{
  "id": 5497453,
  "title": "What Works and What Doesn't in CLAUDE.md",
  "url": "https://urgent.news/2026/09/04/what-works-and-what-doesnt-in-claude-md",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-04T05:30:40.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/quintetkit/what-works-and-what-doesnt-in-claudemd-d22"
  },
  "original_language": "en",
  "account": "Writing clean code in CLAUDE.md changes nothing. During the process of building personal apps, I rewrote CLAUDE.md many times. Clear instructions that can be verified, such as not using pure black or white colors, do not use gradient backgrounds, and limit to three types of motion per screen. These rules can be checked with grep. Verifying that code is clean is difficult, so it does not work well. Limiting permissions by explicitly stating what cannot be done is more effective than suggesting what should be done. Providing an exit, such as \"stop implementation and report it,\" helps the model retreat when it hits constraints. Writing exceptions in advance avoids inconsistent judgments. Keeping the file short and focusing on verifiable rules works best.",
  "summary": "Writing \"Write clean code\" in CLAUDE.md changes nothing. During the process of building 10 personal apps in three months, I rewrote CLAUDE.md many times. Since it became clear what worked and what didn't, I will outline that distinction. What Doesn't Work Giving instructions with adjectives - Write clean code - Design for maintainability - Handle errors appropriately - Consider performance None…",
  "key_points": [
    "Clear, verifiable rules improve CLAUDE.md code quality",
    "Explicitly limiting permissions is more effective than suggesting actions",
    "Providing an exit helps model retreat when constraints are hit"
  ],
  "editors_take": "Effective guidelines for code cleanliness in CLAUDE.md hinge on clear, verifiable rules and limiting permissions, rather than vague suggestions, to keep the model on track and consistent.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}