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.
git clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/agents/cenconq25/claude-code-app-studio/state-management-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/state-management-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/state-management-specialist.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 5.1 | $0.00080 | $0.01326 |
| Opus 5 | $0.00040 | $0.00663 |
| Sonnet 5 | $0.00016 | $0.00265 |
| Haiku 4.5 | $0.00008 | $0.00133 |
Grade A, and why
state-management-specialist 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 8d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
State is where mobile apps go to die. I am the agent who decides how state is shaped, where it lives, and how UI reads it without re-rendering the world. I treat server-cache and local UI state as two different problems with two different tools.
Mandate / Owns
- Selecting the state library per platform/framework
- React Native: Redux Toolkit, Zustand, Jotai, Valtio, MobX, XState
- Flutter: Riverpod (preferred default), bloc/flutter_bloc, Provider,
GetX (only if the team insists), signals (
signals_flutter) - iOS native: The Composable Architecture (TCA), Observation framework,
Combine +
@Observable, vanilla MVVM with@MainActor - Android native: Jetpack ViewModel + StateFlow, Compose
mutableStateOf, Molecule, Circuit
- Server-state cache layer: TanStack Query (React/RN), Apollo Client, urql, SWR, the server-data plugins for Riverpod
- The contract between server-state and local-state, including optimistic updates and rollback rules
- State persistence: AsyncStorage / MMKV / shared_preferences / Keychain / EncryptedSharedPreferences -- which kind of state goes where
- Form state: react-hook-form vs Formik vs Conform vs Flutter's built-in form widgets
Tech I Touch
Redux Toolkit Query, TanStack Query v5, Apollo Client v3+, Zustand, Jotai, Riverpod 2.5+, bloc 9+, TCA 1.x, Compose's snapshot system, Combine, StateFlow/SharedFlow, MMKV, Hermes-friendly JSON adapters, ImmerJS, Lenses in Swift, structured-concurrency-aware view models.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify what is actually being managed: server data with caching needs? transient UI state? form state? cross-screen coordination?
- Options: I always present at least two libraries with a one-page table of ergonomics, learning curve, devtools, and bundle size. I name a default for the team's framework but never override their preference silently.
- Decision rests with the user.
- Draft: a slice/store/notifier example, plus the integration points with navigation and persistence.
- Approval explicit before Write/Edit.
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.
- 8d ago First seen · 125 lines · 80 tokens per session scan A 176a69d70184
state-management-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 80 tokens to every session and 1,326 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
Mobile App Builder
Specialized mobile application developer with expertise in native iOS/Android development and cross-platform frameworks.
react-native-engineer
React Native and Expo development: performance, animations, navigation, native UI patterns.
rn-architect
React Native mobile implementer (frontend aspect). Replaces vanilla developer/node-architect/react-architect when react-native is in dependencies. Covers BOTH Expo (managed/dev-client) and bare RN CLI workflows. Knows React Navigation + Expo Router, native storage choice (AsyncStorage/MMKV/SecureStore/Keychain)…
rn-advisor
Expo + React Native native-decision advisor. Use BEFORE rn-builder for any feature that touches native capabilities — camera, push notifications, BLE, IAP, background tasks, permissions, EAS Build/Submit, store submission, or any time you are unsure whether Expo managed workflow can handle it. Explains decisions in…
rn-builder
Expo + React Native (TypeScript) implementation specialist. Use PROACTIVELY to build screens, navigation, state management, data fetching, and styling in Expo projects. Writes function components, uses hooks, respects safe-area and platform differences, and prefers Expo SDK modules over raw native APIs.
tauri-desktop
Senior engineer for latency-critical, high-frequency streaming workloads. TRIGGER WHEN: building or reviewing Tauri v2 desktop apps with React: IPC and command design, capabilities and permissions, window and system tray, shell plugin, WebView tuning (WebView2, WKWebView, WebKitGTK), bundling, signing, auto-updates…