Dmytro Gaivoronsky

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

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.

Claude Code session topics in tmux status line

The Idea

Put a one-line topic summary in the status line for each session. Keep it fresh automatically. Think Slack or Discord channel topics, or the old IRC topic line, but for Claude Code sessions.

Example lines:

  • OAuth debug: fixing schema validation (5m)
  • Blog post: adding code snippets (2h)
  • tmux config: wiring session display (<1m)

The summary has two parts:

  1. Theme - what is this session fundamentally about
  2. Current focus - what we’re doing right now

Plus a relative timestamp so you can see whether the summary is stale. If it says (2h), it might not reflect the last few messages.

Implementation

It’s mostly glue around Claude Code’s hooks system:

  • The Stop hook fires on every message
  • I throttle actual generation to every 10 messages, because empirically session themes stay stable across 40-50 messages while focus shifts every 8-10
  • When the threshold hits, it spawns a background job that reads the session transcript (JSONL), extracts recent context, and calls Claude Haiku via the claude CLI
  • The hook returns quickly (tens of ms) so Claude Code stays snappy, while summary generation happens async
  • A lock file prevents multiple generations from running at once

Things I Learned

Along the way I discovered a few annoying but useful things.

Summary generation can take 10-60 seconds depending on transcript size and complexity. You really don’t want it blocking the hook.

The claude CLI has overhead you don’t need for this use case. Turning off session persistence with --no-session-persistence and disabling tools with --tools "" helps.

Haiku occasionally ignores formatting instructions unless you’re very explicit. “Output ONLY the topic line” and “Do NOT output the word ‘Theme’ literally” got me to 100% format compliance.

If you go full set -euo pipefail in a script that renders your status line, you’ll eventually get a useless exit 1 in your UI instead of a fallback message. Ask me how I know.

The Plugin

I packaged this as claude-session-topics. The plugin registers the Stop hook automatically. Run /setup-statusline to configure your status line display.

Anyway, if you’re the kind of person who keeps multiple Claude Code sessions open and hates reloading context by scrolling, I’m now firmly in the “status line should show session topics” camp.

In conclusion: pro status-line topic summaries.

Comments

You May Also Enjoy

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.

Building a Claude Code Skill to Scratch My Own Itch

3 minute read

I’ve been using Claude Code lately to work on personal projects: a CLI for searching mountain peaks, Claude Code skills for route research, a Chrome extension for Mountaineers.org, and a tool to export GPX files from Strava. When Anthropic released Claude skills, I dove in and started experimenting with Obra’s superpowers. I liked that experience so much that I started building my own skills. This is one of them.

Virtualization with vagrant

less than 1 minute read

At the 2011 Pycon.UA conference, I presented on speeding up development with virtualized dev environments using VagrantUp and Fabric. Virtualization lets developers create consistent, reproducible development environments across teams. Vagrant makes this process simple by providing a unified workflow for managing virtual machines, while Fabric automates deployment tasks.

Automatically update project version info in sphinx documentation

1 minute read

I often need project version information for documentation, About boxes, or website footers. Instead of hardcoding version numbers, I let git provide them automatically. For my projects, git describe works best. It doesn’t modify sources on checkout and provides version information in a format usable in other git commands such as git diff.