telegram-assistant

telegram-assistant is a skill for Claude Code, Codex from dudu1111685/hermes_mcps. It costs 112 tokens per session (1,322 once invoked), scanned A, original, MIT.

A set of tools for operating the owner's personal Telegram account, including reading chats, searching messages, and handling media.

In plain words
What is it for?
Use it to triage unread chats, read conversations and transcribed voice notes, send or reply to messages, react, edit, search, and manage media.
Why use it?
It brings common Telegram tasks into the coding assistant while keeping messages tied to the correct chats and accounts.

Skill for Claude CodeCodex

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

Good fit Use it to triage unread chats, read conversations and transcribed voice notes, send or reply to messages, react, edit, search, and manage media.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dudu1111685/hermes_mcps/telegram-assistant
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 dudu1111685/hermes_mcps --skill telegram-assistant
Clone the repo
git clone --depth 1 https://github.com/dudu1111685/hermes_mcps

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-assistant

README.md
[![agentmods](https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/telegram-assistant/github.svg)](https://agentmods.dev/skills/dudu1111685/hermes_mcps/telegram-assistant)
Your own site
<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/telegram-assistant"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/telegram-assistant/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-assistant

Your own site · 80×15
<a href="https://agentmods.dev/skills/dudu1111685/hermes_mcps/telegram-assistant"><img src="https://agentmods.dev/badge/skills/dudu1111685/hermes_mcps/telegram-assistant.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,322 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 $0.00112 $0.01322
Opus 5 $0.00056 $0.00661
Sonnet 5 $0.00022 $0.00264
Haiku 4.5 $0.00011 $0.00132

Measured 8d ago against content hash 5e307d366064, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

telegram-assistant 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 8d 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-assistant/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Assistant (hermes_mcps)

You control the owner's personal Telegram account via the telegram MCP server (MTProto user session, not a bot). Everything you send appears as if the owner sent it — sound human and be careful with anything outgoing. Telegram is far more automation-tolerant than WhatsApp (no ban paranoia), but rate limits exist: if a tool answers Telegram rate limit: wait Ns, do other work and retry after that time — never hammer.

Identifiers — different from WhatsApp

  • Chats: numeric ids (channels/supergroups use a -100… form), or @username, or +phone (contacts only), or me = the owner's Saved Messages. Always prefer the exact id/username that tg_list_chats / tg_find_chat returned.
  • Messages: ids are per-chat integers, shown as #123 in tg_get_chat_context. A message id from one chat means nothing in another.

Tool selection at a glance

Intent Tool Not
"What's new on Telegram?" tg_inbox tg_list_chats + per-chat reads
"Read what X wrote" tg_find_chattg_get_chat_context guessing chat ids
Answer someone tg_send_text with replyTo in groups/channels bare sends in busy groups (nobody knows what you answer)
Quick acknowledgement tg_react (👍 ❤️ …) sending "ok" messages for everything
Fix a typo in something you sent tg_edit_message sending a correction message
"Where did we talk about X?" tg_search_messages (global without chat) reading whole histories
Look at an image someone sent tg_get_media with the id from context guessing from the caption
Transcribe one voice note tg_transcribe_message — (context transcribes automatically)
Send a local file tg_send_file

Core loop: read → answer → act

  1. Triage: tg_inbox shows unread chats with recent messages. Muted chats are excluded by default — that's usually what the owner wants.
  2. Resolve names: tg_find_chat maps "X" to an id/username (recent chats
    • address-book contacts, ranked). Never ask the owner for an id a name lookup can find.
  3. Read: tg_get_chat_context renders the conversation — sender names, #id markers, ↳#id reply links, voice notes transcribed inline (when SONIOX_API_KEY is configured), media summarized with retrievable ids. Small limit (15–30) first; paginate back with beforeId only when needed.
  4. Answer: tg_send_text. In groups/channels pass replyTo so the answer is anchored. Basic markdown (bold, code) renders.
  5. Act & report: do what the message requires, then tell the owner what was done on their behalf.

Read the full file on GitHub · 97 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. 8d ago First seen · 97 lines · 112 tokens per session scan A 5e307d366064

Subscribe to this mod's changes

telegram-assistant is a skill published in the GitHub repository dudu1111685/hermes_mcps (5 stars, last pushed 4d ago), licensed MIT. It adds 112 tokens to every session and 1,322 once invoked, about $0.0006 per session on Opus 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.