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.

Offloaded reads of large files v1.0.0

Use this resource to delegate reading large files to a low-cost model to keep the context short

New

  • 430 downloads
  • 149 likes
  • 171 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install offloaded-large-file-reads

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 hands large or multi-file reads to a low-cost worker model, which answers a question and returns a compact summary. Raw contents never enter the main session context. A decision section helps choose between direct reading, delegation and the code graph.

Mostly picked by

Updated November 2, 2026

Card for the “Offloaded reads of large files” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: decision tree between direct reading and delegation
  • SKILL.md: how to use the bulk-read command
  • SKILL.md: worker model configuration

Good fit for

  • You need to analyse a whole folder without filling the context
  • You are looking for an answer across many files without opening each one

Not for

    Tags

    • context
    • token savings
    • file reading
    • delegation
    • claude code

    About

    You say

    “Ask the worker model which functions in this folder call the billing API, without loading the files.”

    Card for the “Offloaded reads of large files” skill

    Skill published by alinaqi 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 delegate reading large files to a low-cost model to keep the context short
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • SKILL.md2.3 KB

    Origin and licence

    Listed unmodified

    Author
    alinaqi
    Source
    github.com/alinaqi/maggy/tree/55aabe2493627e1de9cd09459d555181d66f3111/skills/context-shunt
    Licence
    MIT

    Notice

    « context-shunt » (alinaqi, 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.