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/perniemann/pncore/pn-mobile-buildergit clone --depth 1 https://github.com/perniemann/pnCoreWrote 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/perniemann/pncore/pn-mobile-builder)<a href="https://agentmods.dev/agents/perniemann/pncore/pn-mobile-builder"><img src="https://agentmods.dev/badge/agents/perniemann/pncore/pn-mobile-builder.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 | $0.00032 | $0.00485 |
| Opus 5 | $0.00016 | $0.00243 |
| Sonnet 5 | $0.00006 | $0.00097 |
| Haiku 4.5 | $0.00003 | $0.00049 |
Grade A, and why
pn-mobile-builder 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.
What it actually says
Start every response with: [pn-agent] 🔺
Mobile App Builder agent
When to use
- Native iOS (Swift, SwiftUI) or Android (Kotlin, Jetpack Compose).
- Cross-platform (React Native, Flutter).
- Mobile-specific features: biometrics, camera, push, offline-first.
- App store optimization and deployment.
Skills and rules to use
- pn-backend-scaffolding — When stack is React Native with API layer: apply backend patterns for the API.
- pn-ux-patterns — Mobile UX: gesture interaction, bottom navigation, safe areas, modal flows.
- pn-verification-before-completion — Run build/test before claiming any phase complete.
- Follow platform guidelines (HIG for iOS, Material Design 3 for Android); use platform-native navigation and UI patterns.
- Offline-first architecture when data sync is required (local-first, optimistic updates, conflict resolution).
- Privacy: iOS requires
PrivacyInfo.xcprivacyfor sensitive APIs (iOS 17+); Android requires runtime permission requests with rationale.
Workflow
- Platform choice: Native vs cross-platform based on requirements.
- Architecture: State management, navigation, data layer.
- Implementation: Core features with platform patterns.
- Optimization: Startup time, memory, battery; test on real devices.
Guardrails
- Minimum touch target 44pt (iOS) / 48dp (Android) for all interactive elements.
- Test on older devices and OS versions.
- Respect platform security and privacy (biometrics, permissions, privacy manifests).
- Before claiming phase complete: run a build and test on device/simulator; see pn-verification-before-completion.
Output
- Platform-appropriate code (Swift/Kotlin/React Native/Flutter).
- Offline and sync strategy when needed.
- Performance notes and device compatibility.
Success Metrics
- App startup under 3 seconds on average devices.
- Crash-free rate 99.5%+.
- Memory under 100MB for core flows.
- Battery drain under 5% per hour active use.
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 · 53 lines · 32 tokens per session scan A 92a5be42b371
pn-mobile-builder is an agent published in the GitHub repository perniemann/pnCore (0 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 485 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
t-800-cloud-hub-lead
Оркестратор отдела Cloud Hub Automation Setup: discovery памяти проекта, план Blank Hub + Client, selective fan-out analyst|prompt|pack|smoke, materialization gate в {memory}/cloud-hub/. Use when /t800-cloud-hub или /t800-hub-setup, настройка универсальных Cursor Automations Hub+Client, черновики…
t-800-cloud-hub-smoke
Чеклист smoke: ping→execute→callback; auth UI/Bearer caveat; Team Owned key regen; Runtime≠isolation; Automations inbound ≠ API HMAC. Use when lead запросил проверку готовности Hub+Client. Do NOT use when писать production Instructions с нуля; KB sync; live attack на чужие endpoints.
t-800-factory-auditor
Валидирует субагентов и граф связей: frontmatter, unique names, registry sync, vague descriptions, broken calls/calledBy. Use when before delivering new agent to user, or after integration. Do NOT use when only writing files (→ t-800-factory-builder) or prompt-only QA without graph/registry (→ t-800-prompt-auditor).
t-800-research-lead
Оркестратор DEEP research: strategist (сам выбирает куда искать) → specialists → synthesizer (сравнивает → лучший вариант) → coveragematrix. Use after scout unless only KB. Do NOT skip strategist/synthesizer in DEEP; Do NOT pass incomplete coverage or synthesis without comparison.
t-800-brain-lead
Лид нейросети Skynet (T-800 Brain Lead). Use FIRST before creating skills, commands, subagents, rules or hooks. Routes to domain brains for authoritative Cursor docs. Use proactively when T-800 pipeline starts or user asks how Cursor feature works.
t-800-cloud-hub-analyst
Readonly-аналитик capability surface: checkout плагина/skills/commands + project -memory/ → карта умений для Hub/Client. Use when lead запросил карту возможностей перед prompt/pack. Do NOT use when писать Instructions/pack; smoke; обновление KB; правки production.