TL;DR — CLAUDE.md is powerful, but most people fill it with vague preferences that Claude...
TL;DR — CLAUDE.md is powerful, but most people fill it with vague preferences that Claude acknowledges and then ignores. The instructions that stick are specific, verifiable, and binary — not stylistic. This post shows the difference, with examples.
The CLAUDE.md that got ignored
My first CLAUDE.md had 30 lines. Things like:
- Write clean, readable code.
- Keep functions small and focused.
Most CLAUDE.md files fail because they don't actually constrain Claude's behavior. They become too...
Claude attends to ~150 instructions reliably. Past that the model summarises and stops following. Here is what stays in and what…
Most agent rules read like aspiration. A few read like physics. Five ways a CLAUDE.md instruction breaks, and the one test that…
Every CLAUDE.md I read grows. Nobody shrinks one. That's the symptom. The disease is treating it like...
Have you ever set up a CLAUDE.md file, dropped in 200 lines of rules, and then watched the AI...
CLAUDE.md, Skills, Subagents, Plugins, MCP: which Claude Code features actually earn their place. An honest layering guide from…
