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 parhamb/design-skills --skill ux-notificationsgit clone --depth 1 https://github.com/parhamb/design-skillsWrote 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/parhamb/design-skills/ux-notifications)<a href="https://agentmods.dev/skills/parhamb/design-skills/ux-notifications"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-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/parhamb/design-skills/ux-notifications"><img src="https://agentmods.dev/badge/skills/parhamb/design-skills/ux-notifications.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 | $0.00059 | $0.00907 |
| Opus 5.5 | $0.00024 | $0.00363 |
| Sonnet 5.5 | $0.00012 | $0.00181 |
| Haiku 4.5 | $0.00006 | $0.00091 |
Grade A, and why
ux-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 2mo 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notifications UX
A notification interrupts someone's life. Every one you send spends trust, and the balance is easy to overdraw: the OS-level "turn off all notifications" switch is one long-press away, and once flipped it almost never comes back.
Checklist
| Item | Guidance |
|---|---|
| Permission timing | Ask after the user has experienced value, tied to a feature that needs it — never on first launch. |
| Pre-permission prompt | An in-app screen explains what notifications the user will get before the system dialog appears. |
| Per-type granularity | One toggle per notification type (orders, messages, promotions). Never a single on/off switch. |
| Transactional vs promotional | Marketing notifications are opt-in and separate from transactional ones. Disabling promotions never disables receipts or security alerts. |
| Quiet hours | User can set a do-not-disturb schedule, or the app respects the OS Focus / DND modes. |
| Badge accuracy | App icon badge count matches actual unread items and clears when they are viewed. |
| Deep-link target | Tapping a notification lands on the exact relevant content, never the home screen. |
| Notification content | Specific and actionable: "Sara replied to your comment", not "You have a new notification." |
| Grouping | Multiple notifications from the same source collapse into a group or summary. |
| Android channels | Every notification type has its own channel so users can control them at the OS level. |
| In-app notification center | A history of past notifications is available in the app for anything the user missed or dismissed. |
| Frequency capping | Promotional notifications are rate-limited. Sending caps are enforced per user, per day. |
Permission Strategy
Contextual ask: Request permission at the moment the value is obvious — after the user places an order ("Get delivery updates?"), follows a topic, or sends a first message. Acceptance rates for contextual asks are several times higher than launch-time asks.
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.
- 2mo ago First seen · 88 lines · 59 tokens per session scan A a83d9bbd6299
ux-notifications is a skill published in the GitHub repository parhamb/design-skills (25 stars, last pushed 4mo ago), licensed MIT. It adds 59 tokens to every session and 907 once invoked, about $0.0002 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.
ux-notifications compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ux-notificationsparhamb/design-skills | Skill | 25 | 4mo ago | MIT | A | 59 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 4d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |