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 melaya-labs/melaya-mcp --skill melaya-setupgit clone --depth 1 https://github.com/melaya-labs/melaya-mcpWrote 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/melaya-labs/melaya-mcp/melaya-setup)<a href="https://agentmods.dev/skills/melaya-labs/melaya-mcp/melaya-setup"><img src="https://agentmods.dev/badge/skills/melaya-labs/melaya-mcp/melaya-setup/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/melaya-labs/melaya-mcp/melaya-setup"><img src="https://agentmods.dev/badge/skills/melaya-labs/melaya-mcp/melaya-setup.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 | $0.00119 | $0.02346 |
| Opus 5 | $0.00060 | $0.01173 |
| Sonnet 5 | $0.00024 | $0.00469 |
| Haiku 4.5 | $0.00012 | $0.00235 |
Grade A, and why
melaya-setup 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 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.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Melaya
Melaya gives you the user's own account: their Android phone, a browser they connected, their agent pipelines, the services they authorised, and the record of what every run did. Seventy-six tools across eight permissions.
This skill is the operating discipline. Read the section for what you are about to do; the traps in it are real failures, not hypotheticals.
Always start here
Call melaya_setup_status.
One call returns every requirement with a done flag, and every unmet one comes back with the exact command or URL that fixes it. Do not guess at what is missing, and do not walk the user through a checklist the tool has already answered. One call, then act on nextStep.
Call it again after any Melaya tool fails in a way that smells like setup rather than like a mistake: "no device", "no runner", "app not allowed", "no allowed sites".
Two things that shape everything you do
Where you are running decides what you can do about a command. With shell access on the user's own computer, run it. Without it, on claude.ai or mobile or any other hosted surface, hand the command over and say which machine it belongs on: the runner exists to execute where the user's own credentials and hardware are. Never report having started something you could not start.
What you can see depends on what the user granted. Your tool list is already filtered to their consent. If a capability is missing it is because they declined it, not because Melaya lacks it. Say that plainly and offer to have them reconnect. Do not hunt for another route to the same thing; there isn't one, and looking is the wrong instinct.
Setting up
1. A Melaya account. They already have one if the connection authorised at all; OAuth cannot complete without it.
2. A paired Android phone. Call melaya_phone_pair. It returns an 8-character code valid for five minutes plus an install link. The user opens that link on the phone, installs, and enters the code.
Say these out loud, because each one surprises people:
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 Changed 4bad02b59f6e
- 10d ago First seen · 128 lines · 119 tokens per session scan A 445544e5e95b
melaya-setup is a skill published in the GitHub repository melaya-labs/melaya-mcp (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 119 tokens to every session and 2,346 once invoked, about $0.0006 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
signed-in-browser
Drive the browser the user is already signed into, instead of a cold automation profile. Use when a task lives behind a login — a dashboard, an admin console, an internal tool, a ticket queue, a bank or billing page, webmail, a social account — or when a scripted login is failing on SSO, MFA, CAPTCHA or bot detection.…
post-to-hacker-news
Submit to Hacker News, including Show HN, by driving a signed-in browser. Use when launching a product, tool or MCP server, or when a submission needs its customary author comment. Covers the title rules, when a Show HN is allowed, the url-or-text choice, and how to tell a real submission from a silent failure.
xcodebuildmcp-cli
Official skill for the XcodeBuildMCP CLI. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
xcodebuildmcp
Official skill for XcodeBuildMCP. Use when doing iOS/macOS/watchOS/tvOS/visionOS work (build, test, run, debug, log, UI automation).
apitap
ApiTap gives AI agents cheap access to web data through three layers.
website-explorer
Discover website capabilities from user behaviors. Learn APIs and automate workflows.