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 tolboy/telegram-mcp-tdlib --skill telegram-inbox-assistantgit clone --depth 1 https://github.com/tolboy/telegram-mcp-tdlibWrote 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/tolboy/telegram-mcp-tdlib/telegram-inbox-assistant)<a href="https://agentmods.dev/skills/tolboy/telegram-mcp-tdlib/telegram-inbox-assistant"><img src="https://agentmods.dev/badge/skills/tolboy/telegram-mcp-tdlib/telegram-inbox-assistant/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/tolboy/telegram-mcp-tdlib/telegram-inbox-assistant"><img src="https://agentmods.dev/badge/skills/tolboy/telegram-mcp-tdlib/telegram-inbox-assistant.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 | $0.00050 | $0.01277 |
| Opus 5.5 | $0.00020 | $0.00511 |
| Sonnet 5.5 | $0.00010 | $0.00255 |
| Haiku 4.5 | $0.00005 | $0.00128 |
Grade A, and why
telegram-inbox-assistant 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Inbox Assistant
Help the user understand their Telegram inbox without changing Telegram state. The separately installed telegram-mcp-tdlib server supplies the tools. If it is missing or unauthenticated, read SETUP.md; installing this skill alone does not connect an account. Requires server 1.17.2 or later. For a shared daemon, client setup differs by host; SETUP.md covers the optional Claude Desktop tools bridge and Hermes HTTP. If bundled references are unavailable in the host's delivery surface, use the public setup guide.
Account and scope
Discover the connected Telegram server's tools by their base names below; the
host may prefix them with its configured server name. Do not assume telegram
or any particular username is the server identifier.
Use list_accounts (or the host's list_telegram_accounts alias) when account selection is unclear. Respect the
user's selected account; if several accounts are available with no selection,
ask which one to use. Call get_me for that account before reading conversations
and verify any username the user specified. Carry the same account label
through all calls. Do not merge accounts or switch accounts on an error.
Do not reproduce phone numbers or profile fields unrelated to the task.
Keep an explicit user-specified chat, folder, date range and reading budget. For an unspecified inbox digest, start with at most 20 recent chats and inspect at most 5 relevant conversations, up to 10 messages each. Explain this coverage in the answer. Offer to broaden it when that would help; do not silently scan the entire account.
Read the inbox
- Prefer
inbox_snapshotwithlimit: 20, max_chars: 4000for unread triage. It returns unread chats within a bounded recent-chat prefix, not every unread chat in the account. For a digest including read chats, uselist_chatsinstead. - For a requested folder, use
list_chat_folders/get_chat_folderand respect the folder's inclusion and exclusion rules. If membership cannot be established, say so instead of treating its explicitly included IDs as the entire folder. - Use
conversation_bundlewith the selectedchat_id,limit: 10andmax_chars: 6000to inspect relevant conversations. Its snippets have no timestamps: useget_historyorget_messageswhen dates, deadlines or the full wording matter. For an explicitly named chat, read it directly rather than enumerating unrelated conversations. - Use
search_messagesfor a user-specified subject within a known chat, andget_message_contextto understand a particular hit. Do not widen to global search merely because a bounded chat search returned no hits. - If compact tools are unavailable, use
list_chatsandget_historywith the same scope and budget. If no suitable read tool is available, explain the missing dependency rather than inventing results.
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.
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.
- yesterday First seen · 102 lines · 50 tokens per session scan A 6a7e9f196091
telegram-inbox-assistant is a skill published in the GitHub repository tolboy/telegram-mcp-tdlib (9 stars, last pushed yesterday), licensed Apache-2.0. It adds 50 tokens to every session and 1,277 once invoked, about $0.0002 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 2026-10-16.
Other skills, from other repositories
harness-design-fuzzing
Reference vocabulary for designing instrumented harnesses that drive vulnerability discovery — design classes (trigger-driven vs coverage-driven), tiered scope (T1 isolated function / T2 multi-component / T3 full build), systematic input exploration, the two-coverage distinction (fuzzer-feedback vs audit)…
memory-safety-c-cpp
Reference vocabulary for memory-safety vulnerabilities in native C/C++ code — bug-class taxonomy, common arithmetic patterns that lead to corruption, dispatch-family discipline, type-confusion idioms, use-after-free patterns, and exploitability factors. Read when analyzing, hypothesizing, designing harnesses for, or…
zafiro-config
Read or change Zafiro's own settings by editing the JSON files in its sandbox. Use this whenever the user asks to see, explain, change, add or remove Zafiro configuration — agent profiles, execution rules, takeover rules, MCP servers, custom Python tools, text actions, saved LLM configs, or app preferences such as…
email-formatting
Markdown formatting conventions for email summary documents — heading depth, list style, line length, emoji policy, and a mandatory provenance footer. Read this when producing a markdown report that summarizes one or more email messages so the output matches the project's house style.
json-schema-emails
Canonical shape of the .workflow/emails/emails.json file passed between the fetch and summarize states — required fields (sender, recipient, subject, date, body), types, and field semantics. Read this whenever you write or read emails.json so producer and consumer agree on the shape.
cortex-profile
View and manage your cognitive profile — how you think, work patterns, blind spots, and cross-domain connections. Use when the user says 'show my profile', 'how do I work', 'what are my patterns', 'cognitive style', 'blind spots', 'methodology', or at the start of a session to load context. Also use 'rebuild profile'…