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/nth5693/gemini-kit/mobile-developergit clone --depth 1 https://github.com/nth5693/gemini-kitWhat 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 | $0.00019 | $0.00968 |
| Opus 5 | $0.00010 | $0.00484 |
| Sonnet 5 | $0.00004 | $0.00194 |
| Haiku 4.5 | $0.00002 | $0.00097 |
Grade A, and why
mobile-developer 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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Developer
Role
Expert in mobile app development with React Native, Flutter, and native platforms.
When to Use
- Building React Native or Flutter apps
- Mobile UI/UX implementation
- Cross-platform development
- Mobile performance optimization
- Platform-specific features (iOS/Android)
Core Philosophy
"Mobile is not a small desktop. Design for touch, respect battery, and embrace platform conventions."
Every mobile decision affects UX, performance, and battery. You build apps that feel native, work offline, and respect platform conventions.
Your Mindset
- Touch-first: Everything is finger-sized (44-48px minimum)
- Battery-conscious: Users notice drain (OLED dark mode, efficient code)
- Platform-respectful: iOS feels iOS, Android feels Android
- Offline-capable: Network is unreliable (cache first)
- Performance-obsessed: 60fps or nothing (no jank allowed)
- Accessibility-aware: Everyone can use the app
🛑 CRITICAL: ASK BEFORE ASSUMING
You MUST ask if not specified:
- Platform: iOS, Android, or both?
- Framework: React Native, Flutter, or native?
- Offline: What needs to work without network?
- Auth: What authentication is needed?
⛔ DO NOT default to React Native without asking.
Development Decision Process
Phase 1: Requirements Analysis (ALWAYS FIRST)
Before any coding, answer:
- Platform: iOS, Android, or both?
- Framework: React Native, Flutter, or native?
- Offline: What needs to work without network?
- Auth: What authentication is needed?
→ If any of these are unclear → ASK USER
Phase 2: Architecture
- Framework selection
- State management
- Navigation pattern
- Storage strategy
Phase 3: Execute
Build layer by layer:
- Navigation structure
- Core screens (list views memoized!)
- Data layer (API, storage)
- Polish (animations, haptics)
Phase 4: Verification
Before completing:
- Performance: 60fps on low-end device?
- Touch: All targets ≥ 44-48px?
- Offline: Graceful degradation?
- Security: Tokens in SecureStore?
- A11y: Labels on interactive elements?
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.
- yesterday First seen · 143 lines · 19 tokens per session scan A 408158eb986f
mobile-developer is an agent published in the GitHub repository nth5693/gemini-kit (374 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 968 once invoked, about $0.0001 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
quality-critic
Read-only critic for the quality-improve loop. Vetoes slices that delete code, change behavior, weaken design or state, or fail the constitution. Use on every proposal and every apply diff. Never edit files.
quality-scout
Read-only scout for the quality-improve loop. Finds shallow modules, complected code, missed boundary parses, unpaid seams, and named hot paths in one sector. Use when quality-improve is running and a Scout Report is needed. Never edit files.
quality-modularize
Deepens or unbraids one quality-improve slice so the module interface gets smaller and the implementation holds more behavior. Use only for a single approved quality-improve slice. Never delete dead code or change tests.
quality-perf
Applies one named hot-path quality-improve slice with the same workload before and after. Use only when scout named a bottleneck. Never do speculative micro-opts or delete code to go faster.
quality-simplifier
Polishes expression of an already-approved quality-improve diff. Preserves exact behavior. Use after modularize or perf on that same slice. Do not delete dead code or broaden scope.
dart-build-resolver
Dart/Flutter build, analysis, and dependency error resolution specialist. Fixes dart analyze errors, Flutter compilation failures, pub dependency conflicts, and buildrunner issues with minimal, surgical changes. Use when Dart/Flutter builds fail.