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.

Reasoning, memory and context standards for agents v1.0.0

Use this resource to frame the behavior, memory and context of an autonomous coding agent

New

  • 340 downloads
  • 239 likes
  • 237 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install agent-reasoning-memory-standards

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 applies a framework for reasoning, memory organization and output verification to the setup of a coding assistant. You get behavior guidelines and a context management strategy.

Mostly picked by

Updated November 2, 2026

Card for the “Reasoning, memory and context standards for agents” skill

Details

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

Similar resources

View all

What you get

  • SKILL.md: overview, quick reference and common mistakes
  • references/memory-systems.md: tiered memory
  • references/context-engineering.md: context management
  • references/agent-protocols.md: agent protocols

Good fit for

  • Your agent loses its instructions during a long session
  • You want verification rules before every delivery

Not for

    Tags

    • agents
    • memory
    • context
    • reasoning
    • verification

    About

    You say

    “Write the guidelines for my coding agent: test every change and keep a log of decisions.”

    Card for the “Reasoning, memory and context standards for agents” skill

    Skill published by oakoss 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 frame the behavior, memory and context of an autonomous coding agent
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.3 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/agent-protocols.md1.9 KB
    • references/cognitive-architecture.md2.5 KB
    • references/context-engineering.md2.1 KB
    • references/memory-systems.md2.3 KB
    • SKILL.md6.1 KB

    Origin and licence

    Listed unmodified

    Author
    oakoss
    Source
    github.com/oakoss/agent-skills/tree/85e3a3919d9e0ec7f7302a5143ec4b3e66f5f6ad/skills/agent-standards
    Licence
    MIT

    Notice

    « agent-standards » (oakoss, 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.