sermakarevich

Inspired by my friend’s story how he planned his vacation to Japan with AI, I decided to do so myself. This saved me probably a week for planing and research so might be useful for you as well.…

1. Headless mode Headless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run. 2. Ask human The…

Some time ago I got excited about running multiple Claude coders. This required moving from interactive sessions to claude -p, adding Beads, later a simple Python orchestrator, a UI, an ask_user MCP, and Telegram…

I was curious for some time about other people skills. Garry Tan once posted this: ``` My CTO friend texted me: "Your gstack is crazy. This is like god mode. Your eng review discovered a subtle cross site scripting…

I passed through some evolution, from todo list with /clear + "take next task" prompt to cleaning most of the skills/plugins/claudemd, using centralized beads db, developing ask_human mcp on sqllite and creating…

Some time ago I built a simple app to run swarms of coding agents — I call it fleet (https://news.ycombinator.com/item?id=48256389). It's based on centralized beads with a Python orchestrator and can run any coder…

Claude Code does not support AskUserQuestion in spawned sessions - subagents, agent teams, and workflows — which makes a swarm of agents less efficient in the original implementation. This can be easily fixed with an…

I have been using a Spec-Driven Development approach for all mid+ size coding tasks since Feb 2026: https://news.ycombinator.com/item?id=48231575. One of the reasons for developing my own plugin (sddw - spec driven…

AMD submitted a bug on the Claude Code repo where they complained about coding quality and described that they are running a fleet of 50+ Claude Code sessions using beads —…

Spec Driven Development approach allows to squeeze more from coding agents thanks to few strong concepts: - decomposition across two dimensions. first you generate specs in multiple steps (requirements, code analysis,…

I was intrigued by an AMD issue on GitHub where Stella Laurenzo shared how the AMD team runs a fleet of 50 or so agents: https://lnkd.in/drueskiV. I wanted to get there myself, and I think I managed to. I can now run a…

I started with materializing replies as markdown artifacts. Anything that stays in the terminal gets lost and forgotten quickly, so persisting each reply to a file was the first step toward keeping the work durable.…