gyorgy.sh

mx

eforward2.registrar-servers.com

eforward1.registrar-servers.com

eforward3.registrar-servers.com

eforward4.registrar-servers.com

eforward5.registrar-servers.com

ns

hattie.ns.cloudflare.com

donald.ns.cloudflare.com

caa

txt

google-site-verification=VqYPvMkAPLG0rGf54F9qwJTFRdGx9oZqOwLEbW8mVEo

v=spf1 include:spf.efwd.registrar-servers.com ~all

dmarc

User-agent: *
Allow: /
Content-Signal: ai-train=yes, search=yes, ai-input=yes

Sitemap: https://gyorgy.sh/sitemap.xml
# llms.txt: https://gyorgy.sh/llms.txt

# gyorgy.sh

> Personal site and blog of György. Notes on software, building things, and the occasional side quest.

Every post is available as markdown by appending `.md` to its URL.

## Blog

- [A Claude Code agent fleet: 500 pages in 15 languages](https://gyorgy.sh/blog/claude-code-agent-fleet.md): I started a Claude Code agent fleet from my phone, went to sleep, and woke up to 500 SSR pages in 15 languages. A devlog on running an overnight fleet of Opus,…
- [The Claude Code habits quietly running up your usage](https://gyorgy.sh/blog/claude-code-expensive-habits.md): Most of what makes Claude Code slow and expensive is habit, not the tool. Here are the seven that cost me the most, each with a one-line fix and where to dig d…
- [The tools I use for agentic work](https://gyorgy.sh/blog/agentic-work-tools.md): Agentic work has quietly become the new IDE. A tour of what I actually reach for: the coding agent itself, the terminal I run it in, the editor I read the diff…
- [Running Claude Code on local models with LM Studio and Ollama](https://gyorgy.sh/blog/claude-code-local-models.md): The Claude CLI is just a client for the Anthropic API, so anything that speaks that API can sit behind it. Point it at LM Studio or Ollama and you get the same…
- [Keepresso: keep your Mac awake, even with the lid closed](https://gyorgy.sh/blog/keepresso.md): Keepresso is a native menu-bar app that keeps your Mac awake, even with the lid closed: smart triggers for AI agents and games, timed sessions, closed-display…
- [MyAgens: a self-hosted AI headquarters, reachable from Telegram](https://gyorgy.sh/blog/myagens.md): MyAgens runs a persistent fleet of AI agents on your own machine, reachable from Telegram or a browser. What started as a Telegram bridge to one server now has…
- [Fixing macOS Wi-Fi lag and ping spikes: the AWDL problem](https://gyorgy.sh/blog/macos-awdl-network-jitter.md): Regular latency spikes on Wi-Fi while gaming, using GeForce Now, Xbox Cloud Gaming, or streaming with Moonlight and Parsec? On a Mac the culprit is usually awd…
- [Hello, world](https://gyorgy.sh/blog/hello-world.md): The site is alive. A quick note on what gyorgy.sh is, what I plan to write about (software, developer tips, and AI research), and why I wanted a place of my ow…

## Help

### Tips & tricks

- [Git aliases I use every day](https://gyorgy.sh/help/git-aliases.md): A handful of git aliases that save me thousands of keystrokes a week.
- [Let Claude write your prompt: the meta-prompting loop](https://gyorgy.sh/help/meta-prompting.md): The fastest way to a better prompt is to have Claude help you write it. Here is the draft, critique, refine, run loop I use to get sharper results with less th…

### How-to

- [Serve a folder over HTTP in one line](https://gyorgy.sh/help/local-http-server.md): Quick one-liners to serve the current directory over HTTP, no setup, when you just need to preview something.
- [Use Claude Code remotely from your phone or the web](https://gyorgy.sh/help/use-claude-code-remotely.md): Step away from your desk without stopping a Claude Code run. Turn on remote control and pick the session up from your phone, claude.ai/code, or another machine.
- [Stop running one giant chat: manage context in Claude Code](https://gyorgy.sh/help/claude-code-manage-context.md): A long-running Claude Code session gets slower, pricier, and less accurate. How I keep context lean, and what a big context window actually costs you.
- [/clear, /compact, or a new session: when to reset Claude Code](https://gyorgy.sh/help/claude-code-clear-vs-compact.md): Claude Code gives you two ways to trim a session and a third option to start over. /clear wipes, /compact summarizes, and a simple rule tells you which one the…
- [Plan before you build: getting the most out of plan mode](https://gyorgy.sh/help/claude-code-plan-mode.md): Plan mode makes Claude Code lay out its approach and wait for your sign-off before it touches a file. I use it to skip the expensive redo loop.
- [Sub-agents in Claude Code: smart model, cheap workers](https://gyorgy.sh/help/claude-code-subagents.md): Let a capable model plan and cheap models do the grunt work. How Claude Code sub-agents work, how to set one up, and the token math that makes them pay off.
- [Write a CLAUDE.md that stops you repeating yourself](https://gyorgy.sh/help/claude-md-best-practices.md): A good CLAUDE.md is project memory: say the durable facts once and Claude Code loads them every session. What to put in it, what to leave out, and why it saves…

### Reference

- [curl flags I always forget](https://gyorgy.sh/help/curl-flags.md): The curl flags I look up most, in one place. Follow redirects, save output, headers, and quiet download.
- [Which Claude model should you use in Claude Code](https://gyorgy.sh/help/which-claude-model.md): Opus, Sonnet, Haiku, or Fable. A plain comparison of the Claude models by cost, speed, and capability, plus which one I reach for in Claude Code and when.
- [Context rot: why a long Claude Code chat gives worse answers](https://gyorgy.sh/help/claude-code-context-rot.md): Claude Code does get worse as a session grows, and it is not your imagination. Here is what context rot is, why it happens, and why pasting everything backfire…

Contact: mailto:gyorgy@pueev.com
Expires: 2027-10-18T00:19:59.421Z
Preferred-Languages: en
Canonical: https://gyorgy.sh/.well-known/security.txt
Encryption: https://gyorgy.sh/gyorgy.asc