Skip to contentWriting
- The Missing Layer: Static Security Analysis for CLAUDE.md and AGENTS.md25 April 2026 · 11 min readOWASP LLM Top 10 risks live in your instruction files. Runtime evals don't lint them. Here's what static security analysis catches — with a concrete finding.
- Scoring My Own MCP Contribution18 April 2026 · 5 min readA CLAUDE.md I wrote was merged into modelcontextprotocol/servers. My own scorer returned 59.2/100. Where it was right, where it was structurally unfair, and what the gap to 80 would cost.
- The blindspot, fixed18 April 2026 · 3 min readEarlier today I published a self-audit that named a blindspot in schliff. Hours later, the fix is up as a PR. The same CLAUDE.md now scores 61.0 instead of 59.2.
- What the EU AI Act Actually Asks of a Solo Builder17 April 2026 · 10 min readI built an AI matching system, ran it into Annex III, and walked out the other side. A solo builder's walk-through of EU AI Act compliance — what changed, what I filed, what nobody warned me about.
- Your CLAUDE.md Is an Agent Harness13 April 2026 · 10 min readYour CLAUDE.md is an agent harness. Skills are tools, hooks are guardrails, memory is persistence. How to stop configuring and start designing.
- Karpathy's LLM Wiki and the Problem Nobody Solved for 80 Years13 April 2026 · 11 min readKarpathy's LLM Wiki solves a problem older than computers: knowledge maintenance. Why every system from Memex to Obsidian failed — and what's different now.
- Hydra: A Multi-Model Code Review Council1 April 2026 · 8 min readA code review council built on Karpathy's LLM Council — six advisors across Claude Opus and Codex, cross-examined and synthesized into one verdict.
- Claude Code vs. Codex in 2026: What the Benchmarks Miss31 March 2026 · 13 min readI stopped comparing Claude Code and Codex last Tuesday. That's when Codex started reviewing Claude's code — from inside Claude Code.
- The Most Useful Claude Code Skills You Should Install28 March 2026 · 2 min readA curated guide to the Claude Code skills that actually save time — from automated debugging to spec-driven workflows.
- CLI > MCP: When a Bash Command Beats a Protocol Server27 March 2026 · 8 min readMCP has 97 million monthly downloads and 10,000 servers. But for 80% of what developers actually do, curl and jq is faster, cheaper, and more reliable.
- Claude Code Hooks: Automating Your AI Workflow25 March 2026 · 7 min readClaude Code hooks are shell commands that fire on events inside the agent loop. A working guide to the schema, the full event list, and the four traps people keep hitting.
- Skills Are the New Dotfiles24 March 2026 · 8 min readHow Claude Code skills became the new dotfiles — a personal developer identity layer that defines not just your tools, but how you think.
- MCP Servers That Actually Improve Your Dev Workflow20 March 2026 · 2 min readA practical look at Model Context Protocol servers — which ones matter, how to configure them, and what they enable.
- Why I Write Specs Before Code15 March 2026 · 6 min readEvery non-trivial article on this blog starts as a markdown spec. A practitioner's case for spec-first work with AI assistants — with the artifacts named.