Articles
Industry news, technical articles, and product introductions
📚 Claude Tutorials Hub
40+ step-by-step Claude guides — prompt engineering, Claude Code, API, agents. Browse by topic →
Loading...
Blocking rm -rf in Claude Code: A Deny Rule Stopped 14 Deletes in Two Weeks, 7 Other Spellings Still Get Through, and a Hook That Closes the Gap
To keep Claude Code from deleting things by accident, I added a deny rule, Bash(rm -rf *), to my global settings. Across my sessions from October 7 to 21 it blocked 14 deletes. After each denial the model picked a new directory name 8 times and dropped the delete 6 times. It never tried another spelling. Then I replayed 22 delete commands verbatim against Claude Code 2.1.285 through a stub. rm -fr, rm -r -f, rm -Rf and rm -r deleted the directory in manual, auto and bypass mode alike. /bin/rm, find -delete and bash -c deleted it in manual and bypass mode. In auto mode, rm -fr inside the working directory skips the classifier because it 'would be allowed in acceptEdits mode'. A second, built-in dangerous-rm check fires on targets like $D/*, even in bypass mode, but loses track of a variable assignment when a heredoc comes earlier in the same command. The post ends with a PreToolUse hook that blocks every recursive spelling in all three modes and tells the model what to do instead.
claude-codehooks+5
pitfallsOct 21, 20268 min
315Claude Code 踩坑实录：两个 AI 幻觉真实案例与 hook 日志交叉验证法
Claude Code (Opus 4.8) 一天内两次真实翻车：rg -rn flag 误用被 AI 判定为提示注入、凭空忏悔一次从未发生的文件删除——问题由 Fable 5 排查定案，Opus 4.8 多次测试未能自主发现。本文还原排查过程，并给出用 PostToolUse hook 建立真相基线日志的模型无关防御方案。
debuggingclaude-code+4
ai-tutorialsJul 20, 20265 min
260
Claude Code Hooks: Custom Automation Workflows
Deep dive into Claude Code's Hooks system. Learn to auto-run custom scripts before and after tool calls to build automation workflows that match your team's standards. Includes a hands-on lab: 38 `claude -p` sessions across the full 8-event matrix show only exit 2 blocks a tool (exit 1 and 3 both let it through), a UserPromptSubmit exit 2 aborts the whole turn in 0.195s with 0 turns and $0, and nine empty hooks cost less than the measurement noise.
claude-codeadvanced+3
claudeApr 13, 202613 min
601