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 filipebraida/adonisjs-starter-kit --skill notificationsgit clone --depth 1 https://github.com/filipebraida/adonisjs-starter-kitWrote 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/filipebraida/adonisjs-starter-kit/notifications)<a href="https://agentmods.dev/skills/filipebraida/adonisjs-starter-kit/notifications"><img src="https://agentmods.dev/badge/skills/filipebraida/adonisjs-starter-kit/notifications/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/filipebraida/adonisjs-starter-kit/notifications"><img src="https://agentmods.dev/badge/skills/filipebraida/adonisjs-starter-kit/notifications.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 | $0.00130 | $0.01599 |
| Opus 5.5 | $0.00052 | $0.00640 |
| Sonnet 5.5 | $0.00026 | $0.00320 |
| Haiku 4.5 | $0.00013 | $0.00160 |
Grade A, and why
notifications 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notifications + SSE
In-app notifications persist as rows in the notifications table and stream to the user's personal channel in realtime via SSE. Facteur (@facteurjs/adonisjs) is the framework: one Notification<User, Params> class per type, with a deliverBy: { database, transmit } config and per-channel methods (asDatabaseMessage, asTransmitMessage). Transmit (@adonisjs/transmit) is the SSE transport — in-memory / single-node by default (transport: null in config/transmit.ts); swap to a distributed transport (e.g. Redis) when scaling out to multiple instances. Emission always goes through domain events: actions emit, a listener calls facteur.notification(...).params(...).to([user]).send().
Rules
- A dedicated
notificationsmodule owns the model, transformer, controller and routes for the bell:GET /notifications→ list + unseen count.POST /notifications/:id/read→ mark one read.POST /notifications/seen→ mark all as seen (the dot disappears; row stays "unread").POST /notifications/read→ mark all read.
- Notification classes live at
app/<mod>/notifications/<name>_notification.ts, extendingNotification<User, Params>:static options = { name: 'user-welcome', deliverBy: { database: true, transmit: true } } asDatabaseMessage() { return DatabaseMessage.create().setType(...).setContent({...}).setTags([...]) } asTransmitMessage() { return TransmitMessage.create().setContent({ kind: '...' }) } - User routing via
User.notificationTargets():
Facteur maps each channel's target automatically.{ database: { notifiableId: String(this.id) }, transmit: { channel: `notifications/user-${this.id}` }, } - Emission goes through events — see [[actions-events]]. The listener calls:
await facteur.notification(SomeNotification).params({...}).to([user]).send() - Shared prop
unseenNotifications(count) is computed in the Inertia middleware when a user is authenticated. It powers the bell badge on first render — the SSE stream keeps it in sync afterward. - Bell UI subscribes to the per-user channel via
useNotificationsChannel(user.id, onIncoming), hits the endpoint to fetch the list when opened, marks-all-seen on open, marks-read on click. - Frontend SSE client is a lazy singleton: one
EventSourceon/__transmit/events, all channels multiplex through it. - SSE transport —
apps/web/config/transmit.tsdefaults totransport: null(in-memory, single-node). The@adonisjs/transmitprovider auto-registers the/__transmit/*routes, so the bell works out of the box. Swaptransportfor a distributed driver (Redis) when horizontally scaling.
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 First seen · 113 lines · 130 tokens per session scan A 859860613f93
notifications is a skill published in the GitHub repository filipebraida/adonisjs-starter-kit (96 stars, last pushed 2mo ago), licensed MIT. It adds 130 tokens to every session and 1,599 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
supermemory
Supermemory is a state-of-the-art memory and context infrastructure for AI agents. Use this skill when building applications that need persistent memory, user personalization, long-term context retention, or semantic search across knowledge bases. It provides Memory API for learned user context, User Profiles for…
tuturuuu-external-apps
Connect branded external apps to Tuturuuu authentication, workspace administration, storage, and content APIs.
ui-beats
Use this skill when users want to add, customize, or troubleshoot UI Beats components in React/Next.js projects. It covers component selection, shadcn registry installation from uibeats.com, the UI Beats MCP server, motion and reduced-motion handling, and integration patterns for animated sections.
tuturuuu-realtime
Implement and operate Tuturuuu realtime rooms, collaborative programming, presence, cursors, durable state and private checkpoints.
tuturuuu-cli
Install, authenticate, troubleshoot, or publish the Tuturuuu CLI and SDK.
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.