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.

Managing the model response cache v1.0.0

Use this resource to manage the model response cache and its similarity thresholds

New

  • 471 downloads
  • 175 likes
  • 108 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-response-cache-management

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 calls the cache endpoints to read statistics, list or clear entries, and tune lifetimes and the semantic similarity threshold. You get a cache status and the settings applied.

Mostly picked by

Updated November 2, 2026

Card for the “Managing the model response cache” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: statistics, entries and reasoning cache endpoints
  • SKILL.md: purge and configuration payloads

Good fit for

  • Your costs rise while requests keep repeating
  • A stale response keeps being served from the cache

Not for

    Tags

    • cache
    • responses
    • ttl
    • similarity
    • costs

    About

    You say

    “Show the cache statistics, then clear entries older than seven days.”

    Card for the “Managing the model response cache” skill

    Skill published by cheaper-inference 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 manage the model response cache and its similarity thresholds
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.2 KB

    Origin and licence

    Listed unmodified

    Author
    cheaper-inference
    Source
    github.com/cheaper-inference/omniroute/tree/a2b7934c8a8fec680644349632f9c8e159a7403c/skills/omni-cache
    Licence
    MIT

    Notice

    « omni-cache » (cheaper-inference, 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.