telegram-ads-mcp AGENTS.md

telegram-ads-mcp AGENTS.md is an instructions file for Codex, OpenCode from zai-one/telegram-ads-mcp. It costs 2,656 tokens per session, scanned C, original, no licence file.

Repository instructions for working on zai-one/telegram-ads-mcp, including its agent playbook, currency handling, authentication, write-safety gate, and list fields. Telegram Ads is Telegram's advertising platform, and MCP is a way for assistants to use external tools.

In plain words
What is it for?
Use it when working in the telegram-ads-mcp project, especially for authentication, currency, list-field handling, and protected write operations.
Why use it?
It gives coding agents the project-specific rules they need before changing or querying this repository.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/zai-one/telegram-ads-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/zai-one/telegram-ads-mcp

Made for: Codex, OpenCode.

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-ads-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zai-one/telegram-ads-mcp/agents-md.svg)](https://agentmods.dev/instructions/zai-one/telegram-ads-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zai-one/telegram-ads-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/zai-one/telegram-ads-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,656 This file is loaded in full into every session.
When invoked 2,656 The same file — it is already loaded in full.
Security scan C 1 finding. Scan, not verified.
Origin unknown 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 $0.02656 $0.02656
Opus 5 $0.01328 $0.01328
Sonnet 5 $0.00531 $0.00531
Haiku 4.5 $0.00266 $0.00266

Measured today against content hash 39f46bb108a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

telegram-ads-mcp AGENTS.md scanned grade C with 1 finding 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 today.

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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

Cookies only in gitignored `.env` (`STEL_TOKEN`, `STEL_SSID`). Never paste into chat, Issues, MCP `env`, or tool args. First call: `check_session`. Dead session: **offer** the INSTALL.md DevTools steps (do not ask them t
AGENTS.md · 103 lines

The source is not reproduced here

A licence we could not identify

The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.

Read it on GitHub

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. today Changed · +34 lines · +1,350 tokens per session scan A → C 39f46bb108a4
  2. 4d ago First seen · 69 lines · 1,306 tokens per session scan A d7920aa2115b

Subscribe to this mod's changes

telegram-ads-mcp AGENTS.md is an instructions file published in the GitHub repository zai-one/telegram-ads-mcp (1 stars, last pushed 3d ago), with no licence file. It adds 2,656 tokens to every session, about $0.0133 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

mcp-yandex-audience CLAUDE.md

Claude Code instructions for A1-x-Tech/mcp-yandex-audience, covering claude.md — mcp-yandex-audience, commands, architecture, conventions (do not break) and adding a tool.

A1-x-Tech/mcp-yandex-audience · 2,759 tokens

SimpleTgChatMcp CLAUDE.md

Claude Code instructions for dotneteeer/SimpleTgChatMcp, covering claude.md, what this is, architecture, conventions and adding a new bot api method.

dotneteeer/SimpleTgChatMcp · 1,969 tokens

yandex-direct-mcp CLAUDE.md

Claude Code instructions for nikolaymokh-dev/yandex-direct-mcp, covering claude.md, project overview, architecture, contract hierarchy and dual-channel layout (claude code + codex bundle).

nikolaymokh-dev/yandex-direct-mcp · 10,170 tokens

yandex-direct-mcp AGENTS.md

AGENTS.md instructions for iarbor04/yandex-direct-mcp, covering правила работы с этим mcp-сервером, перед первым вызовом, получение данных, изменения and деньги и единицы.

iarbor04/yandex-direct-mcp · 618 tokens

agentic-ads CLAUDE.md

Instructions for nicofains1/agentic-ads, covering agentic ads, what is this?, ⚠️ behavioral specification — source of truth, vision and architecture overview.

nicofains1/agentic-ads · 1,337 tokens

telegram-mcp AGENTS.md

AGENTS.md instructions for VovaVindar/telegram-mcp, covering agents.md, server overview, agent workflows, 1. auto-organize channels into folders and 2. identify cleanup candidates.

VovaVindar/telegram-mcp · 1,431 tokens