closedloop-ai

closedloop-ai / claude-plugins

Public

Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.

agentic-ai ai-agents anthropic automation claude-code
11
0
100% credibility
Found Mar 07, 2026 at 11 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

Open-source plugins extending Claude Code with AI agents for project bootstrapping, code planning, automated reviews, quality judging, and self-learning to accelerate team software development.

How It Works

1
🔍 Discover ClosedLoop Plugins

You find these helpful add-ons for Claude Code that make AI coding smarter for teams.

2
📦 Add to Claude Code

With one command, you install the plugins right into your coding workspace.

3
🛠️ Set Up Your Project

The bootstrap tool scans your code and creates custom AI experts tailored just for your tech stack.

4
📄 Share Your Requirements

You give it a simple requirements document, and it crafts a detailed step-by-step plan.

5
✅ Review and Go

You check the plan, make tweaks if needed, then hit go to let the AI implement, test, and review.

6
🔄 Watch It Learn and Improve

Over time, the system captures patterns from successes and mistakes to get even better.

🚀 Ship High-Quality Code Faster

Your team delivers reliable features with less hassle, closing the loop on development.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 11 to 11 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-plugins?

Claude-plugins is a set of open-source Anthropic Claude plugins on GitHub that supercharge Claude Code for multi-agent software delivery. Drop in your PRD, and it bootstraps custom agents from your codebase, generates detailed implementation plans, iterates code changes with critics and judges, runs automated reviews with GitHub PR comments, and captures self-learning patterns across repos. Built in Python, it installs via the Claude plugins marketplace with commands like `/bootstrap:start` and `/code:start --prd requirements.md`, turning chaotic LLM coding into a repeatable Bootstrap-Plan-Ship workflow.

Why is it gaining traction?

Unlike basic Claude code plugins, these deliver a full plan-first SDLC with caching, hooks for build validation, visual QA via Playwright, and adaptive learning that grounds agents in your actual tech stack—claiming to outperform Opus and Sonnet at half the cost. The hook is effortless multi-repo coordination and quality gates that loop until code lands cleanly, no churn. Early benchmarks show structured outputs beating ad-hoc prompting, drawing devs hunting the best Claude code plugins GitHub has to offer.

Who should use this?

Backend and full-stack devs on Claude Code who hate debugging LLM hallucinations mid-PR, or teams scaling AI-assisted sprints across monorepos. Ideal for frontend devs designing components with auto-reviews, or platform engineers wiring cross-repo APIs with traceability. Skip if you're not deep into Anthropic's Claude plugins ecosystem.

Verdict

Promising engineering preview for Claude Code power users, but with just 11 stars and 1.0% credibility score, it's raw—docs are solid but lacks broad testing. Try in sandboxes if you want self-improving agents; production teams should wait for maturity. (187 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.