melaya-setup

melaya-setup is a skill for Claude Code from melaya-labs/melaya-mcp. It costs 119 tokens per session (2,346 once invoked), scanned A, original, Apache-2.0.

A setup and operating guide for Melaya, a tool that connects a phone or browser to an agent. It also covers agent pipelines, which are sequences of automated tasks.

In plain words
What is it for?
Use it to pair a phone, install the Melaya app, start its local runner, control Android or a browser, and build, validate, schedule, or debug agent pipelines.
Why use it?
It brings the connection, startup, control, and troubleshooting steps into one place instead of leaving them scattered or unclear.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Part of the melaya plugin — 1 skill, 1 command, 1 MCP server shipped together

Good fit Use it to pair a phone, install the Melaya app, start its local runner, control Android or a browser, and build, validate, schedule, or debug agent pipelines.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/melaya-labs/melaya-mcp/melaya-setup
Install

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.

Any agent
npx skills add melaya-labs/melaya-mcp --skill melaya-setup
Clone the repo
git clone --depth 1 https://github.com/melaya-labs/melaya-mcp

Made for: Claude Code.

Or install melaya, the plugin that ships this one along with the rest of its 1 skill, 1 command, 1 MCP server.

Wrote 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.

agentmods badge for melaya-setup

README.md
[![agentmods](https://agentmods.dev/badge/skills/melaya-labs/melaya-mcp/melaya-setup/github.svg)](https://agentmods.dev/skills/melaya-labs/melaya-mcp/melaya-setup)
Your own site
<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.

agentmods 80×15 button for melaya-setup

Your own site · 80×15
<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>
Per session 119 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 7d ago against content hash 4bad02b59f6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/melaya-setup/SKILL.md · 128 lines

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:

Read the full file on GitHub · 128 lines

Changes

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.

  1. 7d ago Changed 4bad02b59f6e
  2. 10d ago First seen · 128 lines · 119 tokens per session scan A 445544e5e95b

Subscribe to this mod's changes

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.