telegram

telegram is a skill for Claude Code, Codex from AIOSAI/AIPass. It costs 17 tokens per session (4,430 once invoked), scanned B, original, MIT.

A bridge that sends Telegram messages to Claude sessions running inside tmux, a terminal tool that keeps sessions alive. It can also send replies and session-control commands back through Telegram.

In plain words
What is it for?
Sending prompts to branch-specific sessions, receiving replies, streaming progress, and starting, stopping, locking, or suspending sessions.
Why use it?
It lets someone communicate with terminal-based agents from Telegram and keep messages from Telegram and the terminal in one conversation.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aiosai/aipass/telegram
Any agent
npx skills add AIOSAI/AIPass --skill telegram
Clone the repo
git clone --depth 1 https://github.com/AIOSAI/AIPass

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for telegram

README.md
[![agentmods](https://agentmods.dev/badge/skills/aiosai/aipass/telegram.svg)](https://agentmods.dev/skills/aiosai/aipass/telegram)
Your own site
<a href="https://agentmods.dev/skills/aiosai/aipass/telegram"><img src="https://agentmods.dev/badge/skills/aiosai/aipass/telegram.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,430 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.04430
Opus 5 $0.00009 $0.02215
Sonnet 5 $0.00003 $0.00886
Haiku 4.5 $0.00002 $0.00443

Measured 5d ago against content hash 99ab8f1c12f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

telegram scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 53 executable files (__init__.py, apps/__init__.py, apps/handlers/__init__.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

2. A matching provider bridge entry in `~/.claude/settings.json`
src/aipass/skills/lib/telegram/SKILL.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Bridge

Multi-bot personal-assistant bridge: long-polling listener routes user Telegram messages into Claude tmux sessions. The base reply flow is Claude's Stop hook writing a pending file, which the bot picks up and sends back to Telegram; bots opting into streaming (below) also live-edit a "Processing..." placeholder while the reply is still being generated. A control-center bot exposes /start, /kill, /lock, /suspend to wake, kill, and lock or sleep terminal sessions by branch, and a separate hook mirrors terminal-typed messages into the same TG chat so the conversation reads as one continuous thread regardless of which door you type in.

Architecture

  • BaseBot — polling loop, tmux injection, heartbeat, lock management, control verbs, streaming, offline backoff
  • BranchPlugin — per-branch overrides (message prefix, response prefix, session startup)
  • ResponseRouter — CWD-safe pending-file routing for multi-bot
  • TelegramStandards — shared /start, /help, /new, /status command handlers
  • BotFactory — bot create/delete lifecycle (8-step)
  • BotRegistry — fcntl-locked JSON registry CRUD
  • BotOperations — start/stop/status ops
  • BotFatherClient — optional Telethon BotFather automation
  • Config — bot configuration via @api secrets store
  • FileHandler — download, classify, and prompt file uploads
  • LogStreamer — daemon thread tailing logs to Telegram
  • Notifier — standalone push notification sender
  • TmuxManager — tmux session helpers (not the control verbs — see below)
  • UserMessageRelay — UserPromptSubmit hook that mirrors terminal-typed messages into the branch's TG chat

Usage

drone @skills run telegram start <bot_id>
drone @skills run telegram stop <bot_id>
drone @skills run telegram status [bot_id]
drone @skills run telegram create <bot_id> --token <token>
drone @skills run telegram delete <bot_id>
drone @skills run telegram notify "message"

Control verbs (DPLAN-0270 P1)

One bot doubles as a control center: _is_control_bot() is true when branch_name is None (a bare base bot) or "aipass" (the deployed control-center config — same bot_id="base" process, no separate bot). Only that bot handles these commands; branch bots fall through to the normal command set.

Read the full file on GitHub · 168 lines

Files

What ships with it

56 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 168 lines · 17 tokens per session scan B 99ab8f1c12f8

Subscribe to this mod's changes

telegram is a skill published in the GitHub repository AIOSAI/AIPass (273 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 4,430 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.