Alternatives
Products that do what Dr. Ralph – Medical Diagnostics Plugin Using Claude Code's Ralph Wiggum does
Built this over the weekend for a friend dealing with chronic health issues who wanted help analyzing their medical records. Dr. Ralph is a Claude Code plugin that runs a 5-phase diagnostic workflow: records intake, literature research, differential diagnosis, treatment planning, and SOAP documentation. It uses the Ralph Wiggum plugin’s Stop hook pattern - the loop keeps iterating until diagnosis confidence reaches 80% or max iterations. The interesting bit was adapting Ralph for multi-phase work instead of single-task refactoring. I used Thariq’s AskUserQuestion interview approach to spec…
- 1YA
I was randomly browsing claude codes ralph wiggum plugin[1] and was surprised to see my toy project referenced. Since it appears people are getting some value out of it, thought I'd share it here... Full disclosure, this repo itself was built with a primitive ralph wiggum loop so expect AI slop. It works though. ¯\_(ツ)_/¯ https://mikeyobrien.github.io/ralph-orchestrator/ [1] https://github.com/anthropics/claude-code/tree/main/plugins/...
Dec 2025 · github.com
- 2
- 3RR
Built this to manage the full Claude Code workflow autonomously, from initial plan creation to reviewed PR. Tested it on a 25-task plan (5-7 items each) - ran overnight, woke up to a surprisingly solid PR-ready branch. Just run `ralphex` (single binary) in your project directory. Without a plan file, it starts interactive mode. Asks what to build, explores the codebase, writes the plan, then executes. The loop: plan creation (asks questions, writes markdown) → task execution (fresh session each, no context bloat) → multi-phase reviews (Claude + optional Codex) → branch ready for PR. Prompts…
Jan 2026 · ralphex.umputun.dev
- 4OS
We're releasing the next-gen Ralph Wiggum architecture - agent clusters with independent validator agents with clear rejection mandates. As long as the code is not feature-complete and production-grade, it will not be approved. The result is AI without any need for babysittng.
Jan 2026 · github.com
- 5
- 6
- 7
- 8
- 9
Turn feature ideas into stakeholder-ready code prototypes
Mar 2026
- 10
- 11
- 12
- 13
- 14IM
heylo! open sourcing a plugin that I've been daily driving for a month. And I promise, I can't go back to vanilla Claude Code. I'm a heavy Claude Code user, and a couple of things kept bugging me. Claude really likes to jump into code. And its responses are too long. I'd skim past walls of text just to find the recommendation. Plan mode helps, but it didn't go deep enough. The questions it asked were still implementation questions, when what I actually needed was alignment on the problem. So I made it stop. Relay is a different output style and two Python hooks. When you describe what you…
Apr 2026 · github.com
- 15PA
Claude Code is amazing at writing code, but it will happily build from under-specified requirements, implement the same thing different ways, and fail to write great tests unless you specifically ask it to. Prawduct is a set of prompts, skills, hooks, and artifact templates that help focus Claude Code on product development rather than code development. You can start from something a simple as "make a website with a scientific calculator" or as complex as "create a MMO with clients for iOS, Android, and web". You can specify as much or as little arch standards or implementation details as…
Mar 2026 · github.com
- 16CC
I built Claude‑CMD, an open-source command-line interface for working with Claude Code commands, configurations, and AI-driven workflows. It’s designed to help developers and PMs streamline how they interact with Claude Code in coding tasks, automation, and prompt management. Website: claudecmd.com Happy to answer questions or hear suggestions. You can also contribute your own commands to help improve the project. Contributions welcome!
2025 · github.com
- 17AD
Hey HN, as a former data analyst, I’ve been tooling around trying to get agents to do my old job. The result is this system that gets you maybe 80% of the way there. I think this is a good data point for what the current frontier models are capable of and where they are still lacking (in this case — hypothesis generation and general data intuition). Some initial learnings: - Generating web app-based reports goes much better if there are explicit templates/pre-defined components for the model to use. - Claude can “heal” broken charts if you give it access to chart images and run a…
Mar 2026 · rubenflamshepherd.com
- 18CM
Jan 2026 · github.com
- 19PT
I vibe-coded a terminal tool called Pluqqy (I had a dormant domain on hand) to help me keep LLM context organized while coding with AI. It’s my first time writing Go and my first terminal app, built almost entirely with Claude Code. • What it does: Pluqqy lets you manage prompts, rules, and context as small building blocks, then stitch them together into a single file (like AGENT.md or CLAUDE.md) that your coding agent can consume. It’s meant to reduce context drift and make iteration easier. • Why I built it: I was losing track of my agent context between sessions and wanted something…
Oct 2025 · github.com
- 20CC
Chris Wiles showcased his setup for Claude Code and I thought it was sick. So I adapted it for Django projects. Several skills have been added to address the pain points in Django development.
Jan 2026 · github.com
- 21CP
Anthropic announced today that starting June 15, paid Claude plans get a separate monthly credit pool for programmatic usage (claude -p, Agent SDK). Seems OK at first glance but it turns out the monthly credit pool is charged at API rates, which effectively kills any serious programmatic usage for hobbyists. This is a small Claude Code wrapper which runs claude in a PTY, injecting input, finding the session transcript jsonl file, and using a stop hook to determine when claude is done. It's a drop-in replacement for claude code. All arguments except the "-p" argument are forwarded as-is.…
May 2026 · github.com
- 22AO
Hey HN, I wanted to share an open source plugin + skills I put together that turn Claude Code into a job search assistant. The goal is to minimize the amount of time needed to find interesting and relevant jobs. How it works: 1. Clone the repo, install the plugin, and run `/job-search` 2. Claude will ask a few questions to understand the roles you’re interested in and save your preferences locally. 3. Claude will then pull live job postings (currently, LinkedIn Jobs), compare posts against your preferences, and generate a digest of the posts that are relevant. 4. [Optionally] Claude…
Jun 2026 · github.com
- 23CC
I reviewed Anthropic's newly released Claude Code and compared it to Aider. CC has a great design, and I'll be using it sometimes (especially in large code bases), but I'm sticking with Aider as my primary tool for now. If you use LLM coding tools on the command line, then I hope you'll find this useful!
2025 · mechanisticmind.substack.com
- 24SH
We built Verity.md for the new era of loop engineering where traditional code review simply doesn't fit and is a major bottleneck. This is what we think the future of code review looks like: - An adversarial review layer, which is part SAST scanning for quality and security issues deterministically, and part AI (a different one) checking for intent gaps. - Built-in gates that tells the coding agent how to fix itself when it finds an issue (this is the self-healing part). - Compounding knowledge base where every decision is saved, so the next time the coding agent run it starts smarter -…
Jul 2026 · verity.md
Ranked by how close each launch is in meaning, then by votes. Refine with a description →