73 skills tried, three still on disk
Claude Code keeps a usage ledger nobody reads. After 511 sessions I opened mine: 73 skills invoked, 31 of them exactly once, three still on disk. The survivors all have one thing in common.
Topic
Working with Claude Code
An agent as a collaborator rather than an autocomplete — design systems, durable knowledge, automation ladders, subagent fleets on my own source, and now in CI.
One mention, one merged PR: Claude Code as a GitHub App
I ran /install-github-app on my own repo and ten minutes later a README PR was merged. The timings are the least interesting part — the write path, the commit attribution and whose rules the CI agent followed are better.
82 agents, one bug: running Claude's security scanner on my own code
I pointed the new claude-security plugin at this very site. It spawned 82 agents, proposed 10 vulnerabilities, and then argued itself out of 9 of them. The one that survived was real — and it shipped to prod the same afternoon.
Shipping my own site at the speed of a prompt
How I turned my repo's operational knowledge into custom Claude Code skills — /dev, /code-review, /ship — so any change goes from idea to verified-in-production in a single session, with me still on the trigger.
Loop Engineering with Claude Code: Four Rungs and Three Bites
An evening climbing the loop ladder in Claude Code, from a one-shot fix to an unattended cloud routine. The lessons had nothing to do with the code and everything to do with how a loop stops: unenforceable budgets, self-writing reward hacks, and why a trapped loop cannot free itself.
OKF: How to Wire Durable Knowledge Into an AI-Assisted Project
Open Knowledge Format (OKF) is a dead-simple convention for storing durable, executable knowledge alongside your code — no database, no network, just markdown files your AI agent can read and act on.
I Turned My Website Into a Design System for Claude
I love how my site looks, so I taught Claude to build with it — extracting a live React app into a real design system on claude.ai/design, verified component by component.
Also relevant
Posts that touch this subject but live under another topic.
Traces, Tempo and the LGTM stack
Metering the agent fleet: cost & metrics for Claude Code subagents
If you distribute a Claude Code agent to a marketplace, every developer who runs it spends your reasoning budget and yours to answer for. Here is how I wired Claude Code's built-in OpenTelemetry into a Grafana/LGTM stack to watch cost, tokens and tool decisions — per run.