cd /news/ai-agents/i-kept-adding-checks-to-make-claude-… · home › topics › ai-agents › article
[ARTICLE · art-164451] src=dev.to ↗ pub= topic=ai-agents verified=true sentiment=· neutral

I kept adding checks to make Claude Code reliable. Taking them off is what got the build moving

A small-business owner running five software projects on a single server used Claude Code to build them, and after roughly 460 commits over five days that grew the hook count from 28 to 46, the build stalled at 4 of 7 parts. After reviewing 20 sources, 16 from users and forums, the owner cut the accumulated checks and merged four project switches in about two hours, after which all 7 parts passed their checks — though an independent review found only 1 part fully met requirements and 6 only partly, and the cut disabled a feature one part depended on. The owner's guidance: list what must never happen and enforce only that, keep one plain list, have a person approve results, and start clean after two failed fixes.

by read2 min views5 publishedNov 5, 2026

I'm not a programmer. I run a small business with five software projects on one server, and Claude Code builds them. I work mostly at a desktop and by phone one or two days a week.

All I wanted was one central setup, so sessions would stop behaving differently and stop fighting what had already been decided. For weeks that didn't happen.

Every failure got a new check or a new rule. Over five days that meant about 460 commits, and the hooks grew from 28 to 46. The build sat at 4 of its 7 parts.

Our research kept asking how to stop Claude failing, and every answer to that question is another check. Our own notes had already said to freeze first. We never did it.

We asked a different question: what do people who finish actually run? We read 20 sources in full, 16 of them from users or forums, then:

The cut and all four project switches were merged in about two hours, after weeks of being stuck. The checks on all 7 parts of the build now pass, but an independent review found that overstates it: only 1 part fully meets what I asked for, and 6 are partly there. Some of those checks only prove something exists, and our cut switched off one thing a part asked for. So this is not finished, and I'll report what happens.

Written instructions have no guarantee, and Anthropic's own guide says so. Wording and repeat questions can still go wrong, and the same chat that did this work broke my answer format over and over. The cut also removed warnings that caught some mistakes, and it made mistakes of its own along the way, including removing things I'd never asked it to remove.

New chats finishing jobs, fewer repeat questions, and no damage getting past the hard stops. I'll update this post with the results, including if it doesn't work. List what must never happen and enforce only that. Keep one plain list, one item at a time. Have a person approve the result. After two failed fixes, start clean.

If you're interested, say so in the comments. I can share the structure we put in and a project overview you can paste into your own setup. This article was written with the help of Claude, from my own project's records. I've checked it and I stand by it.

── more in #ai-agents 4 stories · sorted by recency
── more on @claude code 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/i-kept-adding-checks…] indexed:0 read:2min 2026-11-05 · —