AI-powered code review prompts for NestJS projects
# NestJS Review Agent
> š AI-powered code review prompts for NestJS/TypeScript projects
[](https://opensource.org/licenses/MIT)
[](http://makeapullrequest.com)
A self-learning code review agent that works with **GitHub Copilot**, **Cursor**, and any LLM-powered IDE.
## ⨠Features
- š”ļø **Security checks** - Injection, auth, secrets, input validation
- š **Bug prevention** - Null safety, async/await, error handling
- šļø **Architecture rules** - NestJS patterns, DI, module boundaries
- ⨠**Code quality** - Types, naming, immutability, no magic numbers
- š **Self-learning** - Remembers patterns it finds
## š Quick Start
### GitHub Copilot (VS Code)
1. Open Cursor Chat (`ā+I` / `Ctrl+I`)
2. Type:
```
Review origin/main..origin/feature using path/to/REVIEW.md
```
### Cursor
1. Open Composer (`ā+I`) or Chat (`ā+L`)
2. Add `REVIEW.md` to context (drag or `@` mention)
3. Type:
```
Review origin/main..origin/feature
```
## š¦ Installation
**Option A: Clone (recommended)**
```bash
git clone https://github.com/shouryaraj/nestjs-review-agent .review-agent
echo ".review-agent/" >> .git/info/exclude # Keep out of git history
```
**Option B: Copy just the prompt**
```bash
curl -o REVIEW.md https://raw.githubusercontent.com/shouryaraj/nestjs-review-agent/main/REVIEW.md
```
**Option C: Reference directly**
```
Review HEAD using ~/path/to/nestjs-review-agent/REVIEW.md
```
## š Files
```
nestjs-review-agent/
āāā REVIEW.md ā Main review prompt (use this!)
āāā learned-patterns.md ā Agent learns here (auto-updated)
āāā rules/
ā āāā security.md ā Security rules
ā āāā bugs.md ā Bug prevention rules
ā āāā architecture.md ā Architecture rules
ā āāā quality.md ā Code quality rules
āāā examples/
āāā review-output.md ā Example review output
```
## š» Usage Examples
```Agent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.