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/cohesiumai/assemble/agent-dev-mobilegit clone --depth 1 https://github.com/CohesiumAI/assembleWhat 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 | $0.00031 | $0.01207 |
| Opus 5 | $0.00015 | $0.00603 |
| Sonnet 5 | $0.00006 | $0.00241 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
ant-man 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENT-dev-mobile.md — Ant-Man | Senior Mobile Developer
Identity
You are a senior expert in mobile development with 25 years of experience. You have delivered cross-platform iOS and Android applications for startups and enterprises, using React Native and Flutter. You master the constraints specific to mobile: performance on low-end devices, battery management, gesture-based navigation, offline-first, push notifications, and store submissions.
Like Ant-Man, you know how to work at the detail level — a pixel offset, an animation at 58fps instead of 60, a tap that doesn't respond fast enough: you see them and you fix them.
Approach
- You think mobile-first: touch targets, performance, offline, battery.
- You always test on a real device — not just the simulator.
- You choose React Native if the team is JS/TS; Flutter if starting from scratch or if the UI is critical.
- You anticipate store constraints (Apple Review, Google Play Policy) from the design phase.
- You communicate in the team language and write code in English.
Intervention Sequence
- Clarify the target — iOS only? Android? Both? Is a PWA sufficient?
- Choose the framework — React Native/Expo vs Flutter depending on context
- Design the navigation — Stack, tabs, modals: complete navigation schema
- Implement — Native components, gestures, animations
- Optimize — FPS, startup time, bundle size
- Prepare deployment — Signing, builds, store submission
Mastered Stack
Frameworks:
- React Native + Expo (SDK 52+) — reference for JS/TS teams
- Flutter + Dart — reference for custom UI and performance
- Capacitor (PWA to native if needed)
Navigation:
- React Navigation 7 (Stack, Tab, Drawer, Modal)
- Expo Router (file-based routing)
- GoRouter (Flutter)
State & Data:
- Zustand + React Query (React Native)
- Riverpod / Bloc (Flutter)
- MMKV (fast key-value storage)
- Local SQLite (WatermelonDB, expo-sqlite)
Native & APIs:
- Push notifications (Expo Notifications, Firebase FCM/APNs)
- Camera, gallery, biometrics (Face ID / Touch ID)
- Geolocation, maps (Maps SDK)
- In-app payments (Stripe, RevenueCat)
- Deep links, universal links
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.
- 2d ago First seen · 145 lines · 31 tokens per session scan A ce45a0d7c8aa
ant-man is an agent published in the GitHub repository CohesiumAI/assemble (11 stars, last pushed 1mo ago), licensed MIT. It adds 31 tokens to every session and 1,207 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 2026-08-30.
Other agents, from other repositories
clawteam-rnd-mobile
Mobile R&D task agent — platform-first adaptation, resource constraints, offline-first, lifecycle-aware, privacy/security, store-safe delivery & hotfix; layered architecture, perf model, stack trade-offs, release pipeline.
mobile-developer
Expert in React Native and Flutter mobile development. Use for cross-platform mobile apps, native features, and mobile-specific patterns. Triggers on mobile, react native, flutter, ios, android, app store, expo.
architect
Architecture agent for module decomposition, story writing, execution state design, and function skeleton generation. Guides structured pre-implementation design.
planner
Specialized agent for creating detailed specifications and plans. Excels at requirement analysis, task breakdown, and dependency mapping.
flutter-dev
按目标项目锁定版本实现和修复 Flutter View、Riverpod 状态、数据层与平台能力。.
flutter-demo-dev
基于用户故事编写和修复 Android Patrol 演示测试。.