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 ali-commits/tlgrm --skill tlgrmgit clone --depth 1 https://github.com/ali-commits/tlgrmWrote 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/ali-commits/tlgrm/tlgrm)<a href="https://agentmods.dev/skills/ali-commits/tlgrm/tlgrm"><img src="https://agentmods.dev/badge/skills/ali-commits/tlgrm/tlgrm.svg" alt="Measured on agentmods" 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 | $0.00100 | $0.01622 |
| Opus 5 | $0.00050 | $0.00811 |
| Sonnet 5 | $0.00020 | $0.00324 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
tlgrm 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 6d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Driving tlgrm (Telegram)
tlgrm is an unofficial Telegram client. You can drive it two ways:
- CLI: run
tlgrm <command> ...in the shell. Every command prints JSON. - MCP server: if the
tlgrmMCP server is connected, call its tools directly.
Both run the same underlying operations. Prefer the MCP tools when available. (The MCP server is a thin bridge to a local tlgrm "server" that owns the Telegram connection; it auto-starts that for you — you don't manage it.)
Preflight (do this first)
Confirm a session exists before anything else:
- CLI: run
tlgrm whoami. MCP: callwhoami. - If it returns
{"success": false, ...}or an auth error, tell the user to runtlgrm loginin their terminal (interactive — you cannot do it for them), and stop.
Accounts (multi-login)
The user may have several Telegram accounts. The default account is used unless one is chosen.
- See accounts:
tlgrm account list. - Act as a specific account: add
-a NAMEto any CLI command (e.g.tlgrm -a work send --target @x --text "hi"). For MCP, the account is fixed when the server is configured (--account); ask the user to set it if they want a different one — don't assume. - If the user names an account ("use my work account"), pass
-a <that>.
Capability map
Read (always available)
| Goal | CLI | MCP tool |
|---|---|---|
| Who am I | tlgrm whoami |
whoami |
| Recent chats | tlgrm chats --limit N |
list_chats |
| Read a chat | tlgrm history --target T --limit N [--offset-id ID] |
get_history |
| Find a message | tlgrm search --query "..." [--target T] |
search_messages |
| Who's in a group | tlgrm members --target T |
get_members |
| About a user | tlgrm user-info --target T |
user_info |
| About a chat | tlgrm chat-info --target T |
chat_info |
| Download media | tlgrm download --target T --message-id ID [--output PATH] |
download_media |
Write (CLI always; MCP needs --allow-write)
| Goal | CLI | MCP tool |
|---|---|---|
| Send a message | tlgrm send --target T --text "..." |
send_message |
| Send a file | tlgrm send --target T --file PATH [--caption "..."] [--voice] |
send_message |
| Reply | tlgrm reply --target T --message-id ID --text "..." |
send_message |
| Edit | tlgrm edit --target T --message-id ID --text "..." |
edit_message |
| Mark read | tlgrm read --target T [--max-id ID] |
mark_read |
| Forward | tlgrm forward --from A --to B --message-ids ID ... |
forward_messages |
| React | tlgrm react --target T --message-id ID --emoji E [--big] |
react |
| Pin | tlgrm pin --target T --message-id ID [--notify] |
pin |
| Unpin | tlgrm unpin --target T [--message-id ID] |
unpin |
| Mute | tlgrm mute --target T [--duration SECONDS] |
mute |
| Unmute | tlgrm unmute --target T |
unmute |
| Save to Saved Messages | tlgrm saved --text "..." |
(use send_message with saved target) |
| Create group/channel | tlgrm create-group --title T [--members ...] [--channel] |
create_group |
| Add members | tlgrm add-members --target T --members ... |
add_members |
| Schedule a message | tlgrm schedule send --target T --text TEXT (--at "ISO8601" | --in 2h) |
schedule_message |
| List/cancel scheduled | tlgrm schedule list --target T · tlgrm schedule cancel --target T --id ID |
(CLI only) |
| Send poll/quiz | tlgrm poll --target T --question Q --option A --option B ... [--quiz --correct N] |
send_poll |
What ships with it
2 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.
- 6d ago First seen · 104 lines · 100 tokens per session scan A e042ec87a024
tlgrm is a skill published in the GitHub repository ali-commits/tlgrm (1 stars, last pushed 2mo ago), licensed MIT. It adds 100 tokens to every session and 1,622 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…