agent-channeltalk
Interact with Channel Talk using extracted desktop app or browser credentials - read chats,…
Interact with Telegram using bot tokens - send messages, read chats, manage reactions
$ npx -y skills add agent-messenger/agent-messenger --skill agent-telegrambot --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/agent-telegrambotContext preview
The summary Claude sees to decide when to auto-load this skill.
Interact with Telegram using bot tokens - send messages, read chats, manage reactions
name: agent-telegrambot
description: Interact with Telegram using bot tokens - send messages, read chats, manage reactions
version: 2.38.0
allowed-tools: Bash(agent-telegrambot:*)
metadata:
openclaw:
requires:
bins:
- agent-telegrambot
install:
- kind: node
package: agent-messenger
bins: [agent-telegrambot]A TypeScript CLI tool that enables AI agents and humans to interact with Telegram using **Bot API tokens** (the kind issued by [@BotFather](https://t.me/BotFather)). Unlike `agent-telegram` which authenticates as a real user account via TDLib, `agent-telegrambot` uses Telegram's HTTP Bot API — designed for server-side and CI/CD integrations.
Before diving in, a few things about Telegram Bot integration:
# Set your bot token (validates against Telegram) agent-telegrambot auth set 123456789:ABC-DEF1234... # Verify authentication agent-telegrambot whoami # Send a message agent-telegrambot message send @username "Hello from bot!" # Get chat info agent-telegrambot chat info @somegroup
`agent-telegrambot` uses Bot API tokens which you create by chatting with [@BotFather](https://t.me/BotFather):
# Set bot token (validates against Telegram API before saving) agent-telegrambot auth set 123456789:ABC-DEF1234... # Set with a custom bot identifier agent-telegrambot auth set <token> --bot deploy # Check auth status agent-telegrambot auth status # Clear stored credentials agent-telegrambot auth clear
# List all configured bots agent-telegrambot auth list # Switch active bot agent-telegrambot auth use <bot-id> # Remove a bot agent-telegrambot auth remove <bot-id> # Use a specific bot for a single command agent-telegrambot --bot deploy message send @channel "Deploy succeeded"
The agent maintains a `~/.config/agent-messenger/MEMORY.md` file as persistent memory across sessions. This is agent-managed — the CLI does not read or write this file. Use the `Read` and `Write` tools to manage your memory file.
Never store bot tokens, credentials, or any sensitive data. Never store full message content (just IDs and chat context).
# Agent Messenger Memory ## Telegram Bots - `deploy` — Deploy Bot (active) - `alert` — Alert Bot ## Chats (Deploy Bot) - `-1001234567890` — #ci-alerts (channel) - `-1009876543210` — Engineering (supergroup) - `123456789` — Alice (DM) ## Aliases - "alerts" → `-1001234567890`
# Set bot token agent-telegrambot auth set <token> agent-telegrambot auth set <token> --bot deploy # Check auth status agent-telegrambot auth status agent-telegrambot auth status --bot deploy # Clear all credentials agent-telegrambot auth clear # List stored bots agent-telegrambot auth list # Switch active bot agent-telegrambot auth use <bot-id> # Remove a stored bot agent-telegrambot auth remove <bot-id>
# Show current authenticated bot agent-telegrambot whoami agent-telegrambot whoami --pretty agent-telegrambot whoami --bot <bot-id>
# Send a text message agent-telegrambot message send <chat> <text> agent-telegrambot message send @username "Hello" agent-telegrambot message send -1001234567890 "Hello channel" # Send with formatting agent-telegrambot message send @username "<b>Bold</b> message" --parse-mode HTML # Reply to a specific message agent-telegrambot message send @username "Reply text" --reply-to 12345 # Send silently (no notification) agent-telegrambot message send @username "Silent message" --silent # Send to a forum topic agent-telegrambot message send <chat> "Topic message" --thread-id 5 # Edit a message (bot's own messages only) agent-telegrambot message edit <chat> <message-id> <new-text> # Delete a message agent-telegrambot message delete <chat> <message-id> --force # Forward a message between chats agent-telegrambot message forward <to-chat> <from-chat> <message-id> # Upload a document agent-telegrambot message upload <chat> ./report.pdf --caption "Daily report"
# Get chat info agent-telegrambot chat info <chat> agent-telegrambot chat info @somegroup agent-telegrambot chat info -1001234567890 # Get chat member info agent-telegrambot chat member <chat> <user-id>
# Set a reaction (replaces any existing reaction by the bot) agent-telegrambot reaction set <chat> <message-id> 👍 agent-telegrambot reaction set <chat> <message-id> 👍 --big # Clear all reactions agent-telegrambot reaction clear <chat> <message-id>
All commands output JSON by default for AI consumption:
Your agent messages as you — not as a bot One CLI for Slack, Discord, Teams, Webex, Telegram, WhatsApp, LINE, WeChat, iMessage, Instagram, KakaoTalk, and Channel Talk.
Repo: agent-messenger/agent-messenger
Interact with Channel Talk using extracted desktop app or browser credentials - read chats,…
Interact with Channel Talk workspaces using API credentials - send messages, read chats,…
Interact with Discord servers - send messages, read channels, manage reactions
Interact with Discord servers using bot tokens - send messages, read channels, manage…
Interact with iMessage on a Mac via the imsg tool - send messages, read chats, watch for new…
Interact with Instagram DMs - send messages, read conversations, manage accounts