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/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/commands/saiday/kukuroo/kukuroo-setup)<a href="https://agentmods.dev/commands/saiday/kukuroo/kukuroo-setup"><img src="https://agentmods.dev/badge/commands/saiday/kukuroo/kukuroo-setup.svg" alt="Measured on agentmods" 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 | $0.00017 | $0.00917 |
| Opus 5 | $0.00009 | $0.00458 |
| Sonnet 5 | $0.00003 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
kukuroo-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsS -X POST "$KUKUROO_ORIGIN/push/send" \ How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wire up Kukuroo
The user invoked this with: $ARGUMENTS
Goal: leave $XDG_CONFIG_HOME/kukuroo/env holding a working origin and send token, verified by a
notification that actually arrived. Every project on this machine reads that one file afterwards.
1. Find what is already there
cat "${XDG_CONFIG_HOME:-$HOME/.config}/kukuroo/env" 2>/dev/null
That file, or KUKUROO_ORIGIN and KUKUROO_SEND_TOKEN already in the environment, is the only place
either value lives on this machine. Kukuroo is deployed on one machine and sent to from others, so
being on a machine that has never been wired up is the normal case and not a sign anything is wrong.
$ARGUMENTS, if given, is the origin. Accept it with or without a scheme and normalise to
https://<host> with no trailing slash.
2. Ask for what is missing
One message, both values:
Which origin does your Kukuroo Worker answer on, and what is its send token? Pasting the token puts it in this transcript; if you would rather it did not, put both in
~/.config/kukuroo/envyourself (KUKUROO_ORIGIN=andKUKUROO_SEND_TOKEN=, a line each) and say when it is done.
Both are in kukuroo.credentials.json on the machine the deployment was set up from: sendToken, and
the address is the custom domain in its wrangler.jsonc or the workers.dev URL the deploy printed.
Say that once if they do not have the values to hand.
If they have not deployed a Worker at all yet, npx kukuroo init my-push is the whole of setup. Say
that and stop, rather than walking them through it here.
3. Prove it, then store it
Send a real notification. This is the only way to know: nothing in the config can tell you whether a device is still enrolled.
curl -fsS -X POST "$KUKUROO_ORIGIN/push/send" \
-H "authorization: Bearer $KUKUROO_SEND_TOKEN" \
-H 'content-type: application/json' \
-d '{"notification":{"title":"Kukuroo is wired up","body":"Your agents can reach this phone.","tag":"kukuroo-warmup","navigate":"'"$KUKUROO_ORIGIN"'/"}}'
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.
- 7d ago First seen · 77 lines · 17 tokens per session scan A cd6ffece394f
kukuroo-setup is a command published in the GitHub repository saiday/kukuroo (123 stars, last pushed 22d ago), licensed MIT. It adds 17 tokens to every session and 917 once invoked, about $0.0001 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 commands, from other repositories
hyperliquid-risk
Mission-critical real-time risk monitoring system with automated alerts, circuit breakers, and emergency shutdown for live Hyperliquid trading by ae.ltd.
feature-status
Show the current status of a feature build - which phase is active, what has completed, what remains, and any blockers.
app-store-audit
Run an enterprise pre submission compliance audit on an iOS or Android app against Apple App Store and Google Play rejection rules. Pass a project path or run from the project root.
feat
Kick off tasks creation for a new feature (4-item interview before invoking pm-agent; an epic-sized requirement routes to phased decomposition, a feature already built on one platform routes to cross-platform parity, a change that touches no endpoint routes to client-only).
setup-onesignal
Configure and verify the OneSignal Cursor plugin and MCP connection.
setup-sandbox
You are helping the user set up Cloudflare Sandbox SDK in their project for secure, isolated code execution.