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.

Repository risk check before an agent edits v1.0.0

Use this resource to check that a repository is safe before an AI agent changes it

New

  • 345 downloads
  • 209 likes
  • 225 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-edit-risk-preflight

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 inspects local files for destructive commands, risky hooks, automation that writes credentials and uncommitted changes. You get a green, yellow or red receipt with the next action to take.

Mostly picked by

Updated November 2, 2026

Card for the “Repository risk check before an agent edits” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: inspection method and risk receipt format
  • references/decision-rules.md: green, yellow and red decision rules

Good fit for

  • You want to run Claude Code on a repository you do not know
  • A repository contains hooks that could write credentials

Not for

    Tags

    • ai agent
    • security
    • hooks
    • repository

    About

    You say

    “Check this repository before Claude Code makes any changes.”

    Card for the “Repository risk check before an agent edits” skill

    Skill published by Signal Loom Works <194151508+el-zachariah@users.noreply.github.com> 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 check that a repository is safe before an AI agent changes it
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.6 KB
    • references/decision-rules.md1.2 KB
    • SKILL.md4.8 KB

    Origin and licence

    Listed unmodified

    Author
    Signal Loom Works <194151508+el-zachariah@users.noreply.github.com>
    Source
    github.com/jeremylongshore/tons-of-skills-marketplace/tree/ab85a061f7bcc039dac13ee193de7a4cd4388571/skills/.curated/agent-safety-preflight
    Licence
    MIT

    Notice

    « agent-safety-preflight » (Signal Loom Works <194151508+el-zachariah@users.noreply.github.com>, 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.