# Mgrep Code Search

> Semantic code search using mgrep for efficient codebase exploration. This skill should be used when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures. It provides natural language semantic search that complements traditional grep/ripgrep for finding features, understanding intent, and exploring unfamiliar code.

Source: https://skillsagentes.com/skills/intellectronica/agent-skills/mgrep-code-search
Repository: https://github.com/intellectronica/agent-skills
Author: intellectronica
License: CC0-1.0
Updated: hace 6 meses
Context cost: 92 tok installed, 870 tok once triggered, 870 tok with every bundled file
Bundle: 1 file, 3 KB
Permissions requested: none declared

## Install

```bash
npx -y skills add intellectronica/agent-skills --skill mgrep-code-search --agent claude-code
```

## What it does

- Realiza búsquedas semánticas en lenguaje natural sobre código, texto, PDFs e imágenes usando mgrep
- Indexa el repositorio con bunx @mixedbread/mgrep watch, respetando .gitignore y .mgrepignore
- Permite refinar búsquedas con opciones como -m, -c, -a y -s, y restringir por ruta

## Use it when

- El codebase tiene más de 30 archivos no ignorados por git
- Hay estructuras de directorios anidadas
- Se busca por concepto, funcionalidad o intención en vez de una cadena exacta
- Se explora un codebase desconocido o se necesita entender dónde o cómo está implementado algo

## Don't bother when

- Se busca un patrón o símbolo exacto
- Es una refactorización basada en regex
- Se rastrea un nombre específico de función o variable (usar grep/ripgrep en su lugar)

## What triggers it

- "¿Dónde está configurada la autenticación en este proyecto?"
- "¿Cómo manejamos los errores en las llamadas a la API?"
- "Explora cómo funciona la capa de caché en este codebase"
- "Busca semánticamente cómo se procesa el pago en src/services"

## Before you install

- Requiere ejecutar bunx @mixedbread/mgrep (no npm/npx ni instalación directa) y correr `watch` antes de buscar para mantener el índice actualizado.

## Files

- SKILL.md — 3 KB

## SKILL.md

Reproduced verbatim from intellectronica/agent-skills under CC0-1.0. This section is the upstream document and is in English.

# mgrep Code Search

## Overview

mgrep is a semantic search tool that enables natural language queries across code, text, PDFs, and images. It is particularly effective for exploring larger or complex codebases where traditional pattern matching falls short.

## When to Use This Skill

Use mgrep when:
- The codebase contains more than 30 non-gitignored files
- There are nested directory structures
- Searching for concepts, features, or intent rather than exact strings
- Exploring an unfamiliar codebase
- Need to understand "where" or "how" something is implemented

Use traditional grep/ripgrep when:
- Searching for exact patterns or symbols
- Regex-based refactoring
- Tracing specific function or variable names

## Quick Start

### Indexing

Before searching, start the watcher to index the repository:

```bash
bunx @mixedbread/mgrep watch
```

The `watch` command indexes the repository and maintains synchronisation with file changes. It respects `.gitignore` and `.mgrepignore` patterns.

### Searching

```bash
bunx @mixedbread/mgrep "your natural language query" [path]
```

## Search Commands

### Basic Search

```bash
bunx @mixedbread/mgrep "where is authentication configured?"
bunx @mixedbread/mgrep "how do we handle errors in API calls?" src/
bunx @mixedbread/mgrep "database connection setup" src/lib
```

### Search Options

| Option | Description |
|--------|-------------|
| `-m <count>` | Maximum results (default: 10) |
| `-c, --content` | Display full result content |
| `-a, --answer` | Generate AI-powered synthesis of results |
| `-s, --sync` | Update index before searching |
| `--no-rerank` | Disable relevance optimisation |

### Examples with Options

```bash
# Get more results
bunx @mixedbread/mgrep -m 25 "user authentication flow"

# Show full content of matches
bunx @mixedbread/mgrep -c "error handling patterns"

# Get an AI-synthesised answer
bunx @mixedbread/mgrep -a "how does the caching layer work?"

# Sync index before searching
bunx @mixedbread/mgrep -s "payment processing" src/services
```

## Workflow

1. **Start watcher** (once per session or when files change significantly):
   ```bash
   bunx @mixedbread/mgrep watch
   ```

2. **Search semantically**:
   ```bash
   bunx @mixedbread/mgrep "what you're looking for" [optional/path]
   ```

3. **Refine as needed** using path constraints or options:
   ```bash
   bunx @mixedbread/mgrep -m 20 -c "refined query" src/specific/directory
   ```

## Environment Variables

Configure defaults via environment variables:

| Variable | Purpose |
|----------|---------|
| `MGREP_MAX_COUNT` | Default result limit |
| `MGREP_CONTENT` | Enable content display (1/true) |
| `MGREP_ANSWER` | Enable AI synthesis (1/true) |
| `MGREP_SYNC` | Pre-search sync (1/true) |

## Important Notes

- Always use `bunx @mixedbread/mgrep` to run commands (not npm/npx or direct installation)
- Run `bunx @mixedbread/mgrep watch` before searching to ensure the index is current
- mgrep respects `.gitignore` patterns automatically
- Create `.mgrepignore` for additional exclusions

---

Skills Agentes — https://skillsagentes.com/skills/intellectronica/agent-skills/mgrep-code-search