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 tg-digestgit 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/tg-digest)<a href="https://agentmods.dev/skills/sanjar-x/claudegram/tg-digest"><img src="https://agentmods.dev/badge/skills/sanjar-x/claudegram/tg-digest/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/tg-digest"><img src="https://agentmods.dev/badge/skills/sanjar-x/claudegram/tg-digest.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 | $0.00057 | $0.00390 |
| Opus 5 | $0.00028 | $0.00195 |
| Sonnet 5 | $0.00011 | $0.00078 |
| Haiku 4.5 | $0.00006 | $0.00039 |
Grade A, and why
tg-digest 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 10d 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:
- tg-digest — 100% identical, 0 lines differ
What it actually says
Собери сводку непрочитанных сообщений из Telegram.
Параметр $chat_limit (по умолчанию 20) ограничивает число чатов.
Алгоритм:
- Вызови
mcp__plugin_claudegram_claudegram__list_chatsсonly_unread=trueиlimitравным$chat_limit(если пусто —20). - Для каждого чата с непрочитанными вызови
mcp__plugin_claudegram_claudegram__get_historyсlimit=min(unread_count, 20). - Сгруппируй по чатам и выдай сводку на русском:
- Чат (тип, имя, кто пишет)
- 1-2 строки сути сообщений
- Если есть прямой вопрос ко мне — выдели жирным
- В конце — список чатов, требующих срочного ответа.
Не помечай прочитанными автоматически. Если попрошу — вызовешь
mcp__plugin_claudegram_claudegram__mark_read.
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.
- 10d ago First seen · 30 lines · 57 tokens per session scan A dd52273ef403
tg-digest is a skill published in the GitHub repository sanjar-x/claudegram (2 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 390 once invoked, about $0.0003 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.
Other skills, from other repositories
g-help
Context-aware help. With no argument, reads current project state and tells you where you are and what to do next, plus a map of every archive. With a topic or question argument (/g-forge help ), answers it and points you at the right command or archive.
g-resume
Re-hydrate a fresh session with the right slice of the durable record. The read-side counterpart to /g-retro — selectively retrieves the relevant retro, ADRs, journal, and handoff keyed by the current branch/milestone/first-task, and assembles a focused re-entry briefing. Loads distilled context into a clean window…
g-voice
Set how G-Forge communicates with you. With no argument, runs a short 2-question intake and sets the right profile automatically — you never need to know the tier names. With dev, mid, or eli5 as an argument, applies that profile directly. Writes .claude/voice-profile. Every G-Forge skill reads this and renders its…
g-listen
Enter listen mode — collect user reports and information without acting, then synthesize and triage when the user signals done.
freeze
Scope or freeze which files Claude can edit during debugging, a refactor, or review. Use when edits should stay in specific dirs, or for a read-only investigate lock. Backed by a sentinel + PreToolUse hook.
calendar-event-manager
Create macOS Calendar events with tiered sound alarms and paired Reminders so events are never missed across Mac and iOS.