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-guarded-actionsgit 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-guarded-actions)<a href="https://agentmods.dev/skills/matskevich/tg-mcp-guarded/tg-guarded-actions"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-guarded-actions/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-guarded-actions"><img src="https://agentmods.dev/badge/skills/matskevich/tg-mcp-guarded/tg-guarded-actions.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 | $0.00033 | $0.00776 |
| Opus 5.5 | $0.00013 | $0.00310 |
| Sonnet 5.5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00003 | $0.00078 |
Grade A, and why
tg-guarded-actions 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
guarded telegram actions
load the private operator profile in your workspace: expected account username and
numeric user id, server aliases, repository path, permitted recipients and authority
rules. inspect installed tool schemas and current tg_get_actions_policy.
authority and policy
human authority answers who, what and why; backend process confirmation validates the concrete api operation. keep these separate in the receipt. an explicit ordinary one-off send request with clear target and content supplies authority for that send; do not ask the owner to repeat a magic phrase solely to fill an api parameter. read the exact backend confirmation text from policy or preview, pass it as the process parameter, and never represent that value as a new user-authored statement. if target, payload or substantive authority is missing, resolve that missing fact.
all writes use the actions server, including files, forwards, edits, deletes, bot
buttons and membership changes. never bypass it with direct telethon, raw requests
or another session. an existing mcp bridge may transport the same guarded tool call.
retain allowlist, confirmation, approval, idempotency and TG_ENFORCE_ACTION_PROCESS=1.
stop for disabled actions, unsafe startup policy or account/target mismatch.
one action
- verify
tg_auth_statuson both routes against the operator profile. resolve the live username andaccount.idexplicitly; the backend guard only checks username. resolve the stable numeric target through read tools and the actions allowlist. - save the latest target message id as a watermark and prepare the exact payload.
call the intended write tool with
dry_run=true. - compare returned target, payload scope and
action_hashwith human authority. retain the matching one-timeapproval_codeandconfirmation_text_required. - wait the configured approval minimum age. execute the same payload using
dry_run=false,confirm=true, the exact processconfirmation_textand code. a changed payload needs a new dry-run; an expired code needs a fresh preview. - read back through the read server in the same peer. for sends, require a new message id above the watermark, the expected author, timestamp and exact payload. verify attachment/caption or the intended state change as applicable. ambiguous matches remain uncertain; an older identical message does not verify this send.
- report actual account, target, action, verification and message ids when available.
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 · 64 lines · 33 tokens per session scan A 1bbab2873735
tg-guarded-actions is a skill published in the GitHub repository matskevich/tg-mcp-guarded (10 stars, last pushed 3d ago), licensed MIT. It adds 33 tokens to every session and 776 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.