All Articles
Three Months of Letting Claude Code Handle the Monthly Content Refresh for My Four Wallpaper Apps
Starting in February 2026 I began handing off the monthly content refresh of my wallpaper apps — Beautiful HD Wallpapers and three sibling titles — to Claude Code. After three months I want to share what kinds of judgement I felt comfortable delegating, and where I deliberately kept my own hands on the work.
Adding Priority and Fairness to a Claude API Job Queue — Backpressure Patterns from a 50M-Download Indie App
A practical design for adding three-tier priority queues and Deficit Round Robin fairness to a Claude API worker. Drawn from running review-automation pipelines across an indie app catalog with 50M cumulative downloads, with full Python code and production metrics from a year of operation.
Designing a Model-Selection Fallback That Survives this model is currently unavailable on Claude API
The 'this model is currently unavailable' error from Claude API behaves nothing like a 529 Overloaded or a rate limit. After six months running it across six auto-publishing pipelines as an indie developer at Dolice, I'm sharing the failure conditions I observed and the per-request model-fallback implementation that ended my weekend firefighting.
Why Claude Code Breaks Your MDX Frontmatter With YAML Errors (and How to Fix It)
If you have ever let Claude Code mass-produce MDX articles, sooner or later your build dies with a cryptic YAML error. Nested double quotes, stray colons, comma-joined tag entries — here is what is actually happening and the five patterns I trust in production.
Holding the Line on Claude's Output Shape With <output_format> — A Pattern From My Indie App Copy Pipeline
How I keep multilingual App Store copy from drifting across 100+ locales by leaning on the <output_format> tag, with the prompts and validators I actually run.
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.
Allocating the 200K Context Window in Claude API — Budgeting System, Tools, Memory, and History in Production
Treat Claude API's 200K context as a budget rather than an open shelf. A TypeScript-backed allocation architecture that carves system, tools, memory, history, and headroom into explicit envelopes — built and tuned in a wallpaper app earning real ad revenue.
Why tool_result could not be submitted Keeps Coming Back, and How to Build a Recovery Handler That Actually Holds
Run a Claude agent long enough and one day it starts: 'tool_result could not be submitted', back to back, and retries change nothing. The error message hides four completely different root causes. Here is what I learned debugging this across the six auto-publishing pipelines I run as an indie developer, with the TypeScript recovery handler I now ship in production.
A Morning Digest Agent across App Store Connect, Play Console, Crashlytics, and AdMob — 30 days of running it on Claude Agent SDK
Opening four dashboards each morning across six apps used to eat 30 to 50 minutes of my day. Here is the Claude Agent SDK recipe that compressed it into one email, with the measured numbers from a full month.
Claude Code Hook `command timed out`: Timeout Settings and Split-Execution Patterns That Actually Work
Fix Claude Code's `command timed out` hook failure without just bumping the timeout. Includes practical split-execution, detached background jobs, and a settings.json layout that keeps your session fast.
Three Weeks of Tuning AdMob Floor Prices with Claude in Chrome
Notes from three weeks of small daily floor-price adjustments across four iOS apps, with Claude in Chrome doing the dashboard rounds and me keeping the judgment calls.
Forecasting Claude API token costs with ±10% accuracy from the first three days
A practical EWMA + seasonality decomposition model that forecasts month-end Claude API costs from only the first three days of token usage, with three-tier automated guardrails for prompt caching, model routing, and rate limiting.