telegram-send

telegram-send is a skill for Claude Code from leopu00/job-hunter-team. It costs 75 tokens per session (2,102 once invoked), scanned C, original, MIT.

An outbound messaging tool for sending replies and files to a user's Telegram chat through a configured bot. Telegram is a messaging app commonly used on phones.

In plain words
What is it for?
It helps send welcome messages, replies to Telegram conversations, generated documents, and onboarding reminders; messages between agents use a separate channel.
Why use it?
It lets an agent reach a user who is away from the web dashboard and keeps messages routed through the correct configured bot.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit It helps send welcome messages, replies to Telegram conversations, generated documents, and onboarding reminders; messages between agents use a separate channel.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/leopu00/job-hunter-team/telegram-send
Install

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.

Any agent
npx skills add leopu00/job-hunter-team --skill telegram-send
Clone the repo
git clone --depth 1 https://github.com/leopu00/job-hunter-team

Made for: Claude Code.

Wrote 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.

agentmods badge for telegram-send

README.md
[![agentmods](https://agentmods.dev/badge/skills/leopu00/job-hunter-team/telegram-send/github.svg)](https://agentmods.dev/skills/leopu00/job-hunter-team/telegram-send)
Your own site
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/telegram-send"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/telegram-send/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.

agentmods 80×15 button for telegram-send

Your own site · 80×15
<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/telegram-send"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/telegram-send.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,102 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00075 $0.02102
Opus 5 $0.00037 $0.01051
Sonnet 5 $0.00015 $0.00420
Haiku 4.5 $0.00007 $0.00210

Measured 10d ago against content hash e4d52de3f529, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

telegram-send scanned grade C with 2 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 10d 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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

- 👩‍💼 Assistente → `--from assistente` (default) - 👨‍✈️ Capitano → `--from capitano` - 🧙‍♂️ Mentor → `--from mentor` The wrapper picks token + chat_id from `channels.telegram.bots.<role>` in the config. If you omit `

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- ❌ `curl https://api.telegram.org/bot$TOKEN/sendMessage` by hand — quoting + URL-encoding bugs, no retry, no chunking.
agents/_skills/telegram-send/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

telegram-send — outbound to the user via Telegram

The user reaches you primarily from their phone. They send PDFs, voice notes, plain messages to your dedicated bot. The bridge relays inbound traffic to your tmux. Outbound — your reply, a welcome message, a generated CV — goes through jht-telegram-send.

3 bot dedicati (decisione 2026-05-13 rev2)

Each user-facing agent has its own Telegram bot:

  • 👩‍💼 Assistente → --from assistente (default)
  • 👨‍✈️ Capitano → --from capitano
  • 🧙‍♂️ Mentor → --from mentor

The wrapper picks token + chat_id from channels.telegram.bots.<role> in the config. If you omit --from, you can also set JHT_TG_BOT_ROLE=<role> in the agent env — the wrapper reads it as default.

When to use it

  • ✅ Initial welcome message after the wizard completes (boot prompt).
  • ✅ Reply to a Telegram-originated chat (the inbound bridge prefixes it with [@utente -> @assistente] [TG]).
  • ✅ Push a generated artifact (CV, cover letter) the user asked for.
  • ✅ Onboarding nudges ("send me your CV, even a draft is fine").

Do not use it for:

  • ❌ Inter-agent messages — use tmux-send instead.
  • ❌ Replies to web chat ([@utente -> @assistente] [CHAT]) — use jht-send.
  • ❌ Heavy attachments (>20 MB). Bot API ceiling; for big files use the dashboard or a relay (future).

Usage

# Default = bot Assistente (oppure ruolo letto da JHT_TG_BOT_ROLE)
jht-telegram-send "<message body>"

# Routing esplicito per ruolo
jht-telegram-send --from capitano "Notifica: 10 nuove posizioni ready."
jht-telegram-send --from mentor --html "<b>Step di crescita</b> della settimana..."

# Override chat_id (raro — debug / multi-tenant futuro)
jht-telegram-send --chat-id 1401844094 "explicit override"

Resolution order (no need to memorise — the wrapper does it):

  1. $TELEGRAM_BOT_TOKEN / $TELEGRAM_CHAT_ID env vars (override esplicito)
  2. $JHT_HOME/jht.config.jsonchannels.telegram.bots.<role>.{bot_token,chat_id} (role = --from o $JHT_TG_BOT_ROLE, default assistente)
  3. $JHT_HOME/credentials/telegram_bot.json (.token) — fallback legacy

Read the full file on GitHub · 152 lines

Files

What ships with it

6 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.

Changes

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.

  1. 10d ago First seen · 152 lines · 75 tokens per session scan C e4d52de3f529

Subscribe to this mod's changes

telegram-send is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 2,102 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.