tg-notify-timers

tg-notify-timers is a skill for Claude Code from Xakki/ai-agents-skills. It costs 154 tokens per session (1,350 once invoked), scanned B, original, MIT.

A settings tool for changing the timers and delivery delays used by Telegram notification hooks. Hooks are automatic scripts that send messages when Claude Code stops, waits for permission, or becomes idle.

In plain words
What is it for?
Use it to tune waiting thresholds, delivery delays, and debouncing for Telegram notifications in Claude Code.
Why use it?
It lets you adjust when notifications are sent without editing plugin files that may be overwritten during updates. Changes take effect after Claude Code restarts.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions Claude Code.

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

Good fit Use it to tune waiting thresholds, delivery delays, and debouncing for Telegram notifications in Claude Code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xakki/ai-agents-skills/tg-notify-timers
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 Xakki/ai-agents-skills --skill tg-notify-timers
Clone the repo
git clone --depth 1 https://github.com/Xakki/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-timers

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/xakki/ai-agents-skills/tg-notify-timers"><img src="https://agentmods.dev/badge/skills/xakki/ai-agents-skills/tg-notify-timers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 154 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00154 $0.01350
Opus 5 $0.00077 $0.00675
Sonnet 5 $0.00031 $0.00270
Haiku 4.5 $0.00015 $0.00135

Measured 11d ago against content hash c66b9c4edebb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade B, and why

tg-notify-timers scanned grade B with 1 finding 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 11d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Canonically — in the `env` of `~/.claude/settings.json` (the hooks inherit its environment).
skills/tg-notify-timers/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tg-notify-timers — TG-hook timers config

Manages the 7 vars the plugin hooks tg-on-notification.sh and tg-on-stop.sh use to decide when and after what delay to send a message to Telegram.

How it works (important)

The hooks read each value as ${TG_NOTIFY_*:-<default>} — i.e. they take the number from the env, and if the var is absent — the built-in default. The hook scripts live in the read-only plugin cache (~/.claude/plugins/cache/...), you can't edit them — they get overwritten on update. So the only way to change a timer is to set an env var that overrides the default.

Canonically — in the env of ~/.claude/settings.json (the hooks inherit its environment). The "default" profile = none of the 7 vars set → the built-in defaults apply. Changes are picked up after a restart of Claude Code (env is read at startup).

Params

Var Hook Semantics Default
TG_NOTIFY_PERM_THRESHOLD notification min duration (sec) for "🔐 Требуется разрешение" 1200 (20m)
TG_NOTIFY_IDLE_THRESHOLD notification min duration (sec) for "⏰ Ожидает ввода" 1200 (20m)
TG_NOTIFY_DELAY notification delivery delay (cancel window, sec) 1800 (30m)
TG_NOTIFY_DEBOUNCE notification min interval between schedules per session 300 (5m)
TG_NOTIFY_STOP_THRESHOLD stop min task duration for a Stop notification 1200 (20m)
TG_NOTIFY_STOP_DELAY stop Stop delivery delay (cancel window) 1800 (30m)
TG_NOTIFY_STOP_DEBOUNCE stop min interval between Stop schedules per session 1200 (20m)

All values are seconds, stored in JSON as strings ("1800").

View current

jq '.env | with_entries(select(.key | startswith("TG_NOTIFY_")))' ~/.claude/settings.json

Empty → the defaults from the table apply.

Change

Edit env in ~/.claude/settings.json (directly via Edit / skill update-config, or the jq below). One timer:

jq '.env.TG_NOTIFY_STOP_THRESHOLD = "1800"' ~/.claude/settings.json > /tmp/s.json && mv /tmp/s.json ~/.claude/settings.json

Read the full file on GitHub · 98 lines

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. 11d ago First seen · 98 lines · 154 tokens per session scan B c66b9c4edebb

Subscribe to this mod's changes

tg-notify-timers is a skill published in the GitHub repository Xakki/ai-agents-skills (6 stars, last pushed 21d ago), licensed MIT. It adds 154 tokens to every session and 1,350 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

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

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

automation

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

KunAgent/Kun · 19 tokens