Skip to content

[GitHub Trending] Dicklesworthstone/destructive_command_guard

7.9 relevance
Score Breakdown
technical depth
7
novelty
8
actionability
9
community
7
strategic
8
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Guard against destructive commands from AI agents, critical for agent safety and highly actionable.

AI/ML github.com
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents. - Dicklesworthstone/destructive_command_guard
Summary

Destructive Command Guard (dcg) is an open-source hook that blocks catastrophic commands from AI coding agents like Claude Code, Codex CLI, Gemini CLI, Copilot CLI, Cursor, and Grok before execution. It uses SIMD-accelerated filtering for sub-millisecond latency and ships with 50+ security packs covering databases, Kubernetes, Docker, and major cloud providers. The tool features fail-open design, heredoc/inline script scanning, and smart context detection to avoid false positives.

Author

Dicklesworthstone