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.

Auditing LLM calls that only classify v1.0.0

Use this resource to find LLM calls that a cheaper classifier could replace, and price the gain

New

  • 375 downloads
  • 180 likes
  • 118 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install inference-cost-audit

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 searches the code for model calls, filters those returning a label, a score or a yes/no, measures their current latency and cost, then prices the swap. It ranks candidates by payoff and delivers a table. You get a prioritised list of savings with measured deltas.

Mostly picked by

Updated November 2, 2026

Card for the “Auditing LLM calls that only classify” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: candidate search, measurements, pricing and ranking by payoff
  • SKILL.md: report structure and the engagement approach the skill describes

Good fit for

  • You must cut the inference cost of an existing application
  • An agent loop feels slow for a simple decision

Not for

    Tags

    • cost
    • inference
    • latency
    • audit

    About

    You say

    “Audit our codebase for LLM calls that only route a request, and price the savings.”

    Card for the “Auditing LLM calls that only classify” skill

    Skill published by onewave-ai 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 find LLM calls that a cheaper classifier could replace, and price the gain
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md4.1 KB

    Origin and licence

    Listed unmodified

    Author
    onewave-ai
    Source
    github.com/onewave-ai/claude-skills/tree/b2267d9171af4f56848d82992381b20b89b44056/jev-audit
    Licence
    MIT

    Notice

    « jev-audit » (onewave-ai, 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.