How do I install the Comms skill?

Run npx skillmds@latest add grandamenium/comms-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Comms safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Comms?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Comms free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

grandamenium (@grandamenium) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Comms by grandamenium — Agent Skill

Name: Comms
Author: grandamenium

Comms

A message has just arrived in your session from the fast-checker daemon — you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.

grandamenium 822d4f2 2.1 KB Updated Sep 17, 2026

File contents

Handling Incoming Messages

Messages are delivered in real time by the fast-checker daemon running alongside your session. You will see them appear in your input as formatted blocks.

Message Format

=== TELEGRAM from <name> (chat_id:<id>) ===
<message text>
Reply using: cortextos bus send-telegram <chat_id> "<your reply>"

=== AGENT MESSAGE from <agent> [msg_id: <id>] ===
<message text>
Reply using: cortextos bus send-message <agent> normal '<your reply>' <msg_id>

What To Do

Read every message block in the injected content
For each message, take action or respond using the Reply using: command shown in the header
For agent messages, always include the msg_id as the reply_to argument so conversations thread correctly
The fast-checker handles temp file cleanup automatically

Priority

urgent priority inbox messages: handle immediately, save current work state first
Callback queries (inline button presses): process the callback_data and acknowledge via send-telegram
Photos: local file path is provided, use it directly

Waiting for a Response

If you send a Telegram message that asks a question and you need the answer before continuing your work, you MUST end your current response entirely (stop all tool execution, produce no more output). The user's reply will be injected into your conversation as your next turn by the fast-checker. If you keep executing tools after sending the question, the reply gets queued by Claude Code and you will never see it until your turn ends. End your turn, and the reply arrives.

Done

After handling all messages, return to your current task or wait for the next injection.

---name: comms-2description: A message has just arrived in your session from the fast-checker daemon — you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.---# Handling Incoming MessagesMessages are delivered in real time by the fast-checker daemon running alongside your session. You will see them appear in your input as formatted blocks.## Message Format```=== TELEGRAM from <name> (chat_id:<id>) ===<message text>Reply using: cortextos bus send-telegram <chat_id> "<your reply>"=== AGENT MESSAGE from <agent> [msg_id: <id>] ===<message text>Reply using: cortextos bus send-message <agent> normal '<your reply>' <msg_id>```## What To Do1. Read every message block in the injected content2. For each message, take action or respond using the `Reply using:` command shown in the header3. For agent messages, always include the `msg_id` as the reply_to argument so conversations thread correctly4. The fast-checker handles temp file cleanup automatically## Priority- `urgent` priority inbox messages: handle immediately, save current work state first- Callback queries (inline button presses): process the callback_data and acknowledge via `send-telegram`- Photos: local file path is provided, use it directly## Waiting for a ResponseIf you send a Telegram message that asks a question and you need the answer before continuing your work, you MUST end your current response entirely (stop all tool execution, produce no more output). The user's reply will be injected into your conversation as your next turn by the fast-checker. If you keep executing tools after sending the question, the reply gets queued by Claude Code and you will never see it until your turn ends. End your turn, and the reply arrives.## DoneAfter handling all messages, return to your current task or wait for the next injection.

Frequently asked questions