ai-codex

skill
Security Audit
Pass
Health Pass
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 243 GitHub stars
Code Pass
  • Code scan — Scanned 3 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested
Purpose
This tool generates a compact, structured index of a codebase (routes, pages, database schemas, components) to provide AI assistants with immediate project context, saving thousands of prompt tokens per conversation.

Security Assessment
Overall Risk: Low. The static code scan checked three files and found no dangerous patterns, malicious code, or hardcoded secrets. The tool does not request any dangerous system permissions. It acts as a local parser and only reads your local project files to generate Markdown files. Based on the available evidence, it does not make external network requests or execute arbitrary shell commands. As a best practice, note that the generated output files could theoretically expose sensitive architectural details or database schema logic if they are accidentally committed to a public repository rather than kept local or added to `.gitignore`.

Quality Assessment
The project demonstrates strong health and community validation. It is fully licensed under the permissive MIT standard, making it safe for integration. The repository is highly active, with updates pushed as recently as today, and has accumulated 243 GitHub stars, indicating solid community trust. The README is comprehensive, offering clear documentation for quick starting, CLI flags, and configuration. The only notable detail is that the project was reportedly designed and written entirely by an AI (Claude Code); while this explains the clean documentation and structure, developers should still apply standard code review practices.

Verdict
Safe to use.
SUMMARY

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

README.md

ai-codex

Built by Claude Code
License: MIT
TypeScript

This project was entirely designed, written, and published by Claude Code (Anthropic's AI coding assistant). The concept, implementation, documentation, and examples were all generated in a single conversation session.

Generate a compact codebase index that gives AI coding assistants instant context about your project structure. Instead of wasting 50K+ tokens on file exploration at the start of every conversation, your AI assistant reads a pre-built index and gets to work immediately.

Why

Every time you start a conversation with an AI coding assistant (Claude Code, Cursor, GitHub Copilot, etc.), it spends thousands of tokens exploring your codebase -- reading files, scanning directories, building a mental model. This happens every single conversation.

ai-codex solves this by generating compact, structured reference files that capture:

  • Every API route with its HTTP methods
  • Every page with its rendering strategy (client vs. server)
  • Every library function signature
  • Your database schema (key fields, relationships)
  • Your component tree with props

The result: 5 small files that replace 50K+ tokens of exploration, every time.

Quick Start

Run it in your project root:

npx ai-codex

That's it. It auto-detects your framework and generates the index.

Output

By default, files are written to .ai-codex/ in your project root:

File What it contains
routes.md API routes grouped by resource, with HTTP methods
pages.md Page tree with client/server rendering tags
lib.md Library exports -- function signatures, classes
schema.md Database schema -- key fields, FKs, relationships
components.md Component index with props, grouped by feature

Files that don't apply are skipped (e.g., no schema.md if you don't use Prisma).

Configuration

CLI Flags

npx ai-codex --output .claude/codex     # custom output directory
npx ai-codex --include src lib           # only scan these directories
npx ai-codex --exclude tests __mocks__   # skip these directories
npx ai-codex --schema prisma/schema.prisma  # explicit schema path

Config File

Create a codex.config.json in your project root:

{
  "output": ".ai-codex",
  "include": ["src", "lib", "app"],
  "exclude": ["tests", "__mocks__"],
  "schema": "prisma/schema.prisma"
}

CLI flags override config file values.

Output Format Examples

routes.md

## products
GET,POST     /api/products [auth,db]
GET,PUT,DELETE /api/products/:id [auth,db]
POST         /api/products/:id/images [auth]

## orders
GET,POST     /api/orders [auth,db]
GET          /api/orders/:id [auth,db]
POST         /api/orders/:id/refund [auth,db]

pages.md

[client]   /                                                  HomePage
[server]   /products                                          ProductsPage
[client]   /products/:id                                      ProductDetailPage
[server]   /cart                                               CartPage
[client]   /checkout                                           CheckoutPage

lib.md

## lib
cart-utils.ts
  fn calculateTotal
  fn applyDiscount
  fn formatPrice
auth.ts  fn validateSession
stripe.ts  fn createPaymentIntent

schema.md

## Product
  id                     String    PK
  categoryId             String
  -> Category, OrderItem[], Review[]

**Order** id(PK) | userId | status -> User, OrderItem[]
**User** id(PK) | email(UQ) -> Order[], Review[]

components.md

## components
(c) CartDrawer  items, onRemove, onCheckout
(c) ProductCard  product, onAddToCart
    PriceDisplay  amount, currency
(c) SearchBar  onSearch, placeholder

Integration with AI Assistants

Claude Code

Add this to your CLAUDE.md:

## Codebase Index
Pre-built index files are in `.ai-codex/`. Read these FIRST before exploring the codebase:
- `.ai-codex/routes.md` -- all API routes
- `.ai-codex/pages.md` -- page tree
- `.ai-codex/lib.md` -- library exports
- `.ai-codex/schema.md` -- database schema
- `.ai-codex/components.md` -- component tree

Cursor / Other AI IDEs

Add the .ai-codex/ directory to your AI assistant's context or rules file. Most AI coding tools support a way to include reference files.

Auto-Refresh

Git Pre-Commit Hook

# .git/hooks/pre-commit
npx ai-codex
git add .ai-codex/

npm Script

{
  "scripts": {
    "codex": "npx ai-codex",
    "precommit": "npx ai-codex && git add .ai-codex/"
  }
}

CI/CD

# GitHub Actions example
- name: Update codebase index
  run: npx ai-codex
- name: Commit index
  run: |
    git add .ai-codex/
    git diff --cached --quiet || git commit -m "chore: update codebase index"

Supported Frameworks

Framework Auto-detected What it scans
Next.js (App Router) Yes app/ or src/app/ (api/**/route.ts, **/page.tsx), lib/, components/
Next.js (Pages Router) Yes pages/ or src/pages/, lib/, components/
Generic TypeScript Yes src/, lib/, utils/, components/

Prisma schema is auto-detected at prisma/schema.prisma.

What Gets Skipped

  • node_modules/, .next/, dist/, build/, .git/
  • .d.ts declaration files, .map source maps, .min.js minified files
  • Backup files (*.backup.*, *-backup-*)
  • shadcn/radix UI primitives (button, dialog, etc.) in components/ui/

Contributing

  1. Fork the repo
  2. Create a feature branch: git checkout -b my-feature
  3. Make your changes
  4. Test on a real project: cd /path/to/your/project && npx tsx /path/to/ai-codex/src/generate-codex.ts
  5. Submit a pull request

Ideas for Contributions

  • Support for more frameworks (SvelteKit, Remix, Astro)
  • Support for more ORMs (Drizzle, TypeORM, Knex)
  • Watch mode (--watch) for continuous regeneration
  • Token count estimation in output
  • Support for Python projects (FastAPI, Django)

License

MIT

Reviews (0)

No results found