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.

Measure cost savings on a corpus v1.0.0

Use this resource to verify routing accuracy and real cost on a test corpus

New

  • 418 downloads
  • 163 likes
  • 199 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install cost-corpus-benchmark

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 runs the structural and adversarial corpus, writes per-case and summary results to the runs folder, and compares measured figures with claimed ones. Options add reference models as baselines.

Mostly picked by

Updated November 2, 2026

Card for the “Measure cost savings on a corpus” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: corpus run steps
  • SKILL.md: smoke gates and environment overrides

Good fit for

  • You are releasing a version and want to check for regressions
  • You are growing the corpus and want to check new cases

Not for

    Tags

    • benchmark
    • cost
    • corpus
    • routing

    About

    You say

    “Run the cost benchmark and tell me whether the win rate dropped.”

    Card for the “Measure cost savings on a corpus” skill

    Skill published by ruvnet 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 verify routing accuracy and real cost on a test corpus
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md3 KB

    Origin and licence

    Listed unmodified

    Author
    ruvnet
    Source
    github.com/ruvnet/ruflo/tree/89b0cd02dd99ea1f63437fde6c05992ec53cc22b/plugins/ruflo-cost-tracker/skills/cost-benchmark
    Licence
    MIT

    Notice

    « cost-benchmark » (ruvnet, 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.