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/zai-one/telegram-ads-mcp/agents-mdgit clone --depth 1 https://github.com/zai-one/telegram-ads-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/zai-one/telegram-ads-mcp/agents-md)<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>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 | $0.02656 | $0.02656 |
| Opus 5 | $0.01328 | $0.01328 |
| Sonnet 5 | $0.00531 | $0.00531 |
| Haiku 4.5 | $0.00266 | $0.00266 |
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 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.
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.
- today Changed · +34 lines · +1,350 tokens per session scan A → C 39f46bb108a4
- 4d ago First seen · 69 lines · 1,306 tokens per session scan A d7920aa2115b
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.
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.
SimpleTgChatMcp CLAUDE.md
Claude Code instructions for dotneteeer/SimpleTgChatMcp, covering claude.md, what this is, architecture, conventions and adding a new bot api method.
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).
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.
agentic-ads CLAUDE.md
Instructions for nicofains1/agentic-ads, covering agentic ads, what is this?, ⚠️ behavioral specification — source of truth, vision and architecture overview.
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.