The "Project DNA" Technique: How I Made AI Stop Writing Alien Code in My Codebase

VaultTec-Dev — Sun, 12 Apr 2026 13:02:52 +0000

If you use Cursor, Claude, or any AI coding assistant, you've probably experienced this: the AI writes code that works, but it doesn't fit. Wrong naming conventions, unfamiliar error patterns, random library choices.

After a few months, your codebase looks like it has 12 different authors.

I stumbled onto a fix so obvious I'm embarrassed it took me this long.

The Problem

Every AI session starts fresh. The AI doesn't know:

Your naming conventions
Which libraries you prefer
How you handle errors
What patterns you've already established
Project-specific context (locales, domain concepts, etc.)

So it guesses. And it guesses differently every time.

The Fix: Project DNA

Create a CONTEXT.md file in your project root. I call it "Project DNA" because it's the core identity of your codebase that AI needs to understand.

Here's mine for Doc2Pay (a SaaS I'm building for Ukrainian accountants):

## PROJECT: Doc2Pay — Invoice Recognition SaaS
## STACK: Next.js 14, Prisma, PostgreSQL, tRPC, Zod
## PATTERNS: Repository pattern, always validate at boundary, Zod schemas for all external data
## ERRORS: Custom AppError class. Always log then rethrow. Never silent catches.
## NAMING: camelCase for vars/functions, PascalCase for components/classes, SCREAMING_SNAKE for constants
## NEVER: Raw SQL queries, magic strings, `any` types, console.log in production
## ALWAYS: Ukrainian locale for dates (uk-UA), UAH for currency display, i18n keys for user text
## DOMAIN: invoices, agencies, accountants, PrivatBank API, tax declarations

10 lines. Changes everything.

How to Use It

With Cursor: Just create the file. Cursor reads it automatically as part of its project context system. No extra setup needed.

With Claude/ChatGPT: Paste it at the start of each session before your actual request.

With GitHub Copilot: Add it as a .github/copilot-instructions.md file — same concept, different path.

Real Results

Before CONTEXT.md:

AI PR review comments: 20+ per session
Time fixing AI style issues: 15-20 min per feature
Codebase consistency: non-existent

After:

AI PR review comments: 2-3 max
Time fixing AI style issues: less than 5 min
Codebase consistency: actually exists

What to Put In Yours

The most impactful sections:

Section	What to include
STACK	Exact libs and versions you use
NAMING	Your specific conventions
ERRORS	How you handle them
NEVER	Rules the AI breaks constantly
ALWAYS	Things you always want to see
DOMAIN	Business concepts AI wouldn't know

The Deeper Insight

AI doesn't need to be smarter. It needs context.

You wouldn't hire a senior developer, give them zero onboarding, and expect them to write code that fits your team's patterns. Same logic applies to AI.

Project DNA is the onboarding doc for your AI assistant.

I'm building SnakeFlow, a free open-source VS Code extension for managing your entire dev environment (Docker, servers, Git, quality checks, GitHub PRs) from one sidebar panel. Check it out: github.com/vaulttec-dev

SnakeFlow: I Built a VS Code Extension That Manages My Entire Dev Environment from One Sidebar

VaultTec-Dev — Sat, 11 Apr 2026 18:38:36 +0000

Every time I started a new project, I'd end up with the same mess: four terminal tabs open (one for the dev server, one for Docker, one for DB migrations, one for random commands), a browser window for GitHub PRs, and a bunch of scattered CLI commands I had to look up every time.

I got tired of it. So I built SnakeFlow — a free, open source VS Code/Cursor extension that puts all of that in one sidebar panel.

What it actually does

Here's a quick walkthrough of the main features:

Dev Server Management

Whatever stack you use — Node.js, Python, Go, Rust, PHP, Ruby, Java, .NET — you can start, stop, and restart your dev server directly from the sidebar. No terminal needed.

Docker Compose Control

# Instead of typing this every time:
docker compose up -d
docker compose logs -f
docker compose down

# You just click buttons in the sidebar

Up, down, restart, and view logs — all without leaving VS Code.

Database & ORM Tools

SnakeFlow supports a wide range of ORMs and migration tools out of the box:

Prisma — generate, migrate, studio
Drizzle — push, generate
Alembic / Django ORM — for Python projects
Diesel — for Rust
EF Core — for .NET
Rails / Flyway — for Ruby and JVM projects

Quality Hub — 60+ Code Quality Checks

This is the part I'm most excited about. The Quality Hub runs checks across several categories:

Secret leak detection     → catches API keys, tokens in your code
Complexity analysis       → flags overly complex functions
Test ratio               → shows test coverage trends
Security scans           → Trivy, Bandit, Semgrep, ESLint Security

It also integrates with cloud platforms: SonarCloud, Snyk, CodeClimate, CodeRabbit, DeepSource, Codacy, and 15+ more — all aggregated in one view.

GitHub PRs + Issues

View open PRs, create new ones, leave comments — without opening a browser tab.

Build Pipeline

Run lint, typecheck, tests, and build as a full pipeline with a clear pass/fail summary. Great for a quick sanity check before pushing.

Ctrl+M M Quick Menu

Hit Ctrl+M M anywhere and get instant access to everything. It's a small thing but saves a surprising amount of time.

Who is it for?

Honestly, anyone who builds software. But especially:

Developers who work across multiple stacks
Teams using monorepos (SnakeFlow is monorepo-aware)
"Vibe coders" who build fast with AI and want quality checks without setting up a full CI pipeline just to see if their code has issues

It's free and open source

No paid tiers, no telemetry, no nonsense. MIT licensed.

VS Code Marketplace: https://marketplace.visualstudio.com/items?it

DEV Community: VaultTec-Dev