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 dudu1111685/hermes_mcps --skill telegram-assistantgit clone --depth 1 https://github.com/dudu1111685/hermes_mcpsWrote 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/dudu1111685/hermes_mcps/telegram-assistant)<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.
<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>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 | $0.00112 | $0.01322 |
| Opus 5 | $0.00056 | $0.00661 |
| Sonnet 5 | $0.00022 | $0.00264 |
| Haiku 4.5 | $0.00011 | $0.00132 |
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.
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), orme= the owner's Saved Messages. Always prefer the exact id/username thattg_list_chats/tg_find_chatreturned. - Messages: ids are per-chat integers, shown as
#123intg_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_chat → tg_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
- Triage:
tg_inboxshows unread chats with recent messages. Muted chats are excluded by default — that's usually what the owner wants. - Resolve names:
tg_find_chatmaps "X" to an id/username (recent chats- address-book contacts, ranked). Never ask the owner for an id a name lookup can find.
- Read:
tg_get_chat_contextrenders the conversation — sender names,#idmarkers,↳#idreply links, voice notes transcribed inline (whenSONIOX_API_KEYis configured), media summarized with retrievable ids. Smalllimit(15–30) first; paginate back withbeforeIdonly when needed. - Answer:
tg_send_text. In groups/channels passreplyToso the answer is anchored. Basic markdown (bold,code) renders. - Act & report: do what the message requires, then tell the owner what was done on their behalf.
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.
- 8d ago First seen · 97 lines · 112 tokens per session scan A 5e307d366064
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.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.