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 qrak/telegram-commandcode --skill skillgit clone --depth 1 https://github.com/qrak/telegram-commandcodeWrote 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/qrak/telegram-commandcode/skill)<a href="https://agentmods.dev/skills/qrak/telegram-commandcode/skill"><img src="https://agentmods.dev/badge/skills/qrak/telegram-commandcode/skill/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/qrak/telegram-commandcode/skill"><img src="https://agentmods.dev/badge/skills/qrak/telegram-commandcode/skill.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 | $0.00093 | $0.01743 |
| Opus 5.5 | $0.00037 | $0.00697 |
| Sonnet 5.5 | $0.00019 | $0.00349 |
| Haiku 4.5 | $0.00009 | $0.00174 |
Grade A, and why
telegram-bridge 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 9d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Telegram Bridge
Give the agent a phone. This skill covers the full loop: verifying the Telegram MCP connection, choosing the right tool, formatting messages that Telegram will not reject, sending artifacts, and reading the human's reply.
0. Preflight — always do this first
Before the first send in a session, call telegram_health.
| Result | Meaning | Action |
|---|---|---|
| Bot id, username | Ready | Continue |
TELEGRAM_BOT_TOKEN is not set / only tool is telegram_status |
Not configured | Walk the user through Setup below, then stop |
| HTTP 401 | Token revoked or wrong | Tell the user to run /revoke in @BotFather and re-add the token |
| Network error | Host cannot reach api.telegram.org |
Report it; do not retry more than twice |
Never claim a message was delivered without a successful tool result. If the call fails, say so and show the agent's error text.
Setup (only if the tool is missing)
Ask for the numeric chat ID and have the user create a bot with @BotFather. The token must be set in the MCP server environment — never ask the user to paste it into the chat.
Command Code:
cmd mcp add telegram \
-e TELEGRAM_BOT_TOKEN=<token> \
-e TELEGRAM_DEFAULT_CHAT_ID=<chat_id> \
-- npx -y github:qrak/telegram-commandcode
Claude Code:
claude mcp add telegram \
-e TELEGRAM_BOT_TOKEN=<token> \
-e TELEGRAM_DEFAULT_CHAT_ID=<chat_id> \
-- npx -y github:qrak/telegram-commandcode
After adding, the agent must be restarted before the tools appear.
1. Choosing the tool
| Goal | Tool | Notes |
|---|---|---|
| Status, summary, alert | telegram_send_message |
Plain text by default |
| Screenshot, chart, rendered page | telegram_send_photo |
URL or absolute local path, ≤10 MB |
| Log, diff, PDF, zip, report | telegram_send_file |
URL or absolute local path, ≤50 MB |
| "Did they reply?" | telegram_get_updates |
Returns only unseen updates by default |
| Working / done / failed marker | telegram_send_reaction |
Needs the message id |
| Pick up a file the user sent | telegram_download_file |
≤20 MB via Bot API |
What ships with it
4 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.
- 9d ago First seen · 164 lines · 93 tokens per session scan A e2a4b7bebe21
telegram-bridge is a skill published in the GitHub repository qrak/telegram-commandcode (3 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 1,743 once invoked, about $0.0004 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.