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 agentmods add skills/toffyui/ccteams/react-native-playbooknpx skills add toffyui/ccteams --skill react-native-playbookgit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/toffyui/ccteams/react-native-playbook)<a href="https://agentmods.dev/skills/toffyui/ccteams/react-native-playbook"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/react-native-playbook.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.03432 |
| Opus 5 | $0.00032 | $0.01716 |
| Sonnet 5 | $0.00013 | $0.00686 |
| Haiku 4.5 | $0.00006 | $0.00343 |
Grade A, and why
react-native-playbook 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 5d 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 — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
React Native Playbook (Expo + TypeScript)
This is the literal procedure for working in an Expo + React Native codebase. The single most expensive class of mistake in this stack is treating it like web React: the second most expensive is proposing native changes without first knowing whether the project runs in Expo Go or a dev client. Both are killed by following the loop in order.
Operating loop
- Read the project's identity files before any opinion. In this order:
package.json— theexpopackage version tells you the SDK line (e.g.~51.x→ SDK 51). Note whetherexpo-dev-client,@shopify/flash-list,react-native-reanimated, andreact-native-safe-area-contextare installed.app.json/app.config.ts|js— existingpluginsarray, permissions (ios.infoPlist,android.permissions),bundleIdentifier/package,newArchEnabledif present.- Repo root —
ios/orandroid/directories present means the native projects are checked in (bare or prebuilt); absent means CNG/managed. - Lockfile —
pnpm-lock.yaml/yarn.lock/package-lock.jsondecides the package manager. Never create a second lockfile.
- Classify the runtime before proposing any native change.
- No
expo-dev-client, noios//android/dirs → the team runs Expo Go: only Expo SDK modules and pure-JS libraries work. Anything else is an escalation (see decision tree A) and must be stated as one. expo-dev-clientpresent oreas.jsonwith build profiles → dev client: config plugins and native modules work, but every change toapp.jsonplugins or native deps requires a rebuild, not a reload.
- No
- Detect the router.
app/directory +expo-routerinpackage.json→ Expo Router (file-based; new screens are new files underapp/). Otherwise@react-navigation/native→ React Navigation (screens register in a navigator; params typed in the param list). - Read 2–3 neighboring screens/components in the area you're changing.
Match their styling approach (
StyleSheet.createvs a styling lib), import order, and data-fetching pattern. Do not import a pattern the repo doesn't already use. - Install dependencies only via
npx expo install <pkg>— it pins the version compatible with the project's SDK. A barenpm installof an RN-adjacent package is how version-mismatch build failures start. - Build the smallest slice, then run the checks (see Verification recipe). Any change touching layout, lists, keyboard, or navigation gets named per-platform verification steps in your report — iOS and Android differ on exactly those four things.
- In your report, separate JS-reloadable changes from rebuild-required
changes. Editing a component = reload. Adding a native dep, a config
plugin, or changing
app.jsonnative keys = new build (npx expo prebuild+ native run, or an EAS build). Saying which one applies is part of being done.
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.
- 5d ago First seen · 224 lines · 64 tokens per session scan A c5552aad2a22
react-native-playbook is a skill published in the GitHub repository toffyui/ccteams (47 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 3,432 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
winapp-maui
Package and sign .NET MAUI Windows apps with winapp, resolving the resizetizer manifest dependency. Use when packaging or signing a .NET MAUI Windows app, building a MAUI MSIX or signed unpackaged build in CI, or fixing 'manifest contains unresolved placeholders ($placeholder$)' errors from winapp package.
apple-search-ads
When the user wants to set up, optimize, or scale Apple Search Ads (ASA) campaigns — including keyword bidding, match types, campaign structure, Creative Product Sets, CPP routing, and ROAS optimization. Use when the user mentions "Apple Search Ads", "ASA", "Search Ads", "Search tab ads", "Today tab ads", "CPT"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.