telegram-interaction

telegram-interaction is a skill for Claude Code, Codex from Fayzullo637/mytelegrammini1-mcp. It costs 18 tokens per session (630 once invoked), scanned A, original, MIT.

A set of guidelines for interacting with people through Telegram Web, the browser-based version of Telegram, using MCP.

In plain words
What is it for?
Use it when an agent needs to interact with humans through Telegram Web. The description does not specify particular actions such as sending messages or managing chats.
Why use it?
It helps an agent follow consistent practices when communicating with people on Telegram Web.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when an agent needs to interact with humans through Telegram Web. The description does not specify particular actions such as sending messages or managing chats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp
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.

Any agent
npx skills add Fayzullo637/mytelegrammini1-mcp --skill telegram-mcp
Clone the repo
git clone --depth 1 https://github.com/Fayzullo637/mytelegrammini1-mcp

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-interaction

README.md
[![agentmods](https://agentmods.dev/badge/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp/github.svg)](https://agentmods.dev/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp)
Your own site
<a href="https://agentmods.dev/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp"><img src="https://agentmods.dev/badge/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for telegram-interaction

Your own site · 80×15
<a href="https://agentmods.dev/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp"><img src="https://agentmods.dev/badge/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00018 $0.00630
Opus 5.5 $0.00007 $0.00252
Sonnet 5.5 $0.00004 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured 2mo ago against content hash eafb5fd27a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

telegram-interaction scanned grade A with 0 findings 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 2mo ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/telegram-mcp/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Web Interaction Skill

You have access to the Telegram MCP Server. When instructed by the USER to chat with someone on Telegram, follow these absolute rules.

Core Directives

  1. Never Sound Like an AI: Humans on Telegram can instantly detect ChatGPT-style formatting.

    • DO NOT use bullet points, numbered lists, or formal greetings ("Привет! Чем могу помочь?").
    • DO NOT write long, multi-paragraph essays.
    • DO NOT use overly complex vocabulary or overly polite phrases ("Буду рад", "С удовольствием").
  2. Format Like a Human:

    • Write in lowercase.
    • Keep sentences short (1-2 lines max).
    • Use simple punctuation (e.g., ), ..., ! instead of perfect periods).
    • Occasional typos are better than perfect, robotic grammar.
  3. Context is King:

    • ALWAYS use get_chat_history before sending a new message to understand the exact context of the conversation.
    • ALWAYS use get_profile_info when interacting with a new user to find conversation starters in their bio.

Usage Workflow

  1. Use search_chats with { query: "<username_or_title>" } to find and open the chat.
  2. Use get_profile_info with {} to read profile context.
  3. Use get_chat_history with { limit: 20 } (or get_recent_chats with { limit: 10 }) to see recent messages.
  4. Think carefully about your next response based on the "Human Formatting" rules.
  5. Use send_message with { text: "<message>" } (or send_file with { filePath, caption?, chat? }, send_photo with { filePath, caption?, chat? }, or reply_to_message with { messageTextOrId, replyText, chat? }) to reply.
  6. (Optional) If you need to wait for a reply, do NOT spam messages. Ask the USER for a strategy or use wait tools.

Example Good vs Bad Replies

Bad (AI-like): "Привет! Я с удовольствием познакомлюсь с тобой. Мой друг посоветовал мне написать. Как проходит твой день? Если у тебя есть какие-то вопросы, я буду рад ответить!"

Good (Human-like): "привет) мне тут посоветовали тебе написать. надеюсь не отвлекаю"

Read the full file on GitHub · 52 lines

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. 2mo ago First seen · 52 lines · 18 tokens per session scan A eafb5fd27a54

Subscribe to this mod's changes

telegram-interaction is a skill published in the GitHub repository Fayzullo637/mytelegrammini1-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 630 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

telegram-interaction compared with skills from other repositories

telegram-interaction next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
telegram-interactionFayzullo637/mytelegrammini1-mcpSkill01mo agoMITA18Claude Code, Codex
interactive-loginyc-software/qmSkill16ktodayMITA46Claude Code, Codex
pinchtab-mcppinchtab/pinchtabSkill11k10d agoMITA52Claude Code, Codex
azure-messaging-webpubsub-javamicrosoft/skillsSkill3.2ktodayMITA43Claude Code
cua-driverdavidondrej/skillsSkill4.3kyesterdayMITA68Claude Code, Codex
open-design-browsercompozy/compozySkill2.9ktodayMITA56Claude Code, Codex
southwestborski/travel-hacking-toolkitSkill906yesterdayMITA40Claude Code