rn-setup

A setup and dependency check for the rn-dev-agent tools used with React Native apps. It identifies the specific app directory, including the nested app directory in a monorepo, which is a repository containing multiple projects.

In plain words
What is it for?
Use it on first use, after setup warnings, or when CDP, device tools, the Maestro test runner, or the fast runner cannot connect or be found.
Why use it?
It helps resolve missing tools and connection failures before development or testing begins.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/lykhoyda/rn-dev-agent/rn-setup
Any agent
npx skills add Lykhoyda/rn-dev-agent --skill rn-setup
Clone the repo
git clone --depth 1 https://github.com/Lykhoyda/rn-dev-agent

Made for: Claude Code, Codex.

Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. Scan, not verified.
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 $0.00113 $0.07169
Opus 5 $0.00056 $0.03585
Sonnet 5 $0.00023 $0.01434
Haiku 4.5 $0.00011 $0.00717

Measured 2d ago against content hash e6fccf22f6aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

rn-setup scanned grade B with 2 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- Suggesting `sudo npm install -g` without first checking if nvm is available

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

LATEST=$(curl -fsSL --max-time 3 https://api.github.com/repos/Lykhoyda/rn-dev-agent/releases/latest 2>/dev/null | jq -r '.tag_name // empty' | sed 's/^v//')
packages/claude-plugin/skills/rn-setup/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Environment Setup & Dependency Check

You are helping a developer set up the rn-dev-agent plugin environment. This skill checks every prerequisite and installs missing dependencies.

When to use

  • First time using the plugin
  • After SessionStart shows WARNING messages about missing tools
  • When cdp_status fails to connect
  • When device_* tools fail with "session not open" or "command not found"
  • When the user runs /rn-dev-agent:setup

Checklist — run each check in order

Resolve APP_ROOT to the exact existing target React Native app directory before starting the checklist. Use the app selected by the user or the uniquely matching app from the available project evidence; in a monorepo, use the nested app directory rather than the repository root. If multiple candidates remain, ask which app is authoritative. Never run check 0 with APP_ROOT unset or empty.

0. Source declaration (non-Git app roots only)

The session binds one source identity before any setup or build step runs. A Git app root is detected automatically and declares nothing. A non-Git app root has no such identity and must declare one explicitly, or every authoritative tool refuses with NON_GIT_MANIFEST_REQUIRED.

git -C "$APP_ROOT" rev-parse --show-toplevel 2>/dev/null && echo GIT || echo NON_GIT

GIT → report N/A (Git worktree) and move on. NON_GIT → check the supervisor environment for RN_DEV_AGENT_DECLARED_ROOT and RN_DEV_AGENT_DECLARED_MANIFESTS. Report MISSING_ROOT, MISSING_MANIFEST_LIST, or MISSING_MANIFEST, then point to the session-authority contract. Setup diagnoses this preflight; it never supplies a declaration.

1. Node.js version

node --version

Required: Node.js >= 24. Every later major, including odd-numbered releases, is supported. If < 24: warn the user to install a supported Node release.

  • If nvm is installed (command -v nvm): nvm install 24 && nvm use 24
  • If fnm is installed: fnm install 24 && fnm use 24
  • Otherwise: download from https://nodejs.org/en/download/ or brew install node@24

Read the full file on GitHub · 361 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. 2d ago First seen · 361 lines · 113 tokens per session scan B e6fccf22f6aa

Subscribe to this mod's changes

rn-setup is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 113 tokens to every session and 7,169 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

skill-packager

Authors Agent Skills v1.0 packages (SKILL.md plus references/scripts), runs packageskill to produce a standards-compliant zip, and uses installskill to add skills from HTTPS, registry, workspace, or an uploaded archive. Use when the user wants to turn documentation, workflows, or code into a portable skill, export a…

vixues/LeAgent · 87 tokens

document-processor

Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.

vixues/LeAgent · 44 tokens

workflow-helper

Guidance for creating, managing and executing workflow automations that chain multiple tools and agents together. Use when the user asks about building, listing, running or composing workflows and automated task pipelines.

vixues/LeAgent · 41 tokens

attendance-signin-sheet

Generate printable attendance / 签到表 spreadsheets from name lists. Use when the user asks for 签到表, attendance sheet, meeting sign-in table, or similar printable roster tables (not full payroll attendance scoring unless asked).

vixues/LeAgent · 51 tokens

data-analyzer

Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.

vixues/LeAgent · 39 tokens

procurement-audit

Review procurement contracts and purchase packages against uploaded compliance rules (招标/采购制度). Use for 采购审核, contract compliance checklists, or procurement statistics rollups.

vixues/LeAgent · 39 tokens