mgrep-code-search 精选

个人 agent skills 合集，涵盖多种日常与工程场景。原文：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.

仓库级简介：该 skill 尚无单独撰写的中文摘要

办公 Claude Code MCP 客户端 CC0-1.0 295

在 GitHub 打开

安装方式

cp -r skills/mgrep-code-search ~/.claude/skills/mgrep-code-search

把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同，Claude Code 默认是 ~/.claude/skills/

整仓一次性获取：git clone --depth 1 https://github.com/intellectronica/agent-skills.git

依赖与权限

无需 API Key
无需联网
依赖外部命令：npm npx ripgrep
以上为按正文与 frontmatter 自动推断的信号，仅供参考；安装前建议先阅读原文。

SKILL.md 正文

来源 intellectronica/agent-skills@9b0e00a · 许可 CC0-1.0 · 内容未修改

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:

bunx @mixedbread/mgrep watch

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

Searching

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

Search Commands

Basic Search

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

# 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

Start watcher (once per session or when files change significantly):

   bunx @mixedbread/mgrep watch

Search semantically:

   bunx @mixedbread/mgrep "what you're looking for" [optional/path]

Refine as needed using path constraints or options:

   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