Skip to content
Back to skills

Agent Messaging Protocol

ASecurity

Use when forwarding or relaying information between parties, routing an owner answer, carrying a decision or request through an intermediary, summarizing another author's message, or adding interpretation to someone else's words.

  • 2 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
documentation

Security analysis

A100/100

Scanned November 7, 2026

npx -y skills add thrum-team/thrum-pro --skill agent-messaging-protocol --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Messaging Protocol?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agent Messaging Protocol
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/thrum-team-agent-messaging-protocol/badge)](https://www.skillsdirectory.com/skills/thrum-team-agent-messaging-protocol)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agent-messaging-protocol
description: "Use when forwarding or relaying information between parties, routing an owner answer, carrying a decision or request through an intermediary, summarizing another author's message, or adding interpretation to someone else's words."
---

# Agent Messaging Protocol for Forwarding and Relaying

- Communicate directly with the intended party whenever possible.
- Treat the original message as the authoritative source.
- Forward a pointer to the original message instead of retyping or paraphrasing its body.
- Include the original author, original message ID, intended recipient, and requested action.
- Attach `message:<original-message-id>` as a message reference when supported.
- Read the original message before acting: `thrum message get <message-id> --json`.
- Reply against the original message: `thrum reply <message-id> ...`.
- Do not route the response back through the intermediary.
- Add commentary or interpretation only when requested or necessary.
- Label added reasoning as `INTERPRETATION - @agent`.
- Never present an interpretation, summary, or recommendation as words or authority from the original author.
- Label a requested summary as `SUMMARY - @agent` and retain the original message ID.
- Preserve the original scope, urgency, constraints, and requested action.
- Do not introduce new requirements, decisions, risks, or authorization while routing.
- Ask the original author directly when clarification is required.
- Continue referencing the original message rather than an intermediary's summary.
- Identify corrections by the exact message they supersede.
- Distinguish delivery, acknowledgement, execution, and verification.
- Do not reply to a message that only acknowledges or thanks; mark it read.
- Preserve the original thread audience when replying unless a deliberately narrower audience is required.

## Routing Envelope

```text
ROUTE POINTER
From: @original-author
Message: msg_...
Action: Read and reply to the original message.
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.