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 ggozad/haiku.skills --skill haiku_skills_notificationsgit clone --depth 1 https://github.com/ggozad/haiku.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/ggozad/haiku.skills/haiku_skills_notifications)<a href="https://agentmods.dev/skills/ggozad/haiku.skills/haiku_skills_notifications"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.skills/haiku_skills_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/ggozad/haiku.skills/haiku_skills_notifications"><img src="https://agentmods.dev/badge/skills/ggozad/haiku.skills/haiku_skills_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 | $0.00012 | $0.00187 |
| Opus 5 | $0.00006 | $0.00093 |
| Sonnet 5 | $0.00002 | $0.00037 |
| Haiku 4.5 | $0.00001 | $0.00019 |
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 12d 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
Notifications
Use the send_notification tool to publish push notifications to an ntfy.sh topic. Use the read_notifications tool to poll and read cached messages from a topic.
Workflow
- Use
send_notificationto send a message to a topic. - Use
read_notificationsto check for incoming messages on a topic. - Topics are shared — anyone subscribed to the same topic receives the messages.
Guidelines
- Choose descriptive, hard-to-guess topic names to avoid collisions.
- Use the
titleparameter for structured notifications. - Use
priorityto signal urgency (1=min, 3=default, 5=max). - The
sinceparameter onread_notificationscontrols how far back to look (e.g. "10m", "1h", "all").
What ships with it
4 files 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.
- 12d ago First seen · 23 lines · 12 tokens per session scan A ca8dbb702e60
notifications is a skill published in the GitHub repository ggozad/haiku.skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 187 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 2026-08-31.
Other skills, from other repositories
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
stfu
Use this skill when the user wants terse, direct responses with no preamble, recap, filler, or unnecessary explanation. Supports persistent toggling with /stfu on and /stfu off. Applies to answers, writing, editing, commands, code changes, summaries, and any interaction where minimal output is preferred.
automate
Turn a workflow described or just completed in a coding agent into one focused, validated AgentUse agent. Use for make-this-repeatable, scheduled-workflow, and first-automation handoffs from third-party coding agents.
onboarding
Guide a new AgentUse user from a confirmed project to one validated first agent and its first CLI or Web UI run. Use for terminal setup and Create my first agent handoffs.
relay-tips
A guide for reducing Claude Code token costs, where tokens are the units used to process text and code. It examines current usage patterns and suggests ways to spend fewer tokens.
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…