Claude apologised and promised never to do it again? Do not trust promises, set up hooks
Claude apologised and promised never to do it again, and a couple of days later it all happened again. A promise lives in one conversation, and Anthropic's guide calls the rules in CLAUDE.md advice. A hook is a check Claude cannot skip: Claude Code runs it itself, before an action, after it or at the end of an answer. Where a hook is needed (deleting data, emails, putting code online, spending money), where it only slows the agents down, and the author's five working hooks: dangerous commands, emails in his name, the task log, the skeptic and a sound. The recording of the masterclass and the working kit of files that goes with it.
O passo a passo em vídeo é para assinantes
O texto acima é grátis e continua grátis. O passo a passo gravado é o que a assinatura acrescenta.
Ver planosArtefato
Hooks kit, 18 files
- how-to-repeat.md The instruction for you: what you will need, how to set it up and how to check each hook. Start here. 6 KB
- CLAUDE.md The order for your Claude Code: explain the hooks, write in your details, test and install them. 8 KB
- block-dangerous-commands.sh Hook 1: stops deleting tables and databases, rewriting code history and turning off the computer's network. 5 KB
- block-email-in-my-name.sh Hook 2: stops an email where you are the sender, from the terminal or through a program. 4 KB
- letter.md The letter after the session: what the lesson was about and where to start. 3 KB
Os arquivos em si são para assinantes. A lista acima é completa: é tudo o que há no conjunto.
Ver planosPergunte sobre este case
A pergunta vai para o autor, não para esta página. Nada do que é enviado aqui é publicado, e a resposta chega no endereço que você deixar.