Category
AI
- ·3 min read
Exit 0 Is Not Evidence: Why AI Coding Agents Need Receipts, Not More Memory
Claude, Codex, Beads, and gbrain each preserve a different kind of truth. One week of silent failures taught me that an agent's report is a claim, memory is a hypothesis, and done requires evidence bound to the exact state that was tested.
- ·3 min read
Statusline v2: Three Rows, Clickable Links, and a Live Project HUD
Upgrading a Claude Code statusline past one line: a three-row layout, clickable branch and PR links, rate-limit pacing arrows, and a live project-state row for GSD, OpenSpec, and Beads — plus the full updated script and where to start if you're extending your own.
- ·3 min read
Workflow vs Agent Team: Two Ways to Run Many Claudes
Once you're spawning subagents, you hit a fork: let the lead agent decide who to spawn and when, or script the orchestration deterministically up front. They feel similar and fail differently. Here's how I pick.
- ·3 min read
The Subagent I Deleted: A Field Note on Layer Discipline
I wrote a subagent that worked. I deleted it ten days later. The replacement was three lines of Prettier config. A short note on the wrong-layer trap, the four-questions test, and why a mature agent-ready repo isn't the one with the most artifacts in it.
- ·3 min read
Installing Isn't Teaching: What I Learned From Auditing My Own Shell History
I asked Claude what new CLI tools I should install based on my last week of shell history. The honest answer wasn't a list of tools — it was that I'd already installed half the modern tools I needed and was still typing `cat` and `cd` like it was 2010. A short note on the gap between *having* a tool and *reaching* for one, and where that same gap shows up in your `CLAUDE.md`.
- ·3 min read
Skills: The User-Facing Workflow Layer
Hooks enforce rules. Subagents review work. Commands and skills are how the team actually invokes them — thin wrappers route to detailed workflows, encoding multi-step knowledge in a single, memorable slash command. The architecture dissected.
- ·3 min read
Subagents That Catch What Hooks Can't
Hooks block known-bad patterns. Subagents make the judgement calls hooks can't — type safety, architecture compliance, accessibility. One real subagent, dissected, plus a template for writing your own.
- ·3 min read
The Identifier That Made My Podcast Sound Russian
I spent an evening shrinking ElevenLabs chunk size from 2500 characters down to 1000, convinced the model was choking on density. It wasn't. One camelCase identifier — appearing three times in a single paragraph — was making my voice clone drift into a Russian accent. A field note on debugging non-deterministic systems.
- ·3 min read
From Audit to Hook: Turning Drift Into Enforcement
A tooling audit surfaces drift. CLAUDE.md tells the agent not to do it. Hooks make sure it actually doesn't. Eight real scripts from a production codebase, with the audit finding each one came from.
- ·3 min read
The Claude Hooks Lifecycle: A Primer You Can Bookmark
Eight events, one JSON payload format, three exit codes that matter. The reference doc I wish I had open the first time I wrote a Claude Code hook.
