Hopping Claudes

oalders1 pts0 comments

On Hopping Claudes · olafalders.com&darr;<br>Skip to main content

Latest Articles

Hire Me

Projects

PrettyGoodPing

is: an inspector for your environment

MetaCPAN

My dotfiles

Categories

About

Feed

Dave Rolsky recently wrote about how he vibe-coded some<br>apps. One of the<br>neat things about today&rsquo;s tools is that we can write tools to scratch personal<br>itches with a lot less effort and friction. I&rsquo;ve written a macOS menu bar<br>timer, a custom Triathlon training plan<br>generator (with a static website and an iCal subscription), added a lot of<br>functionality to My Mind is Racing and, most<br>recently, I&rsquo;ve vibe coded yet another Claude Code agent<br>dashboard.<br>I could have used someone else&rsquo;s app but:<br>I wanted something that does EXACTLY what I want<br>It has to work with my very specific way of using git worktree and tmux<br>There&rsquo;s so much vibe coded stuff out there from people that I don&rsquo;t know and<br>don&rsquo;t yet trust. I don&rsquo;t want to introduce a new supply chain risk into my dev<br>stack<br>I asked Claude to do a bit of research and, after finding<br>disler/claude-code-hooks-multi-agent-observability<br>it used that as inspiration. The first 80% was quick, but there&rsquo;s a lot of<br>faffing about after that to get exactly what I want, because the LLM does not<br>yet read my mind. I&rsquo;ve been messing around with Claude Design, so after<br>shipping the app, I decided we could make it prettier. Now I have my dashboard.<br>I serve it on my Tailscale network, so that I can check on my agents using my<br>phone without having to resort to a terminal. That keeps it available to me,<br>but also private.<br>This allows me to track where something is in CI, whether something is<br>stalled, idle, or needs my feedback and what is ready for UAT or merge. My older<br>flow was flipping through A LOT OF TMUX SESSIONS to try to figure out where<br>everything was. No joy there. This is nicer for me.<br>I&rsquo;ve made the repo public as there&rsquo;s no reason to keep it private, but I&rsquo;ve only added the things that I need, because I&rsquo;m the only user. Maybe your LLM can draw some inspiration when you write your own dashboard.<br>Note that this blog post appears in the dashboard output. I don&rsquo;t use LLMs to write my posts, but I do use them for scaffolding, proofreading, etc.

Quick start:<br># 0. Install ubi (the Universal Binary Installer) if you don't already have it.<br>curl --silent --location https://raw.githubusercontent.com/houseabsolute/ubi/master/bootstrap/bootstrap-ubi.sh | TARGET=~/local/bin sh

# 1. Install the binary (see Install for manual download / build-from-source).<br>ubi --project oalders/clodhopper --in ~/local/bin

# 2. From a project's root, wire the capture hooks into its Claude Code settings.<br>cd /path/to/your/project

# set up hooks in .claude/settings.json or .claude/settings.local.json (idempotent)<br>clodhopper init

# 3. Use Claude Code in that project as normal — events start flowing immediately.

# 4. When you want to look, start the dashboard:<br>clodhopper serve # http://127.0.0.1:4555

See also:<br>disler/claude-code-hooks-multi-agent-observability<br>nicomen/saisons

Related

On GitHub Issues as Untrusted Input<br>June 25, 2026·628 words·3 mins<br>AI<br>security

Better Bots via Hooks<br>June 15, 2026·393 words·2 mins<br>AI<br>git

Claude Will Find a Way<br>June 11, 2026·804 words·4 mins<br>AI<br>security

&uarr;

rsquo claude code dashboard hooks want

Related Articles