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 agentmods add skills/5dive-ai/5dive-plugins/notify-usernpx skills add 5dive-ai/5dive-plugins --skill notify-usergit clone --depth 1 https://github.com/5dive-ai/5dive-pluginsWrote 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/5dive-ai/5dive-plugins/notify-user)<a href="https://agentmods.dev/skills/5dive-ai/5dive-plugins/notify-user"><img src="https://agentmods.dev/badge/skills/5dive-ai/5dive-plugins/notify-user.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.01300 |
| Opus 5 | $0.00036 | $0.00650 |
| Sonnet 5 | $0.00014 | $0.00260 |
| Haiku 4.5 | $0.00007 | $0.00130 |
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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
notify-user — Telegram comms playbook (Antigravity edition)
You're paired with a Telegram chat via the telegram-agy MCP plugin's
bot. The user reads only what reaches the chat — anything you print
to stdout or stderr never gets to them. Every inbound Telegram message
MUST get a reply via the MCP tool before your turn ends, even if it's
just "Done."
The loop is simple: wait_for_message → do the work → reply →
wait_for_message again.
Cadence
- Inbound → ack <5s. Send a short "on it"
replybefore starting any non-trivial work. The Telegram-paired user has no other signal that you received the message. - Long work → edit only if you're still the latest message. Use
edit_messagefor progress updates so the user's phone doesn't buzz on every tick — but only if your previous reply is still the newest message in the chat. If a fresher message exists (a new inbound from the user, or another reply you sent in between), the edit will be missed in scrollback; send a newreplyinstead. - Done or blocked → new
reply. A fresh reply triggers a push notification;edit_messagedoes not. - Silence ceiling: ~60s. Beyond that the user starts assuming the bridge broke. Send a short edit or new reply (per the latest-message rule above) even mid-work if a substantive reply is still >60s away. The silence-watchdog hook will also ping the user after 120s of tool calls without a reply — that's a safety net, not something to rely on.
- Default
timeout_seconds=50forwait_for_message. Antigravity kills any MCP tool call past itsMCP tool timeout(default 60s), so higher timeouts drop messages arriving near the boundary. If<telegram timeout=true/>comes back, END YOUR TURN; do not re-callwait_for_messageto keep polling. The server re-arms you when the next message is queued.
Hard rules
- Reply via the
replyMCP tool, not stdout. Plain text in your turn output is invisible to the Telegram user. - Don't auto-delegate on acknowledgements. Phrases like "you can
talk now", "go ahead", "say something" mean "the channel works,
please respond" — they are NOT requests to involve another agent.
Reply via
reply. Inter-agent handoff (via the5dive-cliskill if installed) is appropriate only when the user explicitly asks for it ("ask scout to do this", "hand off to marketing"). - Don't reply to chats you weren't messaged from. The server
rejects
chat_idvalues outside its allowlist; always sourcechat_idfrom a priorwait_for_messageresult.
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.
- 3d ago First seen · 108 lines · 71 tokens per session scan A 88c7137f3fe6
notify-user is a skill published in the GitHub repository 5dive-ai/5dive-plugins (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,300 once invoked, about $0.0004 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.
Other skills, from other repositories
researcher
Delegate a deep research or survey task to Google's Antigravity CLI (agy staffer, fast Gemini). Use when the user says /agy:researcher, "ask agy to research", "have the agy staffer survey X", or wants a second, independent deep-dive on a topic or codebase without spending the host model's quota.
ask
Ask Google's Antigravity CLI (agy staffer, fast Gemini) a cheap one-shot question - the fast zero-tool mode and the post-install smoke test. Use when the user says /agy:ask, "ask agy", "quick second opinion from agy", or right after installing to verify the plugin works.
reviewer
Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…
gemini-imagegen
Use when the user asks to generate, create, draw, edit, or restyle an image, or when a task needs image assets — logos, icons, illustrations, hero images, textures, photos, placeholder art, social/OG cards. Claude cannot produce raster images; a Gemini session via the agy (Antigravity) CLI has a generateimage tool…
github-ci-fix
Use when PR checks fail, CI is red, or GitHub Actions workflows break - systematically inspects failing checks via gh CLI, pulls logs, checks for flakiness and scopes the breaking commit, scopes external checks, then creates fix plan using existing plan skill.
antigravity-rescue
Use when stuck, wanting a second implementation or diagnosis pass, or handing a substantial task to Google's Antigravity CLI (agy) through a real subprocess -- a genuinely different agent harness, not just another model. Not relevant when already running under Antigravity CLI itself.