Navigable codebase index for Claude Code — stop grepping, start navigating
Initialize nogrep for this project. Follow these steps exactly in order.
Disable nogrep for this project.
Enable nogrep for this project.
Answer the user's question using the nogrep codebase index. Follow these steps exactly:
Show the current status of the nogrep index.
A Claude Code plugin that gives AI agents a navigable index of any codebase, so they stop doing blind grep/find exploration.
nogrep generates a structured .nogrep/ directory with a reverse index and thin context nodes (markdown files). When you need Claude Code to find something, run /nogrep:query — it reads 2 context files instead of running 20 grep commands.
In Claude Code:
/plugin and go to the Marketplaces tab+ Add Marketplace and enter alirezanasseh/nogrepnogrep/reload-plugins to activate/nogrep:init — Claude analyzes your codebase and generates the index/nogrep:query where is auth handled?Phase 1: Collect signals (scripts — file tree, deps, git churn, entry points)
Phase 2: Detect stack (Claude — language, frameworks, domain clusters)
Phase 3: Analyze clusters (Claude — per-domain context nodes from trimmed source)
Phase 4: Write index (scripts — .nogrep/ files, _index.json, CLAUDE.md patch)
Scripts handle data collection and file I/O. Claude does all the analysis work directly during the session — no API keys needed.
| Command | Description |
|---|---|
/nogrep:init | Generate the full codebase index |
/nogrep:update | Incrementally update stale nodes |
/nogrep:query <question> | Query the index, read matched context files, and get an answer |
/nogrep:status | Show index health and freshness |
/nogrep:on | Enable nogrep |
/nogrep:off | Disable nogrep |
.nogrep/
├── _index.json # reverse index (tags → files, keywords → files, paths → context)
├── _registry.json # source path → context file mapping
├── _taxonomy.json # allowed tags for this project
├── domains/ # one file per business domain
├── architecture/ # cross-domain architectural concerns
├── flows/ # multi-domain business flows
└── entities/ # data models
Each context node is a thin markdown file with YAML frontmatter — purpose, public surface, gotchas, and tags. Nodes include a ## Manual Notes section that is never overwritten by updates.
nogrep stores its enabled state in your project's .claude/ directory:
.claude/settings.json — team settings (commit to repo).claude/settings.local.json — personal overrides (gitignored)Source code lives on the develop branch. The main branch contains only the built plugin and is updated automatically by CI on every push to develop.
git clone -b develop https://github.com/alirezanasseh/nogrep
cd nogrep
npm install
npm run build
npm test
MIT
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 alirezanasseh/nogrep --plugin nogrepSemantic code search for Claude Code. Automatically indexes your project and provides intelligent search capabilities.
Optimized file search, semantic indexing, and persistent memory for Claude Code — with optional sync to a self-hosted web dashboard
Structural codebase indexing for efficient navigation. Reduces token consumption by 60-80% through targeted line-range reads instead of full file scans.
Lightning-fast semantic code search with auto-indexing. Automatically manages sgrep watch during Claude sessions.
Beacon — semantic code search for Claude Code
Codebase intelligence — semantic search workflows, dependency graph analysis, and context artifact exploration for SocratiCode