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.

Agent discipline in shared channels v1.0.0

Use this resource to let an agent speak in channels or direct messages where outsiders can read everything

New

  • 506 downloads
  • 193 likes
  • 199 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install shared-channel-agent-discipline

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 written policy: identify the audience, reply only when addressed, filter internal context and send sensitive content as drafts for approval. You get an agent that helps customers without noise or leaks.

Mostly picked by

Updated November 2, 2026

Card for the “Agent discipline in shared channels” skill

Details

Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: destination audience, participation and delivery boundaries
  • references/strict-prompt.template.md and references/channel-policy.example.yaml: strict prompt and per-channel policy

Good fit for

  • An agent answers customers or suppliers in a shared channel
  • An agent receives private messages from strangers or attachments

Not for

    Tags

    • channels
    • agent
    • policy
    • privacy
    • drafts

    About

    You say

    “Set up the supplier channel agent: reply only when mentioned, no internal details, drafts for any price.”

    Card for the “Agent discipline in shared channels” skill

    Skill published by affaan-m 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 let an agent speak in channels or direct messages where outsiders can read everything
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/channel-policy.example.yaml1.7 KB
    • references/strict-prompt.template.md1.7 KB
    • SKILL.md8.8 KB

    Origin and licence

    Listed unmodified

    Author
    affaan-m
    Source
    github.com/affaan-m/ecc/tree/25278e7d7b6cf6e6a4e7a6c8e10f14ff22f0eb5b/skills/counterparty-channel-discipline
    Licence
    MIT

    Notice

    « counterparty-channel-discipline » (affaan-m, 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.