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 leopu00/job-hunter-team --skill notify-usergit clone --depth 1 https://github.com/leopu00/job-hunter-teamWrote 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/leopu00/job-hunter-team/notify-user)<a href="https://agentmods.dev/skills/leopu00/job-hunter-team/notify-user"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/notify-user/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/leopu00/job-hunter-team/notify-user"><img src="https://agentmods.dev/badge/skills/leopu00/job-hunter-team/notify-user.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00090 | $0.01647 |
| Opus 5 | $0.00045 | $0.00823 |
| Sonnet 5 | $0.00018 | $0.00329 |
| Haiku 4.5 | $0.00009 | $0.00165 |
Grade A, and why
notify-user 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 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.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notify-user — single API to reach the user
The user has multiple channels (Telegram bot, web dashboard, future mobile push). Each agent should not have to know which one is live. jht-notify-user decides:
- INSERTs the message into
pending_user_messages(jobs.db, schema V5). - Best-effort send via
jht-telegram-send(~25s timeout). - If Telegram succeeds →
delivered_via='telegram'. - If it fails or isn't configured →
delivered_via='web'. The row is picked up byjht cloud pushand appears on the dashboard at jobhunterteam.ai.
The user therefore receives every message somewhere. The agent never has to handle "Telegram is down" branches.
⚠️ Since the chat lane was unified: this message is ALSO a chat bubble
jht-send and jht-notify-user used to write to two different places — the
chat thread and the notification queue. They do not any more. The box mirrors
pending_user_messages into <agent>/chat.jsonl, so what you write here also
shows up as your bubble in the game chat and in the web chat thread, right
next to the replies you send with jht-send.
The consequence is the only rule that matters here: one message, one tool. Never send the same content down both paths. The user would read it twice, and neither copy knows about the other — the lane cannot tell a duplicate from two turns that happen to say the same thing ("ok" arrives a thousand times), so nothing downstream will clean it up.
When to use it
- ✅ Capitano notifies the user every N ready positions (decisione 2026-05-13, batch).
- ✅ Mentor weekly digest / pattern alerts.
- ✅ Assistente asks the user a question that requires their input.
- ✅ Any alert ("ho consumato 95% della finestra, fermo il team?").
When NOT to use it
- ❌ Inter-agent messages — use
tmux-send/jht-tmux-send. - ❌ Replies to a
[CHAT]message on the web dashboard — usejht-send(already in the chat thread). - ❌ Replies to a
[TG]inbound — usejht-telegram-senddirectly: you already know Telegram is up because the user just wrote you from there. Saves a DB roundtrip. - ❌ Heavy attachments (>20 MB). Use the user's CV folder + a short notification body.
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.
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.
- 10d ago First seen · 123 lines · 90 tokens per session scan A 981125e3d7ac
notify-user is a skill published in the GitHub repository leopu00/job-hunter-team (49 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 1,647 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 2026-08-30.
Other skills, from other repositories
gws-drive
Google Drive: Manage files, folders, and shared drives.
gws-calendar
Google Calendar: Manage calendars and events.
gws-gmail-reply
Gmail: Reply to a message (handles threading automatically).
gws-gmail-send
Skill "gws-gmail-send" from googleworkspace/cli, covering gmail +send, usage, flags, examples and tips.
gws-calendar-insert
Google Calendar: Create a new event.
gws-gmail-watch
Gmail: Watch for new emails and stream them as NDJSON.