A standardized communication protocol for AI agent teams to send structured status updates and notifications via Telegram.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-telegram
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-telegram using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Telegram Communication?
This skill establishes a robust communication framework for autonomous AI agent teams. By integrating with Telegram, it allows various agent roles—including architects, developers, and product managers—to provide real-time updates directly to the user. Using Openclaw Skills, this protocol ensures that every team member follows a consistent message format, making multi-agent collaboration transparent and easy to monitor.
By defining specific account mappings and emoji identifiers, the Agent Telegram skill transforms raw agent logs into a human-readable feed. This is essential for managing complex projects where multiple agents operate simultaneously, as it provides a clear audit trail of task progression, completions, and blockers.
Agent Telegram Communication Use Cases
- Real-time status updates from AI agents during long-running tasks.
- Automated reporting of sub-task completions and generated file outputs.
- Instant notification of blockers or errors requiring manual user intervention.
- Centralized coordination for multi-agent workflows involving backend, frontend, and QA roles.
How Agent Telegram Communication Works
- The AI agent identifies its specific role and associated accountId from the account mapping table.
- Upon reaching a defined reporting milestone (task start, sub-task completion, or error), the agent triggers the message tool.
- The tool formats a message payload specifying the channel as telegram and the predefined target user ID.
- The agent prefixes the content with its unique role-based emoji for visual distinction.
- The Openclaw infrastructure processes the request and dispatches the notification to the user's Telegram account.
Agent Telegram Communication Setup
To implement this communication standard within your Openclaw Skills environment, configure your global settings first:
# Open your main configuration file
vi ~/.openclaw/openclaw.json
Ensure that the channels.telegram.accounts section contains the necessary credentials for each agent role (e.g., architect, backend, sproduct). The skill definition itself should be placed in your workspace directory:
# Ensure the skill file is correctly located
ls ~/.openclaw/workspace/skills/agent-telegram/SKILL.md
Agent Telegram Communication Data Schema & Taxonomy
The skill utilizes a strict JSON schema for the message tool to ensure delivery.
| Parameter | Type | Description |
|---|---|---|
action |
String | Must be set to "send" |
channel |
String | Must be set to "telegram" |
accountId |
String | The specific agent ID (e.g., backend, architect, sproduct) |
target |
String | The fixed Telegram user ID (e.g., 5440561025) |
message |
String | The content, formatted as " |
Standard reporting triggers include task_start, subtask_complete, error_encountered, and task_finished.
Agent Telegram Communication Advanced Features
- Multi-Agent Identity Mapping: Maps specific roles like 'sproduct' to product managers and 'backend' to developers for clear attribution.
- Path-Aware Reporting: Encourages agents to include absolute or relative file paths in completion messages for immediate file access.
- Standardized Error Handling: Provides a specific template for reporting problems and suggesting solutions or requesting user decisions.
- Role-Specific Emojis: Enhances readability in high-traffic Telegram channels through visual role categorization.
SKILL.md
Loading
Related Openclaw Skills
Async Web Search
A high-performance parallel web search tool using Python's asyncio to retrieve data across multiple queries simultaneously.
Codex Orchestrator
A methodical end-to-end software delivery orchestrator for Codex CLI that manages project lifecycles through strict quality gates and spec-driven development.
ClawCost
A financial tracking utility for AI agents that monitors token costs, budget limits, and model-specific expenditures.
FreeRide
FreeRide automates the selection and configuration of free AI models from OpenRouter for the OpenClaw agent ecosystem.
BugReaper
BugReaper is a senior offensive security agent designed to identify real, exploitable vulnerabilities and generate professional reports for bug bounty platforms.
Lance: Web3 Vulnerability Hunter
Lance is a specialized Web3 security agent designed for high-signal vulnerability discovery and reporting in smart contracts and DeFi protocols.
Featured*
