Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Claude Code Workflow for beginners & intermediate users. Tutorial and Installer included
| Date | Stars |
|---|---|
| 2026-07-31 | 1360 |
| 2026-08-05 | 1363 |
| 2026-08-06 | 1363 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
# Claude Code Development Kit
**Keep Claude Code coherent across sessions.** A starter kit that maintains the context layer Claude actually reads.
## Why this exists
A static `CLAUDE.md` decays within a few sessions. The context window fills up. Decisions you made yesterday get re-derived today because nothing kept the docs in sync with the code. Every fresh session starts from scratch, even when the answer is one `git log` away.
This kit is the maintenance layer between you and Claude Code. Four focused doc files become the project's working memory. Slash commands keep them current. Hooks catch the things you'd forget. It's the setup you'd build yourself after a few weeks of using Claude Code, packaged so you start with it on day one.
## The loop
```
/prime load project context at session start
↓
work Claude writes the code
↓
/review-work parallel sub-agents catch bugs + rule violations
↓
/update-docs keep ai-context docs in sync (skipping trivial changes)
↓
/merge verify and ship (standard branch or git worktree)
```
`/verify` runs the app or its tests to confirm a change actually works (observed behavior, not just "it compiles") — the run-it-and-watch step `/review-work` points at.
When Claude hits an architecture decision or a debugging dead end, ask for a **second opinion** — an independent review from a different model (OpenAI Codex by default, or Google Gemini).
## Who this is for
You have a Claude Code subscription and want to hit the ground running. Maybe you're building an app, a side project, or starting something new. You want Claude to understand your project structure, review its own work, keep its own notes in sync — and not accidentally `git push --force` your main branch.
This isn't a heavy framework. It's structured defaults that compound over time.
## Quick start
```bash
curl -fsSL https://raw.githubusercontent.com/peterkrueck/Claude-Code-Development-Kit/main/install.sh | bash
```
Or clone:
```bash
git clone https://github.com/peterkrueck/Claude-Code-Development-Kit.git
cd Claude-Code-Development-Kit
./setup.sh
```
The installer walks you through what to include — Full (recommended), Customize, or Minimal. Re-run anytime to add features.
**First session:**
```bash
cd your-project
claude
> /prime
```
Claude reads your docs, summarizes the project, and you're ready to work.
## What's in the box
### Core (always installed)
| | |
|---|---|
| `CLAUDE.md` template | Your project's AI instruction set |
| `/prime` command | Load core docs into context — tiered: a light prime by default (~4-6k tokens), `--full` for everything, `--deploy` to also load infra |
| `/merge` command | Verify docs are current + tree is clean, then ship to main. Detects silent clean-merge breakage with a build/test pass. Works with standard branches and `git worktree`. |
| `/verify` command | Run the app or its tests to confirm a change actually works — a cross-stack template you fill in for your stack |
| `/update-docs` skill | Keep `docs/ai-context/` in sync after code changes — density-first, skips trivial diffs |
| `context7-guidance` skill | Fetch current library/framework/API docs via Context7 instead of stale training data |
| Doc scaffolding | Four focused files: `spec.md`, `project-structure.md`, `progress.md`, `deployment-infrastructure.md` |
| Security scanner hook | Blocks API keys and secrets from leaking to MCP plugins |
| Deny list + allowlist | Blocks `git push --force`, `rm -rf`, `sudo`, `git reset --hard`, etc.; auto-allows safe read-only shell utilities and doc-domain fetches |
| Asset directories | `assets/` scaffolding for icons, logos, social, web |
### Quality gates (optional)
| | |
|---|---|
| `/review-work` | Spawns parallel Claude sub-agents (Bug Hunter + Rules Auditor, plus an optional Architect) to review your uncommitted diff. Verifies every external-API claim against Context7 (unverified claims are discExcerpt of 9,054 characters
Read on GitHub
57
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:c4884fe9a6d0a3b3, desc:tutorial