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 commands/uri6407/claudegram/authgit clone --depth 1 https://github.com/Uri6407/claudegramWhat 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 | $0.00014 | $0.00431 |
| Opus 5 | $0.00007 | $0.00216 |
| Sonnet 5 | $0.00003 | $0.00086 |
| Haiku 4.5 | $0.00001 | $0.00043 |
Grade A, and why
auth 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 2d 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.
This is a copy
100% identical to auth — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Двухшаговый интерактивный логин в Telegram прямо из активной Claude-сессии.
Шаги:
- Запусти
mcp__plugin_claudegram_claudegram__health_check— если ужеauthorized: true, скажи юзеру и выйди. - Иначе вызови
auth_request_code()— Telegram пришлёт SMS-код на привязанный номер. Покажи юзеруphone(маскированный). - Спроси у юзера код через
AskUserQuestion(полеcode, 5 цифр). Если в userConfig не было пароля 2FA — спроси и его (опционально). - Вызови
auth_submit_code(code=<код>, password_2fa=<2fa или "">). - Если в ответе
needs_2fa: true— спроси пароль и повтори с ним. - Если в ответе
error: PhoneCodeInvalidError/Expired— предложи запросить новый код черезauth_request_code(). - После успеха вызови
health_check— должен показатьok=true,authorized=true,self_id. Скажи юзеру что готово.
Важно: НЕ предлагай ! claudegram-auth через Bash — он требует интерактивного
stdin, который Bash tool в Claude Code не предоставляет (commands/auth.md
устаревший подход). Используй ТОЛЬКО эти MCP-tools.
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.
- 2d ago First seen · 30 lines · 14 tokens per session scan A 5f89c4050512
auth is a command published in the GitHub repository Uri6407/claudegram (2 stars, last pushed 3d ago), licensed MIT. It adds 14 tokens to every session and 431 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to auth, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
coding-prompt
You are continuing work on a long-running autonomous development task. This is a FRESH context window - you have no memory of previous sessions.
initializer-prompt
You are the FIRST agent in a long-running autonomous development process. Your job is to set up the foundation for all future coding agents.
commit
This command helps you create well-formatted commits with conventional commit messages and emoji.
onboard
This command acts as an expert technical mentor to help you rapidly understand a new codebase, generating a comprehensive "Survival Guide" for the project.
code-review
Code review a pull request.
commit
Analyze changes and create a high-quality git commit.