Dmytro Gaivoronsky

🇺🇦 🇺🇸 Engineering leader & builder. 25+ yrs in tech including Google, AWS, and Meta.

Recent Posts

Picking Backup Climbs with 20 Years of Weather Data

4 minute read

You plan a route on Mount Shuksan for weeks, and three days out the forecast falls apart. Now what? People who have climbed here for twenty years answer this from memory. Storm coming off the ocean? Go east of the crest. Marine layer? Head south. They have a mental database built from hundreds of weekends, some of them ruined. I don’t have that database. I’ve been climbing in the Cascades for a few years, and when my primary objective gets stormed out, I have no honest basis for picking a backup. I could copy what more experienced friends do, but I wanted to actually understand it. I wanted an answer I could check against 20 years of records, not secondhand rules of thumb. The result is the PNW Climb Planner, an interactive map that ranks backup objectives for any of 500 Washington peaks, conditioned on the season and the incoming weather pattern. This post is about how I got there.

Claude Code Skills I Built and Use Every Day

3 minute read

I’ve been building Claude Code skills since November, one friction point at a time. A task I did twice became a command. A command I kept tweaking became a skill. I went through my session logs and pulled usage numbers. For each skill I’m showing two stats: the percentage of active Claude days where I used it at least once, and the raw invocation count over the last four weeks.

Reducing Attack Surface for AI Agents: Process-Scoped Credentials

6 minute read

Run env in your terminal. Everything you see there, your AI agent can see too. Claude Code, Cursor, Codex, Windsurf, whatever you use. These tools run as processes on your machine with the same permissions as your shell. If you have AWS_SECRET_ACCESS_KEY in your .zshrc, the agent has it. If you have a .env file with database credentials, the agent can read it. If you exported a Stripe API key three months ago and forgot about it, the agent still knows. This isn’t a bug. It’s how processes work on Unix.

iTerm2 Badges for Claude Code: Know Which Repo You’re In

3 minute read

I wrote about session topic summaries a month ago. That plugin generates a one-liner describing what each Claude Code session is doing and sticks it in the tmux status line. It works. I still use it. But there’s a simpler question I need answered faster: which repo is this? When I have four or five Claude sessions open across different projects, the session topic tells me what I’m doing but not where. I kept glancing at tmux panes, reading the topic, then mentally mapping it back to a repository. That’s one step too many.

I Built an MCP Server for Mountaineers.org

3 minute read

I’ve been a member of The Mountaineers for a few years now. I’ve taken a few courses, climbed a few peaks, gone on a bunch of activities, and made a few friends. At some point I also started building little tools around the site: a Chrome extension that syncs my activity history, a CLI for PeakBagger, and a Claude Code plugin that pulls route beta from a few places. Same itch every time: I want the data without clicking through five tabs. The missing piece was letting an AI assistant query mountaineers.org directly. A lot of that site is public for anyone to browse. MCP just turns those pages into structured results so Claude/Codex can answer questions like “what scrambles are on the calendar?” If you’re a Mountaineers member, the same idea gets more useful: you can ask about your own registrations, activity history, and course enrollments.

Where the Work Goes When Agents Arrive

7 minute read

A friend dropped this in our Slack the other day about Steve Yegge’s Gas Town: I think Gas Town is directionally correct but you have to admit also unhinged in a bunch of ways. I can’t help but be attracted to the absolute gonzo yolo mentality that birthed it, but I wouldn’t want to live there. It’s been rattling around in my head since. He’s right on both counts. And I say that as someone who actually lives there. The main thing I keep noticing isn’t the tools. It’s where the work goes. Over the last six months living in Gas Town, the biggest shift hasn’t been speed, it’s attention. This post is about how that attention moves upstream into design and guardrails, and how the feedback loops change once you stop reading every line.

How I Stopped Losing Track of Side Project Ideas

3 minute read

I’ve been using Claude Code and Codex a lot lately, and something unexpected happened: I started having more ideas than I could track. Not because I’m suddenly more creative. Because building stuff got faster. When you can go from “I wonder if…” to a working prototype in an afternoon, you start noticing more itches worth scratching. A dashboard for ski conditions. A break-even calculator for EV charging. A CLI for searching mountain peaks. A lot of these are afternoon builds. Some would take weeks. A few will never happen. But I kept losing them, scattered across Notion pages, random notes, half-remembered thoughts.

EV vs Gas Break-Even Calculator

2 minute read

Yesterday we were driving up to Snoqualmie Pass to ski with the family, and I realized I’d forgotten to charge the Rivian overnight. So we had to stop in Issaquah and top up at Electrify America, going from about 10% to 85%. The price there was roughly $0.56/kWh, which naturally turned into a conversation with my dad about how charging a Rivian really compares to fueling a gas car. We came up with some rough numbers on the spot, but I was curious what this actually looks like in perspective.

Session Topic Summaries in Claude Code Status Line

2 minute read

A couple of months ago I realized I run way too many parallel Claude Code sessions. Some are rapid-fire sessions where I’m iterating on code quickly. Others are slow burners that sit around for days while I context-switch to other work. The problem: when you come back to one of those slow sessions, you get that familiar moment of staring at the transcript thinking, what was I doing here again? Claude Code doesn’t help. There’s no at-a-glance “this session is about X” indicator. You end up scrolling up, re-reading, trying to reconstruct context like you’re debugging your own brain. So I built a thing.

iPhone to MacBook: My Remote Claude Code Setup

6 minute read

I’ve been looking for a way to run Claude Code sessions remotely, from my phone, while away from my desk. For simple tasks, the existing options work fine. Claude.ai on mobile handles quick questions. Cursor with Linear integration is decent for focused coding. But I kept hitting walls. Claude’s web interface doesn’t support MCP servers, custom plugins, or hooks. No claude-mem for cross-session memory. No custom skills. No ccstatusline. Basically none of the customizations that make my local Claude Code setup actually productive. I wanted access to my real environment, the one I’ve spent time configuring, not a stripped-down web version. Then I read Javier Granda Carvajal’s post on Claude Code on the go. He runs Claude Code on a cloud VM and connects from his phone. I liked the idea but went a different route: my MacBook at home, accessible via mosh and tmux.