Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Blocking destructive commands before they run v1.0.0

Use this resource to block destructive commands from a coding agent before they run

New

  • 557 downloads
  • 116 likes
  • 236 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install block-destructive-shell-commands-hook

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent configures Claude Code's PreToolUse hook: dangerous patterns are intercepted through rule packs, and safe commands pass. You get protection against destructive commands, with adjustable rules.

Mostly picked by

Updated November 2, 2026

Card for the “Blocking destructive commands before they run” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: overview, quick reference and common mistakes
  • references/installation.md: hook installation
  • references/pack-configuration.md: tuning rule packs
  • references/safety-patterns.md: detected safety patterns

Good fit for

  • You let an agent work unattended in a repository
  • You are worried about a git push --force on the main branch

Not for

    Tags

    • security
    • hook
    • commands
    • git
    • rust

    About

    You say

    “Install the guard and check that a git reset --hard is blocked before it runs.”

    Card for the “Blocking destructive commands before they run” skill

    Skill published by oakoss under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to block destructive commands from a coding agent before they run
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/command-detection.md4.6 KB
    • references/installation.md5.4 KB
    • references/pack-configuration.md3.7 KB
    • references/safety-patterns.md4.6 KB
    • references/troubleshooting.md3.4 KB
    • SKILL.md8.8 KB

    Origin and licence

    Listed unmodified

    Author
    oakoss
    Source
    github.com/oakoss/agent-skills/tree/85e3a3919d9e0ec7f7302a5143ec4b3e66f5f6ad/skills/destructive-command-guard
    Licence
    MIT

    Notice

    « destructive-command-guard » (oakoss, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.