I made Claude Code listen before it codes (MIT)
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…
What it does
In the maker’s words, at launch
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 want, it sits with you to fully understand your intent. Then it moves into the approach phase: walks through the options, pros and cons, and tells you which one it leans toward and why. It writes code only when you say so. When you're confident you and Claude are aligned, that's when you give the go ahead. And responses stay short. Feels like texting a staff engineer, not reading an essay. No more scrolling. Relay helps you make the right decisions. When you make a call together, it lands in .relay/sessions/decisions.jsonl in your repo. What you chose, what you rejected, why. Your next session picks up where this one ended, with the reasoning intact. Commit it, your teammate pulls, their Claude Code knows why you did it that way too. The entire "brain" is one markdown file plus ~50 lines of Python. Read all of it in 5 minutes. MIT. Install: /plugin marketplace add basegraphhq/relay-plugin then /plugin install relay@basegraph. What I'd actually love feedback on: the preference learning bit. Relay is supposed to learn how you want to work via AskUserQuestion at real decision points, and silently from corrections you make. Tell me when it asks too much or too little.
Does the same job
all alternatives →- SSSpotlight shows what your Claude Code/Codex are doingJun 2026 · backplanes.com · ▲8
Hola HN! Long time lurker, sometimes commentor, first time poster here. I’ve been working alongside my two co-founders and a few colleagues on a project I’m excited (and a little nervous) to share with you all! Like many of us, I’ve lived a tortured existence with AI coding (is it vibes?) over the past few months - I think November was a big moment with this. But, one thing I’ve noticed after building orchestration layer after orchestration layer is that the thing I always came back to was “what the hell is Claude Code actually doing?” Perhaps it’s because of the time Claude Code got…
- AOAn open source job search plugin for Claude CodeJun 2026 · github.com · ▲5
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…
- IBI built new type of dev environment for agentic coding2025 · github.com · ▲6
The main goal of this was to be able to not just run multiple Claude Code sessions at once, but actually manage them and keep track of what I was doing. Sometimes this is multiple attempts on the same task, sometimes I work several tasks at once. Really I was just sick of twiddling my thumbs waiting for the coding agent to finish, and I wanted it to be easy to work on/review/test another change while I waited.
- LMLet Me Prompt It for You2025 · lmpify.com · ▲6
Ok so over the last 9 days I built lmpify. my personal driver was i want to replace claude because it's annoying. Their Claude3.7 model is perfect for coding, but the Claude.ai interface doesn't cut it for me for these reasons: - Very slow to start up and TTFT is terrible. lmpify hits within 100ms and doesn't need to wait for pageload to start seeing result, result is already starting in DO as soon as you submit. - Claude doesn't support URLs out of the box. When i create a new app/worker, i usually add URLs as source of truth for context . with claude it was still a hassle to…
- RARelaymux, a tmux-based meta-harness for local coding agentsJun 2026 · github.com · ▲9
Hey HN, There’s been a lot of interest recently in meta-harnesses, loops, and multi-agent orchestration. Obviously, there are already a lot of good tools: Conductor, cmux, the native Codex / Claude Code apps, etc. For my own use cases, I’ve felt that the orchestration layer tends to feel overengineered. I mostly wanted a simple local harness (i.e Pi) for running and tracking CLI agents with the ability to hop in (via tmux). Relaymux is my opinionated attempt at that. A few design principles: - The frontend is just Telegram / iMessage / CLI. If I want more visibility, I hop…
- ECEnable Claude to interactively debug your code2025 · github.com · ▲7
I participated in the Nvidia + Vercel 2 hour hackathon in SF tonight, and built something I've wanted, but hadn't tried building. I implemented an MCP Server and VS Code extension to allow Claude Desktop to place breakpoints, step through code, and execute expressions (assuming language support). So you can ask it a question that requires actually stepping through the code and now it can actually do that - check values for you, etc. It's _definitely_ not perfect. Have improvements? Please make a PR!
More dev tools this month
the category →
Open-source GTM skills for technical founders
Dev tools · 29d ago · gtmcofounder.com
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app