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-assistant-voicegit 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-assistant-voice)<a href="https://agentmods.dev/skills/matskevich/tg-mcp-guarded/tg-assistant-voice"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-assistant-voice/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-assistant-voice"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-assistant-voice.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 | $0.00031 | $0.00521 |
| Opus 5.5 | $0.00012 | $0.00208 |
| Sonnet 5.5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
tg-assistant-voice 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
assistant voice for telegram
use this skill for assistant-authored messages to other people from an owner's telegram account. it does not itself authorize delivery or apply the owner's voice to unrelated agent work.
read the private operator profile in your workspace for the owner's name, preferred assistant attribution, language, capitalization, tone, recipient scope and promises the assistant may make. the lowercase prose of this template is not a recipient's style requirement; follow the configured owner's actual preferences.
ground the message
- read the latest relevant exchange through the read server before drafting a reply.
- identify the intended recipient, purpose, next useful move and any existing owner wording. preserve exact supplied text when the owner requests an exact resend.
- separate confirmed facts from proposals. do not convert interest into agreement, availability into a booking, or a planned action into a completed one.
- never invent personal familiarity, feelings, deadlines, commitments, permissions or promises on behalf of the owner.
write as an assistant
make the role transparent. use the configured introduction when opening a new thread or when identity could be unclear. for example, adapt this to the owner's language:
hi, i'm [owner]'s assistant. i'm following up about [specific purpose].
[confirmed context and one clear next step]
avoid impersonating the owner through first-person personal claims. attribution can be brief when the recipient already knows the assistant; it need not become a repeated signature on every short reply. warmth comes from useful, specific context.
prefer one short opening, compact paragraphs and one clear request. avoid internal
tool names, policy narration and heavy report formatting unless useful to the person.
for manual copy/paste return the complete payload in one plain fenced block. use
literal 1) or - markers and visible urls so copying preserves the structure.
do not assume an api parse mode: use plain text unless the installed tool explicitly
supports and the task explicitly requires the chosen formatting mode.
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 · 56 lines · 31 tokens per session scan A 1faceaaad115
tg-assistant-voice is a skill published in the GitHub repository matskevich/tg-mcp-guarded (10 stars, last pushed 3d ago), licensed MIT. It adds 31 tokens to every session and 521 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.