When a Connector Starts Slowing Down at Night: A Health-Aware Circuit Breaker for Solo Automation
Seeing connector errors and latency is only half the job — the other half is deciding when to route around them. This is my implementation of a circuit breaker that opens on error rate and p95, with runnable Python and notes on wiring it into nightly jobs.
A connector failed for two nights and I never noticed — instrumenting my solo setup after observability went to public beta
The week connector observability hit public beta, I realized my one-person operation had no view into errors or latency. Here is how I wrapped my MCP connector calls in a thin meter and started reviewing it weekly.
Three Days of Running Claude Fable 5 Side by Side with Opus 4.8 — Settling My Model Split Before June 15
I ran Claude Fable 5 alongside Opus 4.8 on the same iOS maintenance tasks during the free introduction window. Where the new model clearly pulls ahead, where it does not, and how I split the two before the June 15 billing change.
Two Weeks of Splitting iOS Work Between Claude on Xcode and Claude Code
I ran Claude on Xcode, which lives in the Xcode sidebar, alongside Claude Code in the terminal across two weeks of real wallpaper-app work. Here is how I ended up dividing the tasks, and the simple rule I use to decide which one to open.
11 Days in Crashlytics: A Claude Code Debug Loop Across Two Android Wallpaper Apps
After shipping Beautiful Wallpapers v2.0.0 and Ukiyo-e Wallpapers v1.7.0 in early May, Crashlytics and Play Console threw more than 30 new issues at me in 11 days. This is the operations log of how I drove the fix list down to v2.1.1 / v1.8.1 using Claude Code as a triage partner.
Absorbing the Claude API "Tool Result Submitted" Error in a Retry Layer: A Small Conversation-History Repair
How I absorbed the Claude API "Tool result could not be submitted because the previous turn was not a tool use" error inside a small retry layer, with the diagnosis order I followed after it hit a production batch.
Notes from May 2026: Running a Parallel StoreKit 2 Migration Across Four iOS Wallpaper Apps with Claude Code
Operational notes from running a four-app iOS StoreKit 2 migration in parallel with Claude Code on a single Mac mini M5, captured during May 2026.
Six Weeks Running a Claude Code Hooks + SwiftLint Quality Gate on My Indie iOS Apps
A six-week field report on wiring SwiftLint into Claude Code's PostToolUse hook to keep my indie iOS codebases consistent. Motivation, implementation, three adjustments that mattered, and the rough edges I hit along the way.
Automating Multilingual App Review Replies with Claude API — Living with the App Store's Undocumented Limits
An indie developer running a portfolio of wallpaper and healing apps shares the full implementation of Claude API-powered multilingual review reply automation — including App Store's undocumented 8-second rule, session limits, and the three traps that can get you banned.
How to Encode Your Personal Voice in Claude's System Prompt — Lessons from Running 4 Sites
When every site starts sounding the same, the problem is in your system prompt. Here's what I learned running 4 AI-focused sites about encoding personal writing style so Claude actually sounds like you.
Managing iOS Localizable.strings with Claude Code — A Solo Developer's Multilingual Workflow
How a solo developer managing multiple wallpaper apps used Claude Code to streamline iOS localization. From extracting missing keys to quality checks — a realistic workflow for one-person teams.
90 Days Building a Solo SaaS with Claude Code — And the Three Things I Got Wrong
A working log from 90 days of building a solo SaaS with Claude Code — design conversations, model routing, and Cloudflare Workers constraints. Revisited months later against primary docs, with three technical claims corrected in place.