Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/lukedj78/dev-flownpx agentmods add skills/lukedj78/dev-flow/rn-write-testsWrote 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/lukedj78/dev-flow/rn-write-tests)<a href="https://agentmods.dev/skills/lukedj78/dev-flow/rn-write-tests"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/rn-write-tests/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/lukedj78/dev-flow/rn-write-tests"><img src="https://agentmods.dev/badge/skills/lukedj78/dev-flow/rn-write-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 38 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 47 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 59 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00173 | $0.02198 |
| Opus 5.5 | $0.00069 | $0.00879 |
| Sonnet 5.5 | $0.00035 | $0.00440 |
| Haiku 4.5 | $0.00017 | $0.00220 |
Grade A, and why
rn-write-tests 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.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rn-write-tests — Jest + RNTL + Maestro testing for Expo + RN
Contract
See references/contracts.md (vendored from dev-flow). Key facts:
- Reads
<project-root>/.workflow/meta.json#stack.framework— must be"expo-rn". - Adds dev dependencies + Jest config on first call (idempotent: detects existing setup).
- Writes test files under
<project-root>/__tests__/(Jest convention) for unit/integration. - Writes Maestro YAML flows under
<project-root>/.maestro/for e2e. - Does NOT modify
meta.json#phase.
When this skill applies
- User asks to write a test for a specific source file or flow.
- Orchestrator does NOT route here automatically — test writing is on-demand.
Knowledge dependencies (read these first)
rn-fundamentals/SKILL.md— TS strict, modern primitives the tests will see.rn-data-fetching/references/patterns.md— query/mutation patterns the tests must exercise.
Workflow
Step 1 — Verify preconditions
Read .workflow/meta.json. Abort if stack.framework != "expo-rn".
Step 2 — Detect / install the test stack
Check if jest, jest-expo, @testing-library/react-native are in package.json. If not:
npx expo install --dev \
jest jest-expo \
@testing-library/react-native@^14 \
test-renderer@^1 \
@types/jest -- --legacy-peer-deps
# jest-expo declares `@react-native/jest-preset` as a peer (58: `^0.88.0`), and that package is
# NOT in the SDK's bundledNativeModules — so `expo install` hands you npm latest, which breaks as
# soon as it is a minor ahead of the project's RN (SDK 57, 2026-09-08: 0.87.1 against RN 0.86).
# Pin it to the React Native version the project actually has:
RN_VERSION="$(node -p "require('react-native/package.json').version")"
npm install --save-dev --legacy-peer-deps "@react-native/jest-preset@${RN_VERSION}"
(Without the @react-native/jest-preset line the very first jest run dies with "The React Native Jest preset that jest-expo relies on has moved to a separate package"; with the wrong minor it dies with "Could not locate module react-native/setup-env" — observed 2026-09-08 on SDK 57 / RN 0.86.3. On SDK 58 the suite also needs "resolver": "react-native-reanimated/jest/resolver" in the jest config, or setUpTests() crashes every suite — re-run 2026-10-17 on a fresh SDK 58 app. test-renderer@^1 is a required peer dep of RNTL v14 — it replaced react-test-renderer. Node ^22.13 || >=24 is also required. Native matchers like toBeOnTheScreen() are built into @testing-library/react-native v12.4+ — no separate @testing-library/jest-native needed. See references/jest-setup.md for the full config.)
What ships with it
6 files 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.
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.
- 2d ago Changed · +9 tokens per session 775d0e340bfc
- 8d ago Changed · +7 lines 58348eebb6f2
- 1mo ago Changed · +8 lines · +22 tokens per session 28064b2c3900
- 1mo ago First seen · 121 lines · 142 tokens per session scan A cf53f8fc1bba
rn-write-tests is a skill published in the GitHub repository lukedj78/dev-flow (6 stars, last pushed yesterday), licensed MIT. It adds 173 tokens to every session and 2,198 once invoked, about $0.0007 per session on Opus 5.5. 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
ios-testing-patterns
XCTest and XCUITest execution workflows and flaky test detection patterns.
flutter-testing-skill
Generates Flutter widget tests, integration tests, and golden tests in Dart. Supports local execution and TestMu AI cloud for real device testing. Use when user mentions "Flutter", "widget test", "WidgetTester", "testWidgets", "fluttertest", "integrationtest". Triggers on: "Flutter", "widget test", "Dart test"…
mobiai-android-testing
Use when writing or running tests in an Android project — unit tests, UI tests, choosing the right framework and patterns.
test-automation
Execute Vitest and Playwright test suites with result collection and failure analysis.
cometchat-flutter-v6-testing
Test a Flutter app that uses the CometChat UI Kit — what is worth testing versus what belongs to the kit, mocking the SDK boundary, widget tests around chat screens, and integration/CI setup. Triggers: 'test my cometchat integration', 'mock cometchat in flutter tests', 'widget test chat screen', 'cometchat test setup'.
cometchat-ios-testing
Test an iOS app that embeds CometChat — what to mock vs exercise for real, keeping the CometChatSDK off the network in unit tests, waiting out the async init→login gate, and a lean XCUITest smoke. Triggers: 'test cometchat ios', 'unit test chat swift', 'mock cometchatsdk', 'xcuitest for chat', 'how do I test cometchat…