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.
git clone --depth 1 https://github.com/Amey-Thakur/AI-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/commands/amey-thakur/ai-skills/design-notification-system)<a href="https://agentmods.dev/commands/amey-thakur/ai-skills/design-notification-system"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/design-notification-system/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/commands/amey-thakur/ai-skills/design-notification-system"><img src="https://agentmods.dev/badge/commands/amey-thakur/ai-skills/design-notification-system.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 | $0.00018 | $0.00251 |
| Opus 5 | $0.00009 | $0.00125 |
| Sonnet 5 | $0.00004 | $0.00050 |
| Haiku 4.5 | $0.00002 | $0.00025 |
Grade A, and why
design-notification-system 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 9d 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.
What it actually says
You were invoked as a slash command. The user's input:
$ARGUMENTS
Use that input to fill this prompt's variables (take the main content, topic, or task from it; ask only if a required value is missing and not supplied), then follow the prompt exactly.
Design notifications for:
{events}
Users: {users}
Use notification-strategy, digest-design, notification-batching, and unsubscribe-and-preferences.
Produce:
- Each event classified: must act, should know, or might find interesting.
- Channel per class, defaulting to the least interruptive that works.
- What is batched into a digest and at what cadence.
- The global frequency cap per user.
- Preference controls, granular enough to reduce rather than only stop.
- Quiet hours and time zone handling.
- What is sent regardless of preference, and why.
Rules: default to the least interruptive channel. Every notification needs an action or it belongs in a digest. Cap frequency globally rather than per feature. Make unsubscribing easy, since it beats a complaint.
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.
- 9d ago First seen · 37 lines · 18 tokens per session scan A 61f5eeacd82e
design-notification-system is a command published in the GitHub repository Amey-Thakur/AI-SKILLS (7 stars, last pushed 7d ago), licensed MIT. It adds 18 tokens to every session and 251 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
debrief
Capture the meeting. Notes into the record.
prep
Prepare the meeting. One page from the record.
do-task
Do an ad-hoc, tactical task on a work item with NO PDLC process — no spec chain, no phase gates, no review chain. Work, ask follow-ups on the thread, continue until the requester says it is done.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.