destructive_command_guard
bydicklesworthstone· 102 skills
Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.
How to install destructive_command_guard?
dicklesworthstone/destructive_command_guard
$npx -y skills add dicklesworthstone/destructive_command_guard --skill destructive_command_guardInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Run `npx skills use "https://github.com/dicklesworthstone/destructive_command_guard" --skill "dicklesworthstone/destructive_command_guard"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/dicklesworthstone/destructive_command_guard" that are relevant to the current task. Run `npx skills add "https://github.com/dicklesworthstone/destructive_command_guard"` and select the relevant skills, then follow their instructions.
SKILL.md
| 1 | # dcg (Destructive Command Guard) |
| 2 | |
| 3 | <div align="center"> |
| 4 | <img src="illustration.webp" alt="Destructive Command Guard - Protecting your code from accidental destruction"> |
| 5 | </div> |
| 6 | |
| 7 | <div align="center"> |
| 8 | |
| 9 | [](https://codecov.io/gh/Dicklesworthstone/destructive_command_guard) |
| 10 | [](LICENSE) |
| 11 | |
| 12 | </div> |
| 13 | |
| 14 | A high-performance hook for AI coding agents that blocks destructive commands before they execute, protecting your work from accidental deletion across Claude Code, Codex CLI, Gemini CLI, Copilot CLI, VS Code Copilot Chat, Cursor, Hermes Agent, Grok (xAI), and related tools. |
| 15 | |
| 16 | **Supported:** [Claude Code](https://claude.ai/code), [Codex CLI 0.125.0+](https://github.com/openai/codex), [Gemini CLI](https://github.com/google-gemini/gemini-cli), [GitHub Copilot CLI](https://docs.github.com/en/copilot/concepts/agents/coding-agent/about-hooks), [VS Code Copilot Chat](https://code.visualstudio.com/docs/agent-customization/hooks), [Cursor IDE](https://cursor.com), [Hermes Agent](https://github.com/NousResearch/hermes-agent), [Grok (xAI)](https://x.ai/news/grok-build-cli) (native `~/.grok/hooks/` plus Claude compatibility layer), [Antigravity CLI (`agy`)](https://antigravity.google) (native `~/.gemini/config/hooks.json` via `dcg install --agy`), [OpenCode](https://opencode.ai) (via [community plugin](https://github.com/aspiers/ai-config/blob/main/.config/opencode/plugins/dcg-guard.js)), [Pi](https://github.com/earendil-works/pi) (via [extension recipe](docs/pi-integration.md)), [Aider](https://aider.chat/) (limited—git hooks only), [Continue](https://continue.dev) (detection only) |
| 17 | |
| 18 | <div align="center"> |
| 19 | <h3>Quick Install</h3> |
| 20 | |
| 21 | ```bash |
| 22 | curl -fsSL "https://raw.githubusercontent.com/Dicklesworthstone/destructive_command_guard/main/install.sh?$(date +%s)" | bash -s -- --easy-mode |
| 23 | ``` |
| 24 | |
| 25 | <p><em>Works on Linux, macOS, and Windows via WSL. Auto-detects your platform, downloads the right binary, and configures supported agent hooks including Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, VS Code Copilot Chat (through VS Code's Claude-hook compatibility), Cursor IDE, Hermes Agent, and Grok (xAI) (via <code>dcg install --grok</code> for a native <code>~/.grok/hooks/dcg.json</code>, or via the Claude compatibility layer automatically picked up by Grok). For native Windows, use the PowerShell installer below.</em></p> |
| 26 | |
| 27 | <h4>Windows (native, PowerShell)</h4> |
| 28 | |
| 29 | ```powershell |
| 30 | & ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Dicklesworthstone/destructive_command_guard/main/install.ps1"))) -EasyMode -Verify |
| 31 | ``` |
| 32 | |
| 33 | <p><em>Installs native <code>dcg.exe</code>, verifies the mandatory SHA256 checksum, verifies the release's long-lived minisign signature when <code>minisign</code> is available, and verifies Sigstore/cosign provenance when both <code>cosign</code> and a trusted bundle are available. It adds dcg to your User <code>PATH</code> (<code>-EasyMode</code>), runs a self-test (<code>-Verify</code>), and configures detected agent hooks for Claude Code, Codex CLI, Gemini CLI, GitHub Copilot CLI, Cursor IDE, and Hermes Agent. Copilot is configured at the user level under <code>%COPILOT_HOME%\hooks</code> (or <code>%USERPROFILE%\.copilot\hooks</code>) so every workspace is protected. On Windows the <code>windows.filesystem</code> and <code>windows.system</code> packs are on by default, so <code>del /s</code>, <code>rd /s</code>, <code>Remove-Item -Recurse</code> (with or without <code>-Force</code>), <code>format</code>, and <code>vssadmin delete shadows</code> are blocked out of the box. Pin a version with <code>-Version vX.Y.Z</code>; use <code>-RequireMinisign</code> to fail closed if the sidecar or verifier is unavailable.</em></p> |
| 34 | </div> |
| 35 | |
| 36 | --- |
| 37 | |
| 38 | ## TL;DR |
| 39 | |
| 40 | **The Problem**: AI coding agents (Claude, Codex, Gemini, Copilot, etc.) occasionally run catastrophic commands lik |
Related
6 picksType
- azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage.Jul 2026
- appinsights-instrumentationGuidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references.Jul 2026
- diagnosing-bugsDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.Jul 2026
- systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesJul 2026
- safe-debugRigor Debug / Rigor Audit skill for deep learning research work.Jul 2026
- golang-error-handlingIdiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single…Jul 2026
