warden

Runs Warden AI code analysis locally and on GitHub pull requests with warden.toml configuration.

359|32|Updated Jan 27, 2026
One-click install
npx skills add https://github.com/getsentry/warden --skill warden-getsentry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: warden
Source: https://github.com/getsentry/warden/tree/main/skills/warden
Command: npx skills add https://github.com/getsentry/warden --skill warden-getsentry

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates code analysis and review, catching issues before they reach production and ensuring code quality and security.

Core Features & Use Cases

  • Local Code Analysis: Run Warden to check your uncommitted changes before you push.
  • Automated PR Reviews: Integrate Warden into your GitHub Actions for automatic CI checks.
  • Configurable Rules: Define custom analysis rules and triggers using warden.toml.
  • Use Case: Before committing a new feature, run warden to ensure your code adheres to project standards and doesn't introduce security vulnerabilities.

Quick Start

Run warden to analyze your uncommitted code changes.

Frequently Asked Questions about warden

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run AI code review on uncommitted changes locally?

Run AI code review locally by executing the Warden CLI tool to analyze your uncommitted code changes before pushing. It checks your work against project standards to catch security vulnerabilities and quality issues early.

Can I automate AI code review for pull requests in GitHub Actions?

Yes, you can automate AI code review by integrating Warden into your GitHub Actions workflow for automatic CI checks. It posts inline comments and suggested fixes directly on your pull requests.

How do I configure custom rules and severity thresholds for code analysis?

Configure custom code analysis rules, triggers, and severity thresholds by defining them in a `warden.toml` file. This allows you to tailor the AI review to specific project paths and standards.

What is the best way to catch security vulnerabilities before committing code?

The best way to catch security vulnerabilities before committing is to run a local AI code analysis using Warden. It uses a deterministic, skill-based system to review your changes and ensure adherence to project standards.

Does this AI code review tool support inline comments on GitHub pull requests?

Yes, this AI code review tool supports inline comments on GitHub pull requests. When integrated into your CI workflow, it automatically posts suggested fixes and feedback directly on the pull request.

How does Warden analyze code quality using its skill-based system?

Warden analyzes code quality using a deterministic, skill-based system to review code changes locally or on pull requests. This mechanism ensures consistent analysis for catching issues before they reach production.