omen
Code intelligence for AI agents. Complexity, hotspots, and tech debt analysis over MCP.
claude mcp add --transport stdio panbanda-omen omen
How to use
Omen is a code analysis CLI that surfaces signals about your codebase, helping AI assistants understand hotspots, debt, and potential risk areas. When you run the Omen CLI, it analyzes your repository to generate reports on complexity (cyclomatic and cognitive), self-admitted technical debt, dead code, git churn, and code clones. The resulting outputs guide you to parts of the codebase that are most likely to benefit from review, refactoring, or additional testing. You can use Omen's signals to focus code review, improve test coverage, and prioritize technical debt reduction. The tool is designed to run locally in your project workspace and can be integrated into CI pipelines to provide ongoing quality signals during development and release cycles.
How to install
Prerequisites:
- Rust and Cargo installed on your system (https://www.rust-lang.org/tools/install).
- Optional: you may prefer to install via cargo if you want a global binary.
Installation steps:
-
Install the Omen CLI from crates.io: cargo install omen-cli
-
Verify installation: omen --version
-
(Optional) If you prefer to run directly from source, clone the repository and build: git clone https://github.com/panbanda/omen.git cd omen cargo build --release
The built binary will be at target/release/omen
-
Add a quick alias or ensure the binary is in your PATH, so you can run omen from any project directory.
Additional notes
Tips and troubleshooting:
- Ensure your project has a Cargo.toml or appropriate language project files so Omen can analyze dependencies and code structure.
- If you see low signal output, try running in a larger scope (entire workspace) or exclude generated code that may skew metrics.
- Omen reports may include references to cyclomatic and cognitive complexity per function/file; use these to identify hotspots before refactoring.
- For CI integration, cache Omen outputs between runs to speed up pipelines and avoid re-analyzing unchanged parts of the codebase.
- Environment variables you may encounter: OMEN_CONFIG (path to a custom config), OMEN_OUTPUT_FORMAT (e.g., json, pretty). Adjust per your workflow.
- If you encounter permission or path errors, ensure the binary is accessible in your shell PATH and that you have execute permissions on the binary.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
web-eval-agent
An MCP server that autonomously evaluates web applications.
spec-coding
Transform feature ideas into production-ready code through systematic Spec-Driven Development 通过系统化的**规格驱动开发**,将功能想法转化为可投入生产的代码
just
Share the same project justfile tasks with your AI Coding Agent.
mcp-loxone
An opinionated Model Context Protocol (MCP) server for controlling Loxone home automation systems.
cc-audit
AI-free static security scanner for Claude Code artifacts (Skills, Hooks, MCP configs). Detects data exfiltration, prompt injection, and supply chain risks with deterministic, reproducible results.