Claude-Code

A month ago I wrote about making Claude Code actually ship software. The workflow has been through at least six revisions since I started, but this latest version has been stable. Now it’s packaged as momentum. What This Actually Is Not another “make AI smarter” attempt. This is a workflow that assumes you know what you’re doing and gives you tools to do it faster. A recent post about building Log Carver at C-speed nailed it: “AI is no longer just a productivity booster. It’s a compiler for ideas. But like any compiler, it needs constraints, tests, and a damn good operator behind the keyboard.” ...

For those dabbling with Claude Code subagents: they consume a TON of tokens. Which is fine—if you’re burning them for the right reasons. A blog writer subagent? Maybe that works. You see the final output, judge quality, iterate. But when subagents touch multiple files across your codebase? That’s where things can get problematic. TL;DR Subagents burn 10x more tokens than custom commands. ~50-100K tokens for implementation work vs ~5-10K for the same task with /plan-task. Your mileage may vary, but the difference is substantial. ...

I was watching Miessler demo OpenCode against Claude Code. He fed it a video transcript with 900 lines of custom rules - formatting, content generation, image creation. Complex orchestration. It just… worked. Not because it was simple. The rules weren’t trivial. But because it was focused. One clear task with defined inputs, explicit constraints, specific outputs. It clicked. This is what I’d been building toward with my newly refactored development workflow - breaking work into focused units. Ideation separate from planning. Planning separate from implementation. Implementation separate from testing. Even my shortcut commands in CLAUDE.md follow the pattern: qtest writes ONE test. qfix debugs ONE error. qcom makes ONE commit. ...

TL;DR LLMs are incredible force multipliers for building software. I’m building multiple projects concurrently with Claude Code. They excel at ideation, planning, and code generation when you do it right. But they struggle with predictable runtime behavior. They’re probabilistic systems at their core - you’ll get different results across runs no matter how much you prompt engineer. The variation isn’t a bug; it’s the architecture. Design for their nature, don’t fight it. They can be embedded in software when you account for variability. Great for chatbots, content generation, analysis work where you want different responses. ...

TL;DR Claude Code is powerful, like really.. but chaotic without some structure. Many people probably use it an ad-hoc fashion and there’s nothing wrong with that. I built a systematic workflow that turns it into a shipping machine. The magic is in the command structure. /plan-iteration → /plan-task → implement → /complete-task → /complete-iteration. Each command has specific responsibilities and quality gates. Evidence-based completion prevents the “is it done?” problem. /complete-iteration requires concrete proof that users can access working software. No more marking things “complete” when they’re just coded. ...

I keep hearing that LLMs aren’t good engineers. I think I figured out why, and possibly how to address it. Here’s what I was seeing in my Claude Code workflow. Even with comprehensive specs - detailed HLD, implementation specs, task breakdown - there’s still ambiguity between knowing what to build and knowing the best approach to take when building it. When I’d run /plan-task, Claude would pick a viable path and run with it, without exploring alternatives, because it’s not built to do otherwise. ...

TL;DR I had a critical gap in my Claude Code workflow. Everything was optimized except the moment Claude actually writes code. Even with auto-accept enabled, I was gambling that /complete-task would catch violations after many changes. Hooks let you inject real-time quality checks. When Claude Code hooks became available, I could finally add guardrails that run outside Claude’s context but feed results back through JSON decision control to block bad edits. ...

How I discovered that LLM limitations reveal fundamental truths about software architecture in the AI era The Breaking Point Isn’t What You Think After months of AI-assisted development, I hit a wall that had nothing to do with prompting skills or context limits. The problem was deeper and more fundamental: LLMs lose their minds when applications exceed their cognitive capacity. I wasn’t building monoliths. My applications had proper separation of concerns, clean data models, comprehensive tests, and type safety. The repository pattern, service layers, configuration management - all the architectural best practices were there. But as these well-structured applications grew in complexity, something strange happened. ...

This continues my exploration of AI-assisted development workflows, building on insights from Making Security Ambient and the practical lessons learned from daily Claude Code usage. The Evolution of AI-Assisted Development The progression has been fascinating to observe—and participate in. We started with simple one-shot prompts: “Generate this function.” Then we got smarter about light planning, adding some structure to our requests. From there, we developed systematic AI-assisted workflows like the /plan-task approach I’ve written about, where architectural guardrails transform unpredictable AI assistance into something more craftsperson-like. ...

In the previous article on Beyond Comprehensive Context, I explored how AI-assisted development revealed challenges with comprehensive documentation and token efficiency. What follows are my approaches for memory optimization that emerged from daily use—not as a definitive solution, but as a possible option. The Layered Memory Paradigm What I’ve discovered through daily practice is that Claude Code’s memory system reveals something pretty cool about how expertise actually functions. The system’s three-layered structure mirrors the way I think about knowledge—from universal principles to contextual applications. ...