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.

Choosing model tier and reasoning effort v1.0.0

Use this resource to size a model's capability and reasoning effort before spending budget on a run

New

  • 400 downloads
  • 208 likes
  • 151 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install model-tier-effort-sizing

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 assesses the task's complexity and risk, then recommends a capability tier and a reasoning effort on a neutral scale. It does not choose, launch or change any model.

Mostly picked by

Updated November 2, 2026

Card for the “Choosing model tier and reasoning effort” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: tier criteria (fast, standard, frontier) and effort levels
  • SKILL.md: recommendation format

Good fit for

  • A task looks costly for what it actually requires
  • You are torn between a fast model and a more capable one

Not for

    Tags

    • model
    • cost
    • sizing

    About

    You say

    “Tell me which model tier is enough to rename these 300 files.”

    Card for the “Choosing model tier and reasoning effort” skill

    Skill published by lilmgenius 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 size a model's capability and reasoning effort before spending budget on a run
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md6.2 KB

    Origin and licence

    Listed unmodified

    Author
    lilmgenius
    Source
    github.com/lilmgenius/paperthin/tree/7d5dc6235990230e45a24a25c527d81701da5458/skills/depth/modelchk
    Licence
    MIT

    Notice

    « modelchk » (lilmgenius, 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.