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 skills add sanjar-x/claudegram --skill telegram-workflowgit clone --depth 1 https://github.com/sanjar-x/claudegramWrote 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/skills/sanjar-x/claudegram/telegram-workflow)<a href="https://agentmods.dev/skills/sanjar-x/claudegram/telegram-workflow"><img src="https://agentmods.dev/badge/skills/sanjar-x/claudegram/telegram-workflow/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.
<a href="https://agentmods.dev/skills/sanjar-x/claudegram/telegram-workflow"><img src="https://agentmods.dev/badge/skills/sanjar-x/claudegram/telegram-workflow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00097 | $0.02819 |
| Opus 5.5 | $0.00039 | $0.01128 |
| Sonnet 5.5 | $0.00019 | $0.00564 |
| Haiku 4.5 | $0.00010 | $0.00282 |
Grade A, and why
telegram-workflow 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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- telegram-workflow — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Работа с Telegram через claudegram
MCP-сервер claudegram даёт доступ к личному аккаунту пользователя
через MTProto (не бот). 58 типизированных tools, разбитых по категориям.
Базовые принципы безопасности
- Никогда не отправляй сообщения без явного подтверждения. Намерение «составить черновик» ≠ намерение отправить. Покажи проект текста и жди слов вроде «отправь / шли / да».
delete_message(revoke=True)— необратимо. ДефолтFalse(только у себя). Hookguard-deleteтребует подтверждения. Не передавайTrueбез явного запроса юзера.- Не помечай прочитанным автоматически.
mark_read— только по явной просьбе. Иначе пользователь потеряет визуальные индикаторы непрочитанного. - Деструктивные операции на чатах:
kick_participant,ban_participant,delete_dialog,leave_chat,terminate_authorization,block_user— всегда показывай action + entity и жди "да". - Markdown в
send_message/edit_message. Если в тексте есть*,_,[,],~,\``, и это **не** разметка — передайparse_mode="none"`, иначе Telegram упадёт с ParseMode-error. - Сессия — это пароль. Файл
*.sessionв${CLAUDE_PLUGIN_DATA}даёт полный доступ к аккаунту. Никогда не предлагай пересылать его, копировать в чат, коммитить. invoke_raw— крайний инструмент. Используй только если нет high-level tool. Можешь случайно изменить состояние аккаунта или нарваться на flood-wait.
Каталог инструментов
Все имена под префиксом mcp__plugin_claudegram_claudegram__. Сгруппированы по модулям.
Identity / Account (server/tools/identity/account.py)
| Tool | Назначение |
|---|---|
get_me |
Кто я залогинен |
get_authorizations |
Список активных сессий аккаунта (другие устройства) |
terminate_authorization |
Завершить чужую сессию (по hash) |
update_profile |
Изменить имя/фамилию/био |
set_online |
Online/offline статус |
Messaging (server/tools/messaging/{messages,history,pins,reactions}.py)
| Tool | Назначение |
|---|---|
send_message |
Отправить (parse_mode, reply_to, silent, link_preview, schedule_unix) |
edit_message |
Отредактировать своё |
delete_message |
Удалить (revoke=False default) |
forward_message |
Переслать (silent, drop_author) |
get_history |
Последние N (offset_id, min_id, from_user, reverse) |
search_messages |
Поиск по тексту (chat, from_user) |
mark_read |
Прочитано (max_id, clear_mentions) |
pin_message |
Закрепить (notify, pm_oneside) |
unpin_message |
Открепить одно или все |
react_message |
Поставить эмодзи-реакцию ("" чтобы снять) |
send_dice |
🎲/🎯/🏀/⚽/🎰/🎳 |
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.
- 1mo ago First seen · 173 lines · 97 tokens per session scan A 856c9bdb91f4
telegram-workflow is a skill published in the GitHub repository sanjar-x/claudegram (2 stars, last pushed 6mo ago), licensed MIT. It adds 97 tokens to every session and 2,819 once invoked, about $0.0004 per session on Opus 5.5. 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 skills, from other repositories
monday-planning
Suggest a weekly training structure from recent load and deliver the plan.
vigil-instrument
Instrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual code and config, not a plan. Use when asked to "add monitoring", "instrument this", "add logging", "set up tracing", or "observability".
pave-env
Set up local development environments — devcontainers, Docker Compose, one-command setup, dev/prod parity. Use when asked to "set up dev environment", "devcontainer", "docker compose for dev", "local development setup", or "one command to run".
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
boss-briefing
Vault health check — workflow pattern analysis, profile sync, session gap recovery, persona rule proposals.
monitor-activate
Activate the resident heartbeat and routine monitors.