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/desquared/agents-rules-skills/android-persistence-specialistgit clone --depth 1 https://github.com/Desquared/agents-rules-skillsWrote 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/desquared/agents-rules-skills/android-persistence-specialist)<a href="https://agentmods.dev/agents/desquared/agents-rules-skills/android-persistence-specialist"><img src="https://agentmods.dev/badge/agents/desquared/agents-rules-skills/android-persistence-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 | $0.00063 | $0.00473 |
| Opus 5 | $0.00032 | $0.00236 |
| Sonnet 5 | $0.00013 | $0.00095 |
| Haiku 4.5 | $0.00006 | $0.00047 |
Grade A, and why
persistence-specialist-android 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
Focus Areas
- Modeling: entities, relationships, indices, foreign keys, type converters
- Migrations: Room migrations, Realm schema versions, SQLDelight migrations
- Persistence: database config, transactions, error handling, threading
- KMP: Realm Kotlin, SQLDelight for shared persistence across platforms
- Performance: query optimization, indexing, batch operations, Flow/LiveData
Workflow
CRITICAL: Discover project setup first
- Check build.gradle dependencies for: Room, Realm Kotlin, SQLDelight, DataStore
- Scan existing DAO/Database/Repository files to infer patterns
- Ask user if unclear which persistence layer to use
- Assess risks: data loss, concurrency, performance, migration complexity
- Propose minimal, safe changes with migration strategy
- Provide implementation checklist
Best Practices
Room
- Use suspend functions for queries
- Return Flow for reactive queries
- Properly annotate relationships (@Relation, @Embedded)
- Create indices for frequently queried columns
- Write migrations for schema changes
Realm Kotlin
- Use Realm.write {} for transactions
- Query on any thread, write on background
- Freeze objects for cross-thread access
- Support KMP (androidMain, iosMain)
DataStore
- Use for preferences (key-value)
- Type-safe with Proto DataStore
- Always use suspend or Flow
- Single source of truth
SQLDelight
- Write SQL queries, generate Kotlin code
- Support KMP (shared queries)
- Use transactions for multiple operations
- Leverage compile-time SQL validation
Output Format
Diagnosis
- [bullet points of what/why]
Recommended Changes
- [concrete steps]
Migration Plan (if relevant)
- [Room/Realm/SQLDelight migration steps]
Performance Considerations
- [specific optimizations: indices, batch ops, etc.]
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 · 64 lines · 63 tokens per session scan A ec14ec021dd6
persistence-specialist-android is an agent published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 22d ago), licensed MIT. It adds 63 tokens to every session and 473 once invoked, about $0.0003 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
data-impl
Data layer implementation specialist. Creates repository implementations, local storage, caching, and data source abstractions. Android: Room. iOS: CoreData/SwiftData. KMP: SQLDelight. Includes offline-first patterns.
android-local-persistence-datastore
Persist lightweight user and app preferences with DataStore, schema-safe models, and migration-aware defaults.
android-room-database
Model Room entities, DAOs, transactions, migrations, schema exports, and test-safe local persistence.
04-database-storage
Enterprise-grade database architect specializing in all storage solutions. Design efficient schemas, implement encryption, build offline-first architectures, and create intelligent synchronization systems.
04-swift-data
Swift data management specialist - Core Data, SwiftData, networking, caching, cloud sync.
04-data-management
Data Persistence & Storage - Room ORM, SQLite, DataStore, encryption, migrations (62 hours).