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 agentmods add instructions/vovavindar/telegram-mcp/agents-mdgit clone --depth 1 https://github.com/VovaVindar/telegram-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/instructions/vovavindar/telegram-mcp/agents-md)<a href="https://agentmods.dev/instructions/vovavindar/telegram-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/vovavindar/telegram-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01431 | $0.01431 |
| Opus 5 | $0.00715 | $0.00715 |
| Sonnet 5 | $0.00286 | $0.00286 |
| Haiku 4.5 | $0.00143 | $0.00143 |
Grade A, and why
telegram-mcp AGENTS.md 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 5d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file describes how AI agents can use telegram-mcp to organize and manage a user's Telegram account. Any AI model or agent framework that discovers this file can use these workflows.
Server Overview
telegram-mcp is an MCP (Model Context Protocol) server that provides 19 tools for reading, writing, and organizing Telegram chats, channels, and groups. It connects via Telethon (user account, not bot API), so it has full access to everything the user can see.
Agent Workflows
1. Auto-organize channels into folders
The primary workflow. Analyze all channel subscriptions and create themed folders.
Steps:
- Call
list_dialogs(filter="channels", limit=200)to get all channels with IDs, names, and unread counts. - For each channel, call
get_chat_info(chat_id)andget_messages(chat_id, limit=5)in parallel to get metadata and sample recent content. - Analyze channel names, descriptions, and message content to infer topics.
- Group channels into 5-10 thematic folders (e.g., "Coding", "Design", "News", "Personal").
- Present the plan to the user as a table before making changes.
- On confirmation, call
create_folder(name, chat_ids)for each folder sequentially (parallel calls will cause ID collisions).
Constraints:
- Folder names are limited to 12 characters.
- Telegram allows up to 10 custom folders.
- Create folders one at a time, not in parallel.
2. Identify cleanup candidates
Find channels worth unsubscribing from or archiving.
Steps:
- Call
list_dialogs(filter="channels", limit=200). - Flag channels where
last_message_dateis older than 6 months (inactive/dead). - Flag channels with very high
unread_count(500+) as potentially abandoned by the user. - For flagged channels, call
get_messages(chat_id, limit=3)to check if the channel announced it's shutting down or migrating. - Present results as a table with channel name, last active date, unread count, and recommendation (archive, mute, or unsubscribe).
- On confirmation, call
archive_chatormute_chatas requested. Note: there is noleave_chattool, so the user must unsubscribe manually.
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.
- 5d ago First seen · 114 lines · 1,431 tokens per session scan A 0db975159b44
telegram-mcp AGENTS.md is an instructions file published in the GitHub repository VovaVindar/telegram-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,431 tokens to every session, about $0.0072 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 instructions, from other repositories
ironcurtain CLAUDE.md
Claude Code instructions for provos/ironcurtain, covering claude.md, general workflow, git & worktrees, git workflow and platform considerations.
run402 AGENTS.md
AGENTS.md instructions for kychee-com/run402, covering agents.md, what this is, git workflow — worktrees, never branches, never stash, build & test commands and run all unit tests.
TimeTree-MCP CLAUDE.md
Claude Code instructions for ehs208/TimeTree-MCP, covering timetree mcp project guide, project purpose, current capabilities, architecture map and api behavior notes.
Task Execution Workflow
Rules for selecting, implementing, testing, and closing work in the Sir Thaddeus repository without requiring an external task tracker.
Harness Iteration Framework
Reusable workflow for running the full Sir Thaddeus E2E harness, breaking failures into stages, and iterating on product fixes with fast feedback.
abfall-mcp-server AGENTS.md
AGENTS.md instructions for AlpayC/abfall-mcp-server, covering notes for coding agents, setup, commands, the one principle and traps.