commands needed.
Install universal-ctags (must say "Universal Ctags" in ctags --version):
# macOS
brew install universal-ctags
# Ubuntu / Debian
apt install universal-ctags
claude plugin marketplace add https://github.com/kcem/code-index.git
claude plugin install code-index@code-index
copilot plugin install kcem/code-index
pi install git:github.com/kcem/code-index
Or via npm: pi install npm:pi-code-index
Copy skills/code-indexing/SKILL.md into your agent's skills directory. Works with any agent supporting the Agent Skills format.
All 100+ languages supported by universal-ctags — Python, TypeScript, JavaScript, Go, Rust, Java, C/C++, Ruby, PHP, and many more. No configuration needed — languages are detected automatically.
MIT
100% free, 100% open source, 100% powered by coffee. If it saved your tokens, a coffee keeps the next plugin brewing.
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 kcem/code-index --plugin code-indexAuto-generates and maintains ctags index for efficient code navigation, reducing token usage by providing precise symbol-to-location lookups
Tree-sitter backed code indexing and retrieval for Claude Code. Precise function extraction, cross-file callers, test discovery, and scope-aware grep.
Structural codebase indexing for efficient navigation. Reduces token consumption by 60-80% through targeted line-range reads instead of full file scans.
Semantic code search for Claude Code. Automatically indexes your project and provides intelligent search capabilities.
Fast code search for Android/Kotlin/Java, iOS/Swift/ObjC, Dart/Flutter, TypeScript/JavaScript, Rust, Ruby, C#, PHP, Python, Go, Perl, C++, Protocol Buffers, and WSDL/XSD projects
Fast and token-friendly code reading for AI coding agents. Symbol-aware MCP tools that replace cat/grep with ~85% fewer tokens, sub-millisecond search, and a raw fallback that preserves cat/grep parity byte-for-byte.