A set of scripts for measuring Telegram channel and YouTube performance, including subscribers, views, reactions, likes, and engagement rate. ERR, or Engagement Rate by Reactions, estimates how much a Telegram audience reacts to posts.

Use it to review the last day, week, or month, find top Telegram posts, and retrieve YouTube statistics in JSON or regular output.

It gathers channel and video statistics for selected time periods, so you can compare recent performance without checking each post or video manually.

analytics — Skill for Claude Code and Codex by AlekseiUL: A set of scripts for measuring Telegram channel and…

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 skills/alekseiul/sprut-agent-kit/analytics

Any agent

npx skills add AlekseiUL/sprut-agent-kit --skill analytics

Clone the repo

git clone --depth 1 https://github.com/AlekseiUL/sprut-agent-kit

Made for: Claude Code, Codex.

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/alekseiul/sprut-agent-kit/analytics.svg)](https://agentmods.dev/skills/alekseiul/sprut-agent-kit/analytics)

Your own site

<a href="https://agentmods.dev/skills/alekseiul/sprut-agent-kit/analytics"><img src="https://agentmods.dev/badge/skills/alekseiul/sprut-agent-kit/analytics.svg" alt="Measured on agentmods" height="20"></a>

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 832 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00029	$0.00832
Opus 5	$0.00015	$0.00416
Sonnet 5	$0.00006	$0.00166
Haiku 4.5	$0.00003	$0.00083

Measured 4d ago against content hash d856b43fd635, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analytics 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 4d ago.

The scan reads SKILL.md. This mod also ships 7 executable files (scripts/daily-report.sh, scripts/tg-channel-stats.py, scripts/tg-stats-auth.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/analytics/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analytics - Статистика каналов

Возможности

Telegram (YOUR_CHANNEL)

Подписчики (точное число)
Просмотры, репосты, реакции каждого поста
ERR (Engagement Rate by Reactions)
Топ постов за период
Фильтр по периоду: 24h, 7d, 30d

YouTube (YOUR_YOUTUBE_HANDLE)

Просмотры, лайки по каждому видео (RSS, бесплатно)
С API-ключом: подписчики, комментарии, полная стата

Скрипты

# Полная статистика за 7 дней
python3 skills/analytics/scripts/tg-stats.py --period=7d

# За сутки
python3 skills/analytics/scripts/tg-stats.py --period=24h

# За месяц, топ-10
python3 skills/analytics/scripts/tg-stats.py --period=30d --top=10

# JSON формат (для парсинга)
python3 skills/analytics/scripts/tg-stats.py --period=7d --json

YouTube (RSS - быстрый)

python3 skills/analytics/scripts/yt-stats.py
python3 skills/analytics/scripts/yt-stats.py --json

YouTube (Analytics API - полная стата)

# За 30 дней (по умолчанию)
python3 skills/analytics/scripts/yt-deep-stats.py

# За 7 дней
python3 skills/analytics/scripts/yt-deep-stats.py --days=7

# JSON
python3 skills/analytics/scripts/yt-deep-stats.py --days=30 --json

Глубокая аналитика: подписчики gained/lost, watch time, avg view duration, источники трафика, топ видео с удержанием.

Настройка

Telegram (готово ✅)

Авторизация: Telethon session в ~/.openclaw/tg-stats-session
Скрипт авторизации: scripts/tg-stats-auth.py
API ID: задайте через TG_API_ID env
Канал: YOUR_CHANNEL (ID: -1002484275132)

YouTube (готово ✅)

OAuth2 токен: ~/.openclaw/yt-analytics-token.pickle
Скрипт авторизации: scripts/yt-analytics-auth.py
Channel ID: YOUR_CHANNEL_ID
Google OAuth client: тот же что для gog (calendar)

Безопасность

Все данные read-only
Telethon session локально на local server
Никакие данные не отправляются наружу
Бот в канале с минимальными правами (только can_post_messages)

🔗 Связанные скиллы

Скилл	Связь
`creator-marketing`	Маркетолог использует данные analytics для рекомендаций по контенту
`copywriter`	Смотрит какие посты лучше заходят перед написанием новых
`youtube-seo`	Оптимизирует SEO на основе реальных данных (источники трафика, топ видео)

Read the full file on GitHub · 103 lines

Files

What ships with it

7 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.

4d ago First seen · 103 lines · 29 tokens per session scan A d856b43fd635

Subscribe to this mod's changes

analytics is a skill published in the GitHub repository AlekseiUL/sprut-agent-kit (63 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 832 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 2026-08-30.

Analytics and metrics agent-skills ai-agents ai-assistant automation claude-code claudeclaw

analytics