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 saiday/kukuroo --skill kukuroo-notifygit clone --depth 1 https://github.com/saiday/kukurooWrote 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/saiday/kukuroo/kukuroo-notify)<a href="https://agentmods.dev/skills/saiday/kukuroo/kukuroo-notify"><img src="https://agentmods.dev/badge/skills/saiday/kukuroo/kukuroo-notify/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/saiday/kukuroo/kukuroo-notify"><img src="https://agentmods.dev/badge/skills/saiday/kukuroo/kukuroo-notify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 80 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00088 | $0.01780 |
| Opus 5 | $0.00044 | $0.00890 |
| Sonnet 5 | $0.00018 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
kukuroo-notify scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -X POST "$KUKUROO_ORIGIN/push/send" \ How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Notify the user on their phone
Kukuroo is the user's own Web Push service, running on their own Cloudflare Worker. One authenticated POST puts a notification on their phone. This skill is where the endpoint lives, plus the few rules whose failures are otherwise silent.
Kukuroo is the pipe, not the errand. Spend a line or two on it and get back to the work the user actually asked for.
1. Fire only on an explicit ask
Send when the user asks for it:
- a notification, ping, buzz, or status update on their phone
- a time they want to be told at: "at 5pm", "in 30 minutes", "when the deploy lands"
- leaving: "I'm stepping away", "off the monitor", "going for a walk", "afk"
- Kukuroo by name
A push arrives on a lock screen wherever the user happens to be, so it is theirs to ask for. Work they are sitting there watching is already visible to them, and needs no notification.
2. Find where to send, or ask
Two values: KUKUROO_ORIGIN (where the Worker answers) and KUKUROO_SEND_TOKEN (the bearer token).
Take the first source that has both.
- Already in the environment.
- The file this skill wrote the last time it asked:
cat "${XDG_CONFIG_HOME:-$HOME/.config}/kukuroo/env" 2>/dev/null
There is no third source. A Kukuroo deployment is set up on one machine and sent to from any number of others, so the setup leaves nothing behind here to find, and a search for one is a search that comes back empty.
Ask once, in one message. The user has just asked for a notification, so getting the address is part of the job. Both values in one question, in about two sentences:
Which origin does your Kukuroo Worker answer on, and what is its send token? Pasting the token puts it in this transcript; if you would rather it did not, put both in
~/.config/kukuroo/envyourself (KUKUROO_ORIGIN=andKUKUROO_SEND_TOKEN=, a line each) and say when it is done.
Then let it go. If the answer does not come, or comes back as "not now", drop Kukuroo and do the work they actually asked for. One question costs them a moment. A second one costs them the thread.
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.
- 10d ago First seen · 136 lines · 88 tokens per session scan A c4353e9cbe30
kukuroo-notify is a skill published in the GitHub repository saiday/kukuroo (126 stars, last pushed 26d ago), licensed MIT. It adds 88 tokens to every session and 1,780 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
novu-design-workflow
Design notification workflows the Novu way — choose channels, set severity, decide when a workflow is critical, configure digests, and route based on subscriber state. Applies to BOTH dashboard-authored and code-first (@novu/framework) workflows. Use when planning a new workflow, deciding which channels to include…
human-cli
Reach the actual human you're working for via the human CLI (ask/approve/choose/tell) when you need a decision, approval, or notification and no one is watching this terminal right now. Use for background/autonomous/scheduled runs, risky or irreversible actions, and genuine multi-way ambiguity — not for routine…
novu-manage-preferences
Configure notification preferences in Novu at the workflow and subscriber level. Set default channel preferences (email, SMS, push, chat, in-app), mark preferences as read-only or subscriber-editable, and manage subscriber-specific overrides. Use when setting up notification opt-in/opt-out, configuring per-channel…
Contacts
A contact-management skill for finding, adding, changing, and removing people in an address book.
Reminders
A skill for creating timed reminders in a task or reminder list.
Clipboard
A skill for reading and writing the computer’s system clipboard, the temporary place used for copied text.