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.
npx skills add Fayzullo637/mytelegrammini1-mcp --skill telegram-mcpgit clone --depth 1 https://github.com/Fayzullo637/mytelegrammini1-mcpWrote 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.
[](https://agentmods.dev/skills/fayzullo637/mytelegrammini1-mcp/telegram-mcp)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
-
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").
-
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.
-
Context is King:
- ALWAYS use
get_chat_historybefore sending a new message to understand the exact context of the conversation. - ALWAYS use
get_profile_infowhen interacting with a new user to find conversation starters in their bio.
- ALWAYS use
Usage Workflow
- Use
search_chatswith{ query: "<username_or_title>" }to find and open the chat. - Use
get_profile_infowith{}to read profile context. - Use
get_chat_historywith{ limit: 20 }(orget_recent_chatswith{ limit: 10 }) to see recent messages. - Think carefully about your next response based on the "Human Formatting" rules.
- Use
send_messagewith{ text: "<message>" }(orsend_filewith{ filePath, caption?, chat? },send_photowith{ filePath, caption?, chat? }, orreply_to_messagewith{ messageTextOrId, replyText, chat? }) to reply. - (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"
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.
- 2mo ago First seen · 52 lines · 18 tokens per session scan A eafb5fd27a54
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.
telegram-interaction compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| telegram-interactionFayzullo637/mytelegrammini1-mcp | Skill | 0 | 1mo ago | MIT | A | 18 | Claude Code, Codex |
| interactive-loginyc-software/qm | Skill | 16k | today | MIT | A | 46 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |
| azure-messaging-webpubsub-javamicrosoft/skills | Skill | 3.2k | today | MIT | A | 43 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |
| open-design-browsercompozy/compozy | Skill | 2.9k | today | MIT | A | 56 | Claude Code, Codex |
| southwestborski/travel-hacking-toolkit | Skill | 906 | yesterday | MIT | A | 40 | Claude Code |