mbwsims

mbwsims / claude-universe

Public

Teach Claude Code to think systematically

50
6
100% credibility
Found Apr 15, 2026 at 60 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

A collection of specialized analysis tools and agents that enhance an AI coding assistant's ability to perform systematic code reviews across multiple dimensions like security, testing, architecture, and evolution.

How It Works

1
🌌 Discover Claude Universe

You find this helpful companion for your AI coding assistant on its website, promising smarter code checks.

2
💻 Start your coding session

Open your usual AI helper in the terminal where you build and fix code.

3
🔗 Add the universe

Follow simple instructions to bring all five smart systems into your session once.

4
🚀 Launch orbit check

Type a quick command to scan your whole project for security, tests, quality, changes, and rules in just 60 seconds.

5
Choose your focus
⚡
Quick scan

Get a 10-second status overview to spot issues fast.

🧠
Deep analysis

Run all agents in parallel for comprehensive insights in minutes.

🎯
Targeted check

Focus on one area like tests or security for detailed results.

6
📊 Review dashboard

See clear findings, scores, and advice on your code's health across all layers.

✅ Smarter coding unlocked

Your AI now thinks systematically, helping you build better, safer code every day.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 60 to 50 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is claude-universe?

Claude-universe is a TypeScript plugin for Claude Code sessions that teaches Claude to analyze projects systematically via 20 slash commands across five domains: instructions, tests, security, codebase structure, and git evolution. Run /orbit for a 60-second dashboard sweeping security vulns, test gaps, hotspots, and drift, or scope like /orbit security tests. It pairs Claude's reasoning with MCP servers for deterministic metrics on JS/TS/Python, falling back to manual tools anywhere.

Why is it gaining traction?

Unlike plain Claude prompts, it delivers batch-computed insights like risk scores, layer violations, and secret scans that Claude misses alone, with zero setup via /plugin install. Devs love the /orbit pr mode for diff-aware PR reviews and plain-English activation, blending AI teaching with hard metrics. At 50 stars, it's hooking early adopters in the claude universe seeking claude teach me code analysis without full CI.

Who should use this?

Backend devs auditing JS/TS/Python repos for secrets or auth gaps before PRs; teams using Claude Code for quick test plans or threat models; solo coders wanting /recap on git drift or /scan vulns without setup. Ideal if github teach yourself computer science via AI appeals, but skip for non-Claude workflows.

Verdict

Grab it if Claude Code is your daily driver—strong docs and fallbacks make it instantly useful despite 50 stars and 1.0% credibility signaling early maturity. Test on toys first; production-ready for audits, but lacks broad lang support yet.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.