tg-notify

tg-notify is a skill for Claude Code from Xakki/ai-agents-skills. It costs 128 tokens per session (664 once invoked), scanned A, original, MIT.

A skill that sends short reports from a coding session to a Telegram direct message, group, or channel through a bot. It can also support automatic notifications for long tasks and certain prompts when configured.

In plain words
What is it for?
Use it to send a Telegram status update after a task lasting more than 20 minutes, for scheduled jobs, or whenever the user explicitly requests a notification.
Why use it?
It keeps users informed when a long-running task finishes or when they are away from the terminal, while avoiding automatic messages for short tasks.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the ai-agents-skills plugin — 23 skills, 3 agents, 6 hooks shipped together

Good fit Use it to send a Telegram status update after a task lasting more than 20 minutes, for scheduled jobs, or whenever the user explicitly requests a notification.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Xakki/ai-agents-skills
Claude Code
/plugin install ai-agents-skills

Made for: Claude Code.

Or install ai-agents-skills, the plugin that ships this one along with the rest of its 23 skills, 3 agents, 6 hooks.

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 tg-notify

README.md
[![agentmods](https://agentmods.dev/badge/skills/xakki/ai-agents-skills/tg-notify/github.svg)](https://agentmods.dev/skills/xakki/ai-agents-skills/tg-notify)
Your own site
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/tg-notify"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/tg-notify/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 tg-notify

Your own site · 80×15
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/tg-notify"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/tg-notify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 128 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 664 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00128 $0.00664
Opus 5 $0.00064 $0.00332
Sonnet 5 $0.00026 $0.00133
Haiku 4.5 $0.00013 $0.00066

Measured 12d ago against content hash 5b5078dc62ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tg-notify 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 12d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (context-header.sh, runtime.sh, tg-notify.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/tg-notify/SKILL.md · 54 lines

What it actually says

tg-notify

Manual sender of a Telegram message to a configurable destination (DM, group, or channel) via a bot. The plugin also ships hooks (../../hooks/) that auto-notify on long turns and permission/idle prompts — those fire on their own once configured; this skill is the manual sender.

When to use

Threshold: 20-minute minimum for auto-sends (matches the TG_NOTIFY_STOP_THRESHOLD hook default). Shorter → just answer in the terminal. Unknown duration → treat as below threshold, don't send.

Auto-send only if one of:

  • A long-running op (>20 min) just finished — send a short status report with timing.
  • The user explicitly asks for a Telegram notification/ping (any duration).
  • A scheduled / background job needs to report (any duration).

Track duration honestly with SECONDS=0; <command>; dur=$SECONDS so the check is real.

Main thread only

If you are a subagent / teammate (spawned with a task by another agent, no direct line to the user), do not invoke this skill — return your report to the teamlead and let them decide. When in doubt, assume subagent and hand the report up. (Auto-send hooks are unaffected; they fire on the main session's lifecycle, not from inside a subagent.)

How to invoke

ROOT="${AI_AGENTS_SKILLS_ROOT:-${CLAUDE_PLUGIN_ROOT:-${PLUGIN_ROOT:-${CURSOR_PLUGIN_ROOT:-}}}}"
TG="$ROOT/skills/tg-notify/tg-notify.sh"

# Short status (title only)
"$TG" -s ok -t "Backup завершён" -m "wephost: 64 GiB, 12m 03s"

# Title + multi-line body via stdin (preferred for reports)
{
  echo "rsync /home/wephost: 64.0 GiB, 12m 03s"
  echo "Все сервисы запущены."
} | "$TG" -s ok -t "saFin: миграция завершена"

# Send to a different destination than the default (e.g. a channel)
echo "released v1.2.3" | "$TG" -s ok -t "Deploy" -c "@my_channel"

Reference

Configuration (env vars, destination types), full flag table, and conventions live in reference.md — read it when you're actually sending.

Files

What ships with it

5 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. 12d ago First seen · 54 lines · 128 tokens per session scan A 5b5078dc62ec

Subscribe to this mod's changes

tg-notify is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 21d ago), licensed MIT. It adds 128 tokens to every session and 664 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

skill-factory

A workflow that examines completed session work and turns reusable patterns into Claude Code skills.

sangrokjung/claude-forge · 122 tokens

session-wrap

Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.

sangrokjung/claude-forge · 58 tokens

relay

Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…

sangrokjung/claude-forge · 97 tokens

docs

Use when documentation generally needs to catch up with a branch before pushing or merging, covering internal developer docs, external customer-facing docs, and release notes together — "update the docs", "do a docs pass before I merge", "make sure everything's documented". Prefer this when no single documentation…

The01Geek/prflow · 97 tokens

strategic-compact

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

sangrokjung/claude-forge · 27 tokens

automation

Create, inspect, update, delete, and run Kun scheduled tasks or saved workflows.

KunAgent/Kun · 19 tokens