rn-testing

A guide for creating and running Maestro end-to-end tests for React Native apps. It covers written user flows, test timing, test identifiers, multiple devices, network simulation, and app-state checks.

In plain words
What is it for?
Use it to write UI tests, create end-to-end flows, add test identifiers, run tests, verify features, simulate network responses, inspect stored app state, and write assertions.
Why use it?
It helps tests behave like real user interactions and avoids treating a screen produced by injected state as proof that the journey works.

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

Made for: Claude Code, Codex.

Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,976 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00106 $0.04976
Opus 5 $0.00053 $0.02488
Sonnet 5 $0.00021 $0.00995
Haiku 4.5 $0.00011 $0.00498

Measured 2d ago against content hash 1769b7dc6a8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rn-testing 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 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.

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.

packages/claude-plugin/skills/rn-testing/SKILL.md · 499 lines

How it starts

The opening of the file, as written. The whole thing — 499 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rn-testing — Maestro Patterns, Timing Rules, and Test Strategy

How to write and run UI test flows for React Native feature verification. Covers test runner selection, timing rules, testID conventions, multi-device testing, network mocking, and store inspection setup.


Test Runner: maestro-runner floor (>= 1.1.24)

All YAML replay goes through rn-dev-agent's maestro_run, cdp_run_action, or cdp_run_e2e_suite tools. They require maestro-runner >= 1.1.24 from the versioned pin-cache (attested 1.1.24 is the default known-good) and refuse missing, older, unverified, or checksum-mismatched binaries before UI mutation.

node <plugin-root>/rn-dev-agent-core/dist/maestro-runner-pin.js diagnose --json
bash <plugin-root>/scripts/ensure-maestro-runner.sh
node <plugin-root>/rn-dev-agent-core/dist/maestro-runner-pin.js diagnose --json

Success requires pinned-ok, version >= 1.1.24, provenance pin-cache, and the versioned selected path. Never resolve replay from PATH, ~/.maestro-runner, or another CLI.


Verification Fidelity — No Silent Shortcuts (#61)

Verification means simulating a real user. State injection that produces a matching screen is NOT verification.

The following count as shortcuts that invalidate verification unless the user explicitly sanctions them:

  1. Deep-linking past the entry point of the flow being verified (e.g. deep-linking to success-details/<existingId> instead of walking the create flow).
  2. Forcing route params a real user can't set (e.g. isNewPolicy=true, fromSuccess=true, mode=edit injected via URL).
  3. Writing to MMKV / AsyncStorage / SecureStore to reset cooldowns, permissions, "has-seen" flags, or session state.
  4. Dispatching Redux / Zustand actions directly rather than through UI (cdp_dispatch from outside a real user gesture).
  5. Calling native-module APIs to skip platform dialogs (e.g. faking permission grants, dismissing system prompts via JS).

These tools work equally well from inside a real flow and as state injection — the plugin can't tell the difference. The agent is the safeguard.

Read the full file on GitHub · 499 lines

Files

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.

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 · 499 lines · 106 tokens per session scan A 1769b7dc6a8a

Subscribe to this mod's changes

rn-testing is a skill published in the GitHub repository Lykhoyda/rn-dev-agent (11 stars, last pushed 2d ago), licensed MIT. It adds 106 tokens to every session and 4,976 once invoked, about $0.0005 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 2026-08-30.

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