Repomix — Codebase Packer & Analyzer

Pack entire codebases into a single, AI-friendly file for analysis. Repomix intelligently collects repository files, respects .gitignore, runs security checks, and generates structured output optimized for LLM consumption.

When to Use

• - "Analyze this repo" / "Explore this codebase"
• "What's the structure of facebook/react?"
• "Find all authentication-related code"
• "How many tokens is this project?"
• "Pack this repo for AI analysis"
• "Show me the main components of vercel/next.js"

Quick Reference

Pack a Remote Repository

CODEBLOCK0

Always output to a temporary directory (/tmp on Unix, %TEMP% on Windows) for remote repositories to avoid polluting the user's working directory.

Pack a Local Directory

CODEBLOCK1

Key Options

Option	Description
INLINECODE3	Output format: xml (default, recommended), markdown, plain, INLINECODE7
INLINECODE8

Tree-sitter compression (~70% token reduction) — use for large repos | | --include <patterns> | Include only matching patterns (e.g., "src/**/*.ts,**/*.md") | | --ignore <patterns> | Additional ignore patterns | | --output <path> | Custom output path (default: repomix-output.xml) | | --remote-branch <name> | Specific branch, tag, or commit (for remote repos) |

Workflow

Step 1: Pack the Repository

Choose the appropriate command based on the target:

CODEBLOCK2

Step 2: Check Command Output

The command displays:

• - Files processed: Number of files included
• Total characters: Size of content
• Total tokens: Estimated AI tokens
• Output file location: Where the file was saved

Note the output file location for subsequent analysis.

Step 3: Analyze the Output

Structure overview:

1. 1. Search for the file tree section (near the beginning of the output)
2. Check the metrics summary for overall statistics

Search for patterns (use the output file path from Step 2):
CODEBLOCK3

Read specific sections using offset/limit for large outputs.

Step 4: Report Findings

• - Metrics: Files, tokens, size from command output
• Structure: Directory layout from file tree analysis
• Key findings: Based on pattern search results
• Next steps: Suggestions for deeper exploration

Best Practices

1. 1. Use --compress for large repos (>100k lines) to reduce token usage by ~70%
2. Use pattern search first before reading entire output files
3. Use a temporary directory for output (/tmp on Unix, %TEMP% on Windows) to keep the user's workspace clean
4. Use --include to focus on specific parts of a codebase
5. XML is the default and recommended format — it has clear file boundaries for structured analysis

Output Formats

Format	Best For
XML (default)	Structured analysis, clear file boundaries
Markdown

Human-readable documentation | | Plain | Simple grep-friendly output | | JSON | Programmatic/machine analysis |

Error Handling

• - Command fails: Check error message, verify repository URL/path, check permissions
• Output too large: Use --compress, narrow scope with INLINECODE20
• Network issues (remote): Verify connection, suggest local clone as alternative
• Pattern not found: Try alternative patterns, check file tree to verify files exist

Security

Repomix automatically excludes potentially sensitive files (API keys, credentials, .env files) through built-in security checks. Trust its security defaults unless the user explicitly requests otherwise.