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 matskevich/tg-mcp-guarded --skill tg-voice-notesgit clone --depth 1 https://github.com/matskevich/tg-mcp-guardedWrote 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/matskevich/tg-mcp-guarded/tg-voice-notes)<a href="https://agentmods.dev/skills/matskevich/tg-mcp-guarded/tg-voice-notes"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-voice-notes/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/matskevich/tg-mcp-guarded/tg-voice-notes"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-voice-notes.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 | $0.00037 | $0.00602 |
| Opus 5.5 | $0.00015 | $0.00241 |
| Sonnet 5.5 | $0.00007 | $0.00120 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
tg-voice-notes 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 13d 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
telegram voice notes
read the private operator profile in your workspace for the expected account, read server alias, private artifact location and existing local transcription backend. tg-mcp retrieves media; transcription is a separate local capability. do not assume a particular wrapper, speech model, cloud service or text-to-speech tool is installed.
locate and download
- verify read-server
tg_auth_statusagainst the profile and resolve the stable numeric peer. retrieve a bounded message slice around the requested note. - record peer id, message id, author, timestamp, caption/text and media metadata. ordinary message text or a caption does not prove that the attached audio was read.
- download only the needed attachment with the installed tool's supported shape:
tg_download_media(group=peer_id_string, message_id=source_message_id, output_dir=private_output_directory)
- check success and the returned file path. the path is on the mcp server's host; establish that the configured local transcription route can access that file. verify that a readable nonempty file has the expected media type before processing.
if download fails, inspect that same peer/message and available error evidence. do not search unrelated dialogs or silently treat the attachment as processed. keep raw media and full transcripts private; share a derivative only within authority.
transcribe with the existing route
look for the project's established transcription pipeline and cache first. reuse a valid cached transcript when its source identity/content matches the downloaded media. otherwise run the configured local backend, with language detection or the known language as appropriate. preserve timestamps when available; do not fabricate them.
do not install or download speech models implicitly, start duplicate jobs for the
same media, or upload private audio to a cloud service without explicit authority.
if no configured backend is available, report the missing capability and keep the
downloaded media as media_unprocessed; do not substitute a guessed transcript.
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.
- 13d ago First seen · 60 lines · 37 tokens per session scan A 506991627254
tg-voice-notes is a skill published in the GitHub repository matskevich/tg-mcp-guarded (10 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 602 once invoked, about $0.0001 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 2026-10-19.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.