Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

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.

Repeatable agent loops: discover, audit and run v1.0.0

Use this resource to design, audit, run or publish a bounded, repeatable agent loop

New

  • 584 downloads
  • 135 likes
  • 191 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install repeatable-agent-loops

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 analyzes code and coding threads to find recurring tasks, looks for a published loop that fits, interviews you about the goal, flags weak checks or overly broad authority, then runs the loop with an evidence receipt. Each loop has defined terminal states.

Mostly picked by

Updated November 2, 2026

Card for the “Repeatable agent loops: discover, audit and run” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • references/discover.md: finding repeatable work in code and threads
  • references/audit.md and run.md: auditing a loop and running it with a receipt
  • references/publish.md and debrief.md: run debriefs and publication to Loop Library

Good fit for

  • You repeat the same coding task often and want to automate it under control
  • You want to review an agent loop before giving it permissions

Not for

    Tags

    • agents
    • loops
    • automation
    • audit
    • Loop Library

    About

    You say

    “Analyze this repository's work threads and tell me which recurring tasks deserve a bounded loop.”

    Card for the “Repeatable agent loops: discover, audit and run” skill

    Skill published by forward-future 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 design, audit, run or publish a bounded, repeatable agent loop
    3. Review and adjust the result

    Content preview

    Files

    • agents/openai.yaml0.2 KB
    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.4 KB
    • references/audit.md2.7 KB
    • references/debrief.md1.8 KB
    • references/discover.md3.9 KB
    • references/publish.md3.2 KB
    • references/run.md3.4 KB
    • SKILL.md15.4 KB

    Origin and licence

    Listed unmodified

    Author
    forward-future
    Source
    github.com/forward-future/loopy/tree/75966cbd572a4185064971c9fe5e9c52e8f8456d/skills/loopy
    Licence
    MIT

    Notice

    « loopy » (forward-future, 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.