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

PalateKit

Menu

Request a resource

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

0 / 280

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.

Designing a CLI agents can use and humans can supervise v1.0.0

Use this resource to design and build a CLI that is safe for an agent and supervisable by a human

New

  • 557 downloads
  • 238 likes
  • 133 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-friendly-cli-design-3

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 sets where the contract comes from, the command shape, safeguards proportionate to the possible damage and the verification tests. You get a CLI with JSON output, a dry-run option, an audit log and authentication rules.

Mostly picked by

Updated November 2, 2026

Card for the “Designing a CLI agents can use and humans can supervise” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: six phases, from command shape to verification
  • references/: authentication patterns, audit log, JSON contract, human output and testing
  • cases/: worked examples of CLIs already built

Good fit for

  • You are wrapping an API in a command-line tool for agents
  • You are adding --json and --dry-run to an existing CLI

Not for

    Tags

    • cli
    • agents
    • json
    • security

    About

    You say

    “Design a CLI to manage the invoices in my local database, with a simulation mode.”

    Card for the “Designing a CLI agents can use and humans can supervise” skill

    Skill published by crafter-station 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 design and build a CLI that is safe for an agent and supervisable by a human
    3. Review and adjust the result

    Content preview

    Files

    • cases/conventions.md11 KB
    • cases/osmo.md4.2 KB
    • cases/portfolio-shape.md3.2 KB
    • cases/README.md5.3 KB
    • cases/sunat-cli-renta.md8 KB
    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/audit-log-patterns.md5.4 KB
    • references/auth-patterns.md6.6 KB
    • references/build-and-runtime.md7.6 KB
    • references/compounding-surface.md7.1 KB
    • references/human-output.md14.7 KB
    • references/json-contract.md6.7 KB
    • references/testing.md2.7 KB
    • references/trust-ladder-patterns.md6.5 KB
    • SKILL.md20.5 KB

    Origin and licence

    Listed unmodified

    Author
    crafter-station
    Source
    github.com/crafter-station/skills/tree/f0fe474d76ed3f04113664095ff1b9e9844e8020/skills/cli-build
    Licence
    MIT

    Notice

    « cli-build » (crafter-station, 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.