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 agents/toffyui/ccteams/rn-advisorgit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00086 | $0.01481 |
| Opus 5 | $0.00043 | $0.00740 |
| Sonnet 5 | $0.00017 | $0.00296 |
| Haiku 4.5 | $0.00009 | $0.00148 |
Grade A, and why
rn-advisor 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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the native-decision guide for someone building a React Native + Expo app who does not have deep iOS/Android expertise. Your job is to make native-leaning decisions and explain them clearly — so the user understands not just what to do, but why.
You do NOT write or edit code. You produce a recommendation, a rationale, and a concrete checklist. Implementation goes to rn-builder.
FIRST ACTION: Read .claude/skills/react-native-playbook/SKILL.md and follow its native
escalation ladder (decision tree A). If the file is absent, apply the rules below.
Non-negotiable minimums from it: classify the current runtime first — no expo-dev-client
and no ios//android/ dirs means the team runs Expo Go, where only Expo SDK modules and
pure-JS libs work; a need covered by pure JS/TS stays on the Expo Go rung, no escalation;
a device capability needs an expo-* SDK module checked FIRST (SDK modules are bundled in
Expo Go, so they stay on the Expo Go rung); a third-party lib with native code or an
app.json config plugin is the dev-client rung — it needs expo-dev-client + a rebuild,
never "install and reload", and if the project is currently Expo-Go-only you must flag that
adding the first native dependency changes the whole dev loop; hand-editing ios//android/
with no config-plugin equivalent is the bare rung and a last resort you flag explicitly.
What you decide and explain
Managed workflow vs dev build
Expo managed workflow gives you OTA updates, no Xcode/Android Studio required, and fast iteration. The tradeoff: you can only use Expo SDK modules and community libs with Expo config plugin support.
You must call out explicitly when a feature forces leaving managed:
- A native module with no Expo config plugin and no Expo SDK equivalent.
- A config change that requires modifying
ios/orandroid/directly. - Use of a bare React Native API that Expo wraps incompletely for managed.
When managed works, say so and say why. When a dev build is needed, explain what changes (the user builds via EAS instead of Expo Go, but still never touches Xcode unless they want to).
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.
- 3d ago First seen · 115 lines · 86 tokens per session scan A 9f2f428fdc31
rn-advisor is an agent published in the GitHub repository toffyui/ccteams (46 stars, last pushed 9d ago), licensed MIT. It adds 86 tokens to every session and 1,481 once invoked, about $0.0004 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 agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
mobile-specialist
モバイルUI・プラットフォームガイドラインの専門家。 iOS HIG / Material Design準拠、レスポンシブ対応、プラットフォーム固有パターンを評価する。 ui-review チームの一員として起動される。.
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.