What is operate-telegram-ads-growth-loop?

An automated operating loop for Telegram Ads, Telegram’s advertising system. It researches campaigns, checks results, and prepares decisions and reports, while requiring approval for actions that spend money or change live ads.

Researching Telegram channels and search terms, preparing ad ideas, watching approved campaigns, reviewing statistics, classifying results, and creating recommendations or approval requests.

It removes the need to track research, checks, measurements, and follow-up manually. It also keeps consequential advertising actions behind explicit approval.

operate-telegram-ads-growth-loop — Skill for Claude Code by sh0tn1k

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add sh0tn1k/telegram-ads

Claude Code

/plugin install telegram-ads

Made for: Claude Code.

Or install telegram-ads, the plugin that ships this one along with the rest of its 13 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop/github.svg)](https://agentmods.dev/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop)

Your own site

<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop"><img src="https://agentmods.dev/badge/skills/sh0tn1k/telegram-ads/operate-telegram-ads-growth-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,890 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original 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.

Model	Per session	Once invoked
Fable 5.1	$0.00028	$0.02890
Opus 5	$0.00014	$0.01445
Sonnet 5	$0.00006	$0.00578
Haiku 4.5	$0.00003	$0.00289

Measured 7d ago against content hash f2014bfa2d88, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

operate-telegram-ads-growth-loop 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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/validate_campaign_brief.py, scripts/validate_search_queries.py, scripts/validate_target_cluster.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/operate-telegram-ads-growth-loop/SKILL.md · 243 lines

How it starts

The opening of the file, as written. The whole thing — 243 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Telegram Ads Autonomous Growth Operator

Оператор полного цикла Telegram Ads

Этот skill превращает Hermes из помощника, обсуждающего каждое действие, в специализированного Telegram Ads Campaign Operator. Оператор самостоятельно:

Изучает продукт, проект и Telegram assets
Исследует поисковые запросы и каналы/боты для таргетинга
Формирует изолированные рекламные гипотезы
Проверяет готовность назначения
Готовит рекламные объявления и approval requests
После approved action регистрирует наблюдение
Периодически читает статистику
Вычисляет показатели и определяет evidence checkpoints
Классифицирует результат и готовит рекомендации
Создаёт внутренние задачи и approval drafts
Уведомляет о материальных событиях

Границы автономии

Hermes НЕ МОЖЕТ без отдельного explicit approval:

Создавать или запускать live-рекламу
Останавливать рекламу
Менять CPM, бюджет, targeting
Редактировать объявление
Публиковать материалы
Отправлять пользовательские сообщения
Выполнять deploy
Менять production DB или конфигурацию
Тратить рекламный бюджет

Маршрутизация запросов на наблюдение (CRITICAL)

Когда пользователь просит «поставить рекламу на наблюдение», «следить за кампанией», «сообщить когда останется N Stars», или «сам решай когда рекомендовать отключение» — используй ТОЛЬКО канонический путь через Telegram Ads Targeting Operator.

Канонический путь (единственно допустимый)

Найди ad_id через telegram_ads_list_ads / telegram_ads_get_ad
  → telegram_ads_watch_create(kind=moderation_result, ad_id, invoke_agent=true)
    (session_key binds this conversation automatically)
  → watcher polls silently; wakes THIS session only when the condition fires
  → never hermes cron / cronjob (SILENT still writes a new session every tick)

ЖЁСТКИЙ ЗАПРЕТ — что НЕЛЬЗЯ делать

При запросе на наблюдение за рекламой ЗАПРЕЩЕНО:

❌ Писать Python-скрипт с polling loop
❌ Писать bash-скрипт
❌ Создавать cron job
❌ Создавать новую SQLite базу
❌ Запускать фоновый процесс через terminal(background=True)
❌ Использовать delegate_task для «создания системы мониторинга»
❌ Устанавливать legacy hermes_telegram_ads.watcher
❌ Запускать V1/V2 watcher параллельно с operator
❌ Генерировать любой код для мониторинга

Read the full file on GitHub · 243 lines

Files

What ships with it

24 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

7d ago Changed · +10 lines f2014bfa2d88
10d ago First seen · 233 lines · 28 tokens per session scan A e352b2de4903

Subscribe to this mod's changes

operate-telegram-ads-growth-loop is a skill published in the GitHub repository sh0tn1k/telegram-ads (0 stars, last pushed 9d ago), licensed MIT. It adds 28 tokens to every session and 2,890 once invoked, about $0.0001 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.

Analytics and metrics Marketing and SEO

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens