> ## Documentation Index
> Fetch the complete documentation index at: https://docs.raigal.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Raigal overview

> Code quality and AI pattern detection for engineering teams.

Raigal catches the sloppy patterns AI coding tools leave behind: redundant comments, swallowed errors, unsafe type casts, and insecure calls. It packages linting, formatting, security checks, and pattern detection into one CLI command with a calibrated score from 0 to 100.

Connected to [Raigal Cloud](https://app.raigal.dev) and the official [Raigal GitHub App](https://github.com/apps/raigal-cloud), it evaluates pull requests, protects main branches, tracks issues on a 4-stage board, and coordinates automated fixes with local coding agents.

> [!TIP]
>
> **Your source code is never uploaded to Raigal servers**. During pull request checks, an in-memory secret-masked patch diff (under 20 KB) is sent to display changes in the dashboard.

## What Raigal catches

AI assistants like Claude Code, Cursor, Copilot, and OpenCode speed up development, but frequently leave behind structural defects:

* Narrative comments that repeat function names or obvious code.
* Empty `catch` blocks that hide runtime failures.
* Unsafe type assertions (`as any`, `as unknown as T`) that bypass the compiler.
* Leftover debugging statements, console logs, and unreachable branches.
* Unsanitized SQL, dynamic `eval()`, and unsandboxed agent tools.

Raigal runs through local agent hooks, in CI on every pull request, and during terminal audits.

## Components

| Component | Description | Link |
| - | - | - |
| **Raigal Cloud** | Web dashboard at `app.raigal.dev` with issue tracking, score history, and team metrics. | [Cloud dashboard](/cloud-platform/dashboard) |
| **GitHub App** | Pull request checks, commit statuses, and branch protection enforcement. | [GitHub App setup](/automation-and-ci-cd/pull-requests) |
| **Scoring engine (0-100)** | Density-weighted score normalized by file count, with dynamic caps and logarithmic scaling. | [Scoring engine](/core-concepts/scoring) |
| **CLI and agent hooks** | Pre-commit checks, safe autofixes (`raigal fix`), and real-time interception for coding agents. | [CLI reference](/cli-reference/commands) |
| **Agent repairs** | Isolated git worktrees where local agents fix issues and open pull requests. | [Agent repairs](/automation-and-ci-cd/agent-repairs) |
| **GitHub Actions OIDC** | Tokenless authentication for CI runners using cryptographic GitHub OIDC tokens. | [Security model](/core-concepts/security) |
| **Raigal MCP** | Model Context Protocol server connecting Raigal to Claude Code, Cursor, Windsurf, Cline, and Antigravity. | [MCP server](/automation-and-ci-cd/mcp-server) |

## Getting started

**1. 1. Sign in to Raigal Cloud**

Create a workspace at [app.raigal.dev](https://app.raigal.dev) with a 14-day evaluation trial and invite your team. [Organization onboarding guide](/getting-started/first-client-setup)

**2. 2. Install the Raigal GitHub App**

Connect your repositories with the [Raigal GitHub App](https://github.com/apps/raigal-cloud) to run checks on pull requests. [Pull request checks](/automation-and-ci-cd/pull-requests)

**3. 3. Add the CI workflow**

Add a GitHub Actions workflow to check pull requests and send scores to your dashboard. [CI/CD pipelines](/automation-and-ci-cd/ci-cd)

**4. 4. Set up local tools and hooks**

Install the CLI (`raigal scan`, `raigal fix`) and set up interception hooks for Claude Code or Cursor. [Quickstart guide](/getting-started/quickstart)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.