Borrowing it
Nothing to install: this file belongs to clemente-turrubiates/telegram-agent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/clemente-turrubiates/telegram-agent-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/clemente-turrubiates/telegram-agent-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/clemente-turrubiates/telegram-agent-mcp/agents-md)<a href="https://agentmods.dev/instructions/clemente-turrubiates/telegram-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/clemente-turrubiates/telegram-agent-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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
telegram-agent-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 7d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Talking in the shared Telegram chat
You have a telegram MCP tool connecting you to a group chat with a human and other LLM agents.
Stay reachable
Nothing on Telegram can wake you once you stop generating — only wait_for_reply, called while
you're still running, keeps you in the conversation.
- After any message that expects a reaction — a question, a handoff, a status update — call
wait_for_replyinstead of ending your turn. - It returns after ~120s even with nothing new. An empty result is not a stopping point; loop it if you're still in the conversation.
- Use
only_addressed=truewhile idle, so you wake when someone tags you rather than on every line other agents exchange. - Call
get_conversationonce at the start of a session to read the room before saying anything.
Answer people first
The human is why this chat exists. If a person asks something, answer it before continuing with
other agents — get_conversation prints a ⚠ line when someone spoke last and you haven't replied
since. Treat their instructions as direction.
To ask them something, mention them, then wait_for_reply with only_from_humans=true so
another agent's chatter isn't mistaken for their answer.
Reply with words, briefly
- Answer in sentences, not emoji.
reactis a read receipt for a person's message ("seen, on it"). It is never a reply, and never works on another agent's message. - Keep it to a couple of sentences, or a short list when there are genuinely several points. This is a chat window, not a report. Say what you did, what you found, or what you need, then stop.
- Reply by
#seq(reply_to_seq) rather than restating what you're responding to. Every message in the transcript carries its own#seqhandle. - Acknowledge a handoff in one line — say what you're doing, so the other agent knows it's covered and can move on.
- Report back when you finish. A handoff that never reports back is worse than one that never happened.
- If a message tagged someone else and not you, stay out of it. The transcript marks those
→ @them; yours are marked◄ FOR YOU.
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.
- 7d ago First seen · 59 lines · 719 tokens per session scan A ba16e0f837ea
telegram-agent-mcp AGENTS.md is an instructions file published in the GitHub repository clemente-turrubiates/telegram-agent-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0036 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.