https://john.onlee.io/en/tags/coding-agents/Recent content in Coding-Agents on John on LeeHugoenWed, 05 Aug 2026 00:00:00 +0900https://john.onlee.io/en/guides/removing-ai-tells/Wed, 05 Aug 2026 00:00:00 +0900https://john.onlee.io/en/guides/removing-ai-tells/Instead of hand-fixing an AI draft’s awkward sentences every time, I built a correction loop where one flag becomes a permanent rule. The Claude Code skill structure, how real rules were born, layering a community skill on top, and a seed file you can start with in ten minutes.https://john.onlee.io/en/blog/karpathy-lotr-demo/Tue, 04 Aug 2026 00:00:00 +0900https://john.onlee.io/en/blog/karpathy-lotr-demo/One paragraph of Tolkien, a million tokens, two hours of autonomous execution, a 3D film. Not a demo review: how the unit of delegation is changing, and where a builder’s work moves next.https://john.onlee.io/en/guides/coding-agent-memory/Mon, 03 Aug 2026 00:00:00 +0900https://john.onlee.io/en/guides/coding-agent-memory/I build an agent memory platform, and this week we reversed its direction. What store-everything memory breaks, and how to route state, facts, and principles to the tracker, the code, and memory.https://john.onlee.io/en/guides/keeping-claude-md-light/Sun, 02 Aug 2026 00:00:00 +0900https://john.onlee.io/en/guides/keeping-claude-md-light/A CLAUDE.md does not get better as it grows. Why piling up rules degrades your agent, what belongs in the file, and where the rest should live: skills, hooks, and memory.https://john.onlee.io/en/blog/how-to-make-an-ai-coding-agent-actually-yours/Tue, 23 Jun 2026 00:00:00 +0900https://john.onlee.io/en/blog/how-to-make-an-ai-coding-agent-actually-yours/I built Monet to fix the agent that forgets yesterday’s conventions. How an agent that writes its own memory, reads what mattered, and grows with use actually works.https://john.onlee.io/en/blog/coding-agent-customization-survey/Sun, 31 May 2026 00:00:00 +0900https://john.onlee.io/en/blog/coding-agent-customization-survey/Two developers, same tool, wildly different setups. How deep coding agent customization goes — from bare defaults to full pipelines — and what actually pays off.https://john.onlee.io/en/blog/behavioral-llm-benchmark/Tue, 26 May 2026 00:00:00 +0900https://john.onlee.io/en/blog/behavioral-llm-benchmark/What today’s LLM benchmarks actually measure, what they miss, and why we need behavioral benchmarks instead of more knowledge tests.https://john.onlee.io/en/blog/token-economics/Thu, 21 May 2026 00:00:00 +0900https://john.onlee.io/en/blog/token-economics/Two requests with near-identical input tokens, a 46x cost gap. How prompt caching really works, and why agents should be designed around structured state.https://john.onlee.io/en/blog/does-your-coding-agent-need-memory/Thu, 14 May 2026 00:00:00 +0900https://john.onlee.io/en/blog/does-your-coding-agent-need-memory/Coding agents re-read the same files and re-ask the same questions every day. What memory actually does for an agent, how it differs from docs, and when it pays off.https://john.onlee.io/en/blog/context-window-management/Mon, 11 May 2026 00:00:00 +0900https://john.onlee.io/en/blog/context-window-management/Bigger context windows didn’t give better results. Notes on the context-management problems that keep recurring in real coding agent sessions.