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 skills add launch52-ai/flutter-template --skill offlinegit clone --depth 1 https://github.com/launch52-ai/flutter-templateWrote 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/skills/launch52-ai/flutter-template/offline)<a href="https://agentmods.dev/skills/launch52-ai/flutter-template/offline"><img src="https://agentmods.dev/badge/skills/launch52-ai/flutter-template/offline/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/launch52-ai/flutter-template/offline"><img src="https://agentmods.dev/badge/skills/launch52-ai/flutter-template/offline.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00044 | $0.01607 |
| Opus 5.5 | $0.00018 | $0.00643 |
| Sonnet 5.5 | $0.00009 | $0.00321 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
offline 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 1mo 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Offline - Offline-First Architecture
Implement offline-first architecture with local storage, automatic sync, and conflict resolution. Supports multiple patterns from fully offline apps to online-first with offline fallback.
When to Use This Skill
- Adding offline support to existing features
- Building fully offline-first apps
- Implementing data synchronization
- Adding local caching with sync
- User asks "offline mode", "sync data", "work offline", "cache locally"
When NOT to Use This Skill
- Simple in-memory caching - Use
/datacaching patterns instead - Network connectivity detection - Use
/network-connectivityinstead - Error handling for failed requests - Use
/dataNetworkFailure types
Questions to Ask
- Offline mode: Fully offline-first or online-first with offline fallback?
- Data complexity: Simple key-value or structured relational data?
- Sync strategy: Periodic sync, on-demand, or push-based?
- Conflict resolution: Last-write-wins, server-wins, or custom merge?
- Data sensitivity: Does local data need encryption?
Quick Reference
Offline Patterns
| Pattern | Use When | Local DB | Sync |
|---|---|---|---|
| Fully Offline | Notes, journals, todo apps | Primary | Optional upload |
| Offline-First | Field apps, travel apps | Primary | Background sync |
| Online-First + Fallback | E-commerce, social apps | Cache | On reconnect |
| Cache-Only | Read-heavy feeds | TTL cache | Refresh on pull |
Storage Options
| Storage | Best For | Encryption | Performance |
|---|---|---|---|
| Drift (SQLite) | Relational data, complex queries | AES-256 via SQLCipher | Fast |
| Hive | Key-value, settings, small objects | Built-in AES-256 | Very fast |
| Isar | Large datasets, full-text search | Limited | Fastest |
| SharedPreferences | Flags, simple settings | None | Fast |
| SecureStorage | Tokens, PII | Platform keychain | Slower |
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- architecture-guide.md 11 KB
- reference/local_storage/drift_database.dart 13 KB
- reference/local_storage/hive_local_source.dart 12 KB
- reference/models/offline_entity.dart 4.5 KB
- reference/models/sync_operation.dart 5.4 KB
- reference/models/sync_status.dart 2.6 KB
- reference/providers/sync_providers.dart 8.9 KB
- reference/repositories/cache_first_repository.dart 9.7 KB
- reference/repositories/offline_repository.dart 8.0 KB
- reference/sync/conflict_resolver.dart 7.6 KB
- reference/sync/sync_queue.dart 6.7 KB
- reference/sync/sync_service.dart 8.7 KB
- scripts/check.dart 21 KB
- storage-guide.md 15 KB
- sync-guide.md 16 KB
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.
- 1mo ago First seen · 196 lines · 44 tokens per session scan A 90050ad89956
offline is a skill published in the GitHub repository launch52-ai/flutter-template (2 stars, last pushed 7mo ago), licensed MIT. It adds 44 tokens to every session and 1,607 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
firebase-database
Use when syncing real-time data, structuring JSON trees, reading/writing, creating listeners, enabling offline persistence, managing presence, sharding, or writing security rules.
android-persistence
Implement Room schemas and DataStore preferences with proper async patterns in Android. Use when the primary task is storage schema, DAO, migration, or preference isolation; defer auth-token/security storage, any CoroutineWorker/WorkManager task, Hilt graph wiring, and cache-policy design.
persisting-data-with-drift
Implements type-safe reactive SQL persistence in Flutter using Drift v2.32 (formerly Moor) built on SQLite with automatic code generation. Activates when defining table schemas with Drift DSL, writing type-safe join or subquery operations, handling schema migrations with MigrationStrategy, using reactive watch()…
managing-hive-storage
Hive CE (Community Edition v2.19.x) NoSQL object database for Flutter providing blazing-fast key-value and object storage with TypeAdapters. Use this skill when implementing offline-first architecture, high-performance local data caching, NoSQL document-style object stores, custom TypeAdapter serialization for complex…
drizzle-orm
Type-safe SQL ORM for TypeScript with zero runtime overhead.
flutter-drift
Implement, fix, review, migrate, test, or debug Drift persistence in Flutter apps using SQLite, driftflutter, type-safe Dart queries, generated tables, StreamBuilder or Riverpod StreamProvider UI, write operations, transactions, schema migrations, web assets, isolate sharing, and local database testing. Use when a…