김태영

Claude Code’s source code got leaked. Controversy and debate followed, but overnight someone had already built Claw Code and was racking up stars from around the world. This was clearly the time to go all in. Fear not, I’m coming! I get home from work and it’s already late, but that’s fine. Energy drink in my right hand, coffee in my left. I slept four hours a night for two days straight. ...

In EP.2, I used hooks to cut what Claude reads. Test results showed only failures, build logs only errors. I decided to measure how much I’d actually saved. Measure first Claude Code logs every conversation as JSONL files. They stack up per project under ~/.claude/projects/, each entry containing token usage. I built a script (analyze-tokens.js) that reads these, cross-references with daily session files, tallies turns, cache_read/write/output separately, and converts everything to cost. ...

I now have 5 projects. shop, blog, code_dungeon, good_game, and a root that manages them all (that’s not its actual name). Each project runs its own Claude session. The problem is there’s only one of me. If I kick off a task in shop and switch to editing a draft in blog, I have no idea when shop finishes. If I start Phase 1 in code_dungeon and go check on good_game, code_dungeon might be stuck waiting for permission and I wouldn’t know. Staring at 5 terminals in rotation isn’t monitoring. It’s just eye strain. ...

After trimming down to 9 agents and putting CLAUDE.md on a diet, the intervals between Compacting conversation... messages got noticeably longer. Same tasks, but it lasted much longer than before. Felt good. Then I was watching the console after requesting a new feature. Tests ran. 30 cases, all passing. But Claude was mentioning the successful tests again. Something felt subtly off. I asked Claude. “Why are you mentioning tests that already passed?” Claude explained the concept of tools. When Claude executes a terminal command or reads a file, those are all “tool calls.” And every time a tool runs, its entire output stacks into the conversation context. npm test results — 30 lines. Hugo build log — 180 lines. All of it. Tests all passed with nothing to look at, yet it read all 30. For build errors, only the last 5 lines mattered, but it loaded all 180. ...

A friend asked me to build an e-commerce site for cosmetics. I’d been writing nothing but C at work, so this was a chance to try a new stack. Toss Payments for checkout, React for the frontend. “Every next-gen finance project is going React” — that comment stuck with me, and Toss Payments was Node-friendly. The direction came together quickly. Obviously, I’d never used this stack before. I wanted to learn it, but the deadline didn’t allow for “study first, build later.” So I gave vibe coding a shot. ...