I instrumented my Claude Code session logs by project. 50% of a $13K shadow-cost week goes to one codebase. The other six combined did not break $200.
Hi, I'm Jie 👋
I keep a commercial KVM cloud platform from falling over for a living. On the side I run a multi-agent Claude Code pipeline that has put 32 iOS apps on the App Store. I write here when something in either world surprises me — usually with a number attached.
-
Shipped claude-agent-ledger v0.4 —
added
--by project, found out 50% of my Claude Code spend goes to one codebase. - ShipReady v1.0 sitting in Apple review since Apr 19. PetBook v1.0.8 in queue too.
- This site is the new public surface — built it Mon–Tue. The OG image is auto-generated; see scripts/og_image.py.
frexx.top
32 iOS apps on the App Store. All solo. All shipped through the same multi-agent pipeline.
prereviews.app
Pre-flight audit for App Store submissions. Free in-browser audit + Mac App with 60+ checks and AI second-pass.
apple-presubmit-audit
70+ App Store Review checks built from ~50 real rejections. CLI for indie iOS devs. Same engine that powers ShipReady.
claude-agent-ledger →
Per-subagent · per-model · per-project · per-session · per-day cost attribution for Claude Code. Reads the local JSONL session logs and shows what each dimension actually consumed at marginal API rates. My own pipeline runs at ~$13K/week shadow cost on a $200/mo Max plan (~250× leverage) — the gap is the most interesting thing I've seen in LLM infra this year.
npm install -g claude-agent-ledger
agent-ledger week --summary - Where my Claude Code spend actually went last week
AI Agents ship fast but break in the same long-tail ways distributed systems always have. Most teams don't yet have the eval, observability or reliability practices to catch it.
Six years of debugging a hypervisor at 3 AM gives you a reflex: if you don't have a per-component bill of materials, you don't actually understand the system. I'm pointing that reflex at AI Agents.