All Articles
Catching Template Phrases Before They Ship: grep Guards in Claude Code SKILL.md
Even with detailed prompt instructions, generating articles every day eventually lets template phrases slip through. I added grep-based guards to the final step of my Claude Code SKILL.md so that violations block the push and force the model to rewrite. Here's what changed after one week.
What metadata.user_id in the Claude API Is Actually For — Designing the Abuse-Detection vs. Privacy Trade-off
The metadata.user_id field in the Messages API exists to sharpen abuse detection, but sending raw email addresses creates a privacy problem. Here is the HMAC-based stable pseudo-ID pattern I use, plus a clear set of rules for when to send it and when not to.
When Claude Code's Read Tool Silently Truncates Large Files — offset/limit Patterns and When to Reach for Bash
Lessons from running an indie app business since 2014: how Claude Code's Read tool quietly cuts off after 2000 lines, the three signs of truncation, and when to use offset/limit versus bash.
Why Claude Code's Glob and Grep Return Zero Results
When Claude Code's Glob or Grep tool returns no matches even though the files clearly exist, the cause is almost always one of four things. Here's how to triage.
Bulletproof JSON Output with Claude API Prefill: A Four-Layer Defense Pattern from Indie SaaS
How I went from late-night JSON parse failures to a 100% parse success rate across thousands of monthly Claude API requests. Working code in TypeScript and Python, plus production numbers from an indie SaaS.
A Five-Layer Preflight Design for Claude API — How I Cut Hundreds of 400/422/529 Errors to Zero
A production-tested five-layer preflight design that catches Claude API failures before the network call — schema, token budget, model capability, content policy, and spend cap — with full TypeScript implementation and one month of operational numbers.
Designing Claude Code Skills That Actually Run Unattended — Three Patterns to Avoid Permission-Dialog Stalls
I learned the hard way that Claude Code skills can silently freeze in scheduled runs because of permission dialogs. Here are three implementation patterns that keep file work, path detection, and recovery fully autonomous — distilled from a month of running content automation across four sites.
Type-Safe Claude API Tool Calling with Zod: Patterns for TypeScript Developers
How to implement Claude API tool calling with TypeScript and Zod for full type safety. Covers schema-to-API conversion, runtime validation, and three common pitfalls with practical code examples.
Implementing the Saga Pattern in Claude Agent SDK — Compensating Transactions and Idempotency
A practical guide to building safe multi-step Claude Agent SDK workflows. We cover compensating transactions, idempotency keys, and partial-failure state recovery, all from patterns that have run in production.
Pre-commit AI Review with Claude Code, husky, and lint-staged — Reviewing Only Staged Files
A pragmatic guide to running a lightweight Claude Code review on only the files you've staged for commit. Using husky and lint-staged, this setup minimizes both cost and latency for solo developers.
Implementing the Transactional Outbox Pattern with Claude Agent SDK — Eliminating Lost Side Effects in Production
Stop the 'the row was inserted but the email never went out' class of bugs in Claude Agent SDK apps. A production-grade walkthrough of the Transactional Outbox pattern using Postgres and Cloudflare Queues.
Parallel Development with Claude Code Across Multiple Repos — What Three Simultaneous Projects Taught Me
Claude Code gets messy with multiple repos. Here are the CLAUDE.md strategies, session habits, and cost tips from three months of real parallel development.