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.

Guardrails against destructive commands v1.0.0

Use this resource to limit destructive commands and writes during a deployment or migration

New

  • 535 downloads
  • 149 likes
  • 101 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install destructive-command-guardrails

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 applies three modes: Careful asks for confirmation before risky commands, Freeze restricts writes to one folder, Guard combines both. These are instructions the agent follows, not a technical block: no hook ships with it. You stay in control of sensitive operations.

Mostly picked by

Updated November 2, 2026

Card for the “Guardrails against destructive commands” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: Careful, Freeze and Guard modes with watched patterns
  • SKILL.md: unlock procedure and enforcement limits

Good fit for

  • An agent works unattended on a production environment
  • You run a migration and want to block data deletions

Not for

    Tags

    • security
    • commands
    • guardrail
    • production

    About

    You say

    “Switch to Guard mode: writes only in src/billing, and confirmation before any deletion.”

    Card for the “Guardrails against destructive commands” skill

    Skill published by affaan-m 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 limit destructive commands and writes during a deployment or migration
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • SKILL.md2.5 KB

    Origin and licence

    Listed unmodified

    Author
    affaan-m
    Source
    github.com/affaan-m/ecc/tree/25278e7d7b6cf6e6a4e7a6c8e10f14ff22f0eb5b/skills/safety-guard
    Licence
    MIT

    Notice

    « safety-guard » (affaan-m, 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.