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 Akash97p/agent-notify --skill agentnotifygit clone --depth 1 https://github.com/Akash97p/agent-notifyWrote 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/akash97p/agent-notify/agentnotify)<a href="https://agentmods.dev/skills/akash97p/agent-notify/agentnotify"><img src="https://agentmods.dev/badge/skills/akash97p/agent-notify/agentnotify/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/akash97p/agent-notify/agentnotify"><img src="https://agentmods.dev/badge/skills/akash97p/agent-notify/agentnotify.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00106 | $0.02021 |
| Opus 5.5 | $0.00042 | $0.00808 |
| Sonnet 5.5 | $0.00021 | $0.00404 |
| Haiku 4.5 | $0.00011 | $0.00202 |
Grade A, and why
agentnotify 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 1mo 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentNotify
Use the installed agentnotify CLI to alert the user at meaningful attention boundaries.
AgentNotify runs locally, reads its own per-user credentials, and raises a desktop notification
without stealing focus.
Notifying is the standing default, not something to ask permission for. The user is not watching the terminal; a finished task or a blocking question that is never announced is a task the user learns about late.
Command name
- Windows, and WSL calling the Windows broker:
agentnotify.exe - macOS, Linux, and a Linux-native broker:
agentnotify
Every example below uses agentnotify.exe; drop the extension on macOS and Linux.
Check availability
Run once per session, before the first send:
agentnotify.exe health
If the command is unavailable or the broker is not running, continue the user's task and report the notification failure only when it is relevant. Do not retry in a loop.
When to send
Send one without being asked whenever:
- human input is needed — a decision, a permission, an answer that blocks progress — and send it before starting to wait, not after;
- a task is finished, whatever its size;
- work is stopped by a terminal error or an external blocker.
Any request to be told when something happens — "ping me when it's done", "let me know if you get
stuck", "notify me" — is a request for an agentnotify send, for the rest of that session. Do not
ask the user which notification mechanism to use.
When you need an answer rather than an acknowledgement — you cannot continue until the user decides something — raise an interaction and wait for it instead; see Ask a question and wait for the answer below.
Do not send for:
- routine mid-task progress, ordinary tool calls, or every substep;
- a question the user just asked and is clearly still watching for;
- turns that are pure conversation — answering a question, explaining something, no work performed.
The only exception is an explicit opt-out ("no notifications", "stop pinging me"), which holds for the rest of that session. Silence from the user is not an opt-out. When in doubt, send it.
What ships with it
1 file 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.
- 1mo ago Changed · +67 lines · +36 tokens per session 75ade81170dd
- 1mo ago Changed · +14 lines c48b2f5e2fb8
- 1mo ago First seen · 118 lines · 70 tokens per session scan A 61387193cd7a
agentnotify is a skill published in the GitHub repository Akash97p/agent-notify (1 stars, last pushed 1mo ago), licensed MIT. It adds 106 tokens to every session and 2,021 once invoked, about $0.0004 per session on Opus 5.5. 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
todos
Use when the user asks for a shared plan, a task needs at least three substantive execution steps, or a loose TODO is pending. Without an explicit plan request, not for one-shot answers or checks, or one- to two-step work that is not already in the list.
low-code-platforms
Low-code and internal tool platforms including Retool, Supabase, Appsmith, Tooljet, n8n, and Zapier. Use when building admin panels, internal tools, workflow automations, or integrating low-code platforms with custom code.
one-on-one-prep
Deep-dive preparation for 1:1 meetings with direct reports. Surfaces recent work, wins, friction, wellbeing signals, and development goal progress, anchored in the org's performance framework, organizational values, and management best practices. Produces a prep sheet with suggested conversation topics, not a script.
meeting-prep
Comprehensive pre-meeting briefing that gathers all relevant context from Slack, email, Google Docs, Notion, and calendar. Produces a structured prep document so the manager walks into every meeting fully prepared. Supports thorough meeting preparation.
priority-planner
Helps managers cut through noise and identify their highest-leverage actions for the day or week. Aggregates signals from calendar, triage, team context, and OKRs/goals. Presents a suggested focus list grouped by urgency, importance, and investment. The manager reviews and adjusts. Supports effective execution and…
triage-messages
Batch-processes Slack messages and emails to surface what needs the manager's attention, categorised by urgency and type. Designed for batch-responder managers who do Slack sweeps rather than staying in reactive mode. Supports effective communication and responsiveness. Never drafts replies, only surfaces and…