Chisle
The coding-agent plugin that bills 52% of a bare model across 20 live tasks. Terse persona + tool-output compressor + context diet.
翻訳待ち
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being executed by agents.
翻訳待ち
開発ツールRust · ShellGitHub @Dicklesworthstone自分でインストール所有者未確認
Paste into Claude or ChatGPT for installation instructions suited to your environment.
Have you tried it? One tap is enough. No sign-in needed.
Loading the full README. The saved excerpt is shown below.
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), Posit Assistant, Oh My Pi, and related tools.Read the full README ↗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), Posit Assistant, Oh My Pi, Factory Droid's Execute tool, and related tools.
Supported: Claude Code, Codex CLI 0.125.0+, Gemini CLI, GitHub Copilot CLI, VS Code Copilot Chat, Cursor IDE, Hermes Agent, Posit Assistant (Positron/RStudio extension, standalone server, and pa terminal client), Grok (xAI) (native ~/.grok/hooks/ plus Claude compatibility layer), Antigravity CLI (agy) (native ~/.gemini/config/hooks.json via dcg install --agy), OpenCode (native tool.execute.before plugin via dcg install --opencode — see docs/opencode-integration.md), Oh My Pi (omp) (native tool_call extension via dcg install --omp), Crush (native hooks.PreToolUse entry in crush.json via dcg install --crush — see docs/crush-integration.md), Reasonix (native hooks.PreToolUse entry in settings.json via dcg install --reasonix — see docs/reasonix-integration.md), Muse Code (native hooks.PreToolUse matcher group in ~/.config/muse/settings.json via dcg install --muse — see docs/muse-integration.md), Amp (native tool.call plugin via dcg install --amp — see docs/amp-integration.md), Pi (via extension recipe), Aider (limited—git hooks only), Continue (detection only)
Factory Droid's Execute tool is supported through dcg install --droid;
see coverage and Script-mode limitations.
Install a verified release on Linux, macOS, or WSL. The copyable recipe authenticates the pinned installer before running it and supports normal, easy-mode, and system-wide installation.
Install a verified release with PowerShell. This recipe checks the installer's pinned SHA256 and Minisign signature before execution, then requires Minisign verification of the native binary too.
The Problem: AI coding agents (Claude, Codex, Gemini, Copilot, etc.) occasionally run catastrophic commands like git reset --hard, rm -rf ./src, or DROP TABLE users—destroying hours of uncommitted work in seconds.
The Solution: dcg is a high-performance hook that intercepts destructive commands before they execute, blocking them with clear explanations and safer alternatives.
| Feature | What It Does |
|---|---|
| Zero-Config Protection | Blocks dangerous git/filesystem commands out of the box |
| 50+ Security Packs | Databases, Kubernetes, Docker, AWS/GCP/Azure, Terraform, and more |
| Sub-Millisecond Latency | SIMD-accelerated filtering—you won't notice it's there |
| Heredoc/Inline Script Scanning | Catches python -c "os.remove(...)" and embedded shell scripts |
| Smart Context Detection | Won't block grep "rm -rf" (data) but will block rm -rf / (execution) |
| Rich Terminal Output | Human-readable denial panels, rule context, and suggestions on stderr |
| Agent-Safe Streams | Machine-readable hook output stays on stdout while rich UI stays on stderr |
| Native Codex Support | Codex CLI 0.125.0+ receives a minimal stdout JSON denial that current clients enforce reliably |
| Graceful Degradation | Plain output for CI, pipes, dumb terminals, and no-color environments |
| Scan Mode for CI | Pre-commit hooks and CI integration to catch dangerous commands in code review |
| Bounded Failure Policy | Analysis timeouts become explicit review/block outcomes; malformed raw hook envelopes remain auditable and configurable |
| Explain Mode | dcg explain "command" shows exactly why something is blocked |
# AI agent tries to run:
$ git reset --hard HEAD~5
# dcg intercepts and blocks:
════════════════════════════════════════════════════════════════
BLOCKED dcg
────────────────────────────────────────────────────────────────
Reason: git reset --hard destroys uncommitted changes
Command: git reset --hard HEAD~5
Tip: Consider using 'git stash' first to save your changes.
════════════════════════════════════════════════════════════════
# ~/.config/dcg/config.toml
[packs]
enabled = [
"database.postgresql", # Blocks DROP TABLE, TRUNCATE
"kubernetes.kubectl", # Blocks kubectl delete namespace
"cloud.aws", # Blocks aws ec2 terminate-instances
"containers.docker", # Blocks docker system prune
]
This is the beginning of the README. Read the rest at the original. Read the full README ↗