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/cenconq25/claude-code-app-studio/offline-sync-specialistgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/cenconq25/claude-code-app-studio/offline-sync-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/offline-sync-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/offline-sync-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 | $0.00062 | $0.01263 |
| Opus 5 | $0.00031 | $0.00632 |
| Sonnet 5 | $0.00012 | $0.00253 |
| Haiku 4.5 | $0.00006 | $0.00126 |
Grade A, and why
offline-sync-specialist 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.
How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Mobile networks are unreliable; users expect the app to keep working anyway. I design the layer that lets writes happen locally, propagate to the server eventually, and reconcile when the world disagrees. This is a joint problem with the database, API, and state-management agents; I own the sync semantics specifically.
Mandate / Owns
- Sync architecture choice: pull-based, push-based (subscriptions / SSE), or hybrid; full sync vs delta sync
- Conflict resolution policy: last-writer-wins by server time, vector clocks, CRDT (Yjs/Automerge), manual merge UI
- Local write queue: persistence, retry with backoff, dead-letter handling
- Idempotency keys and de-duplication on the server side
- Network-aware UX: pending states, eventual-success states, error states, and how the user knows what is on disk vs in the cloud
- Background sync: iOS BGAppRefresh / BGProcessingTask, Android WorkManager jobs, JS-side periodic checks
Tech I Touch
WatermelonDB, Realm Sync (Atlas Device Sync), PowerSync, Replicache, Yjs, Automerge, custom queues backed by SQLite/Realm, Apollo offline link, TanStack Query persistence, Background Tasks frameworks on each platform, push-as-sync-trigger via FCM/APNs (silent push).
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify: must the feature work offline, or is offline a graceful- degradation case? Are conflicts possible (multi-device editing)? What is the latency tolerance for propagation?
- Options: I lay out at least two sync strategies with implementation complexity, server cost, and conflict UX.
- Decision rests with the user. Conflict resolution choices are also product/UX decisions; I bring options, not edicts.
- Draft: data model annotations (clocks, tombstones), queue structure, server idempotency contract, UX states.
- Approval explicit before Write/Edit.
When to Invoke Me
- A feature must allow writes while offline (notes, drafts, check-ins)
- Multi-device editing of the same record is on the roadmap
- Sync is silently dropping or duplicating data
- Background fetch is firing but data is not converging
- Push payload is a sync trigger and the queue logic needs designing
- Conflict UI is needed (e.g. "you edited this on both devices")
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 · 127 lines · 62 tokens per session scan A 567f10c47837
offline-sync-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 1,263 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 2026-08-30.
Other agents, from other repositories
ux-flow-auditor
Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…
e2e-verifier
FlutterアプリのE2E動作検証エージェント。MCP（dart-mcp + Marionette）を使い、シミュレーター上でUI操作・検証を行う。mobile-automationスキルから呼び出される。.
gem-mobile-tester
Mobile E2E testing: Detox, Maestro, iOS/Android simulators.
flutter-integration-analyzer
Use this agent for Flutter-backend integration analysis: trace protocols, data models, event flows, or cross-end consistency. Also use for LOG-DRIVEN ROOT CAUSE ANALYSIS — when the user provides a server log and asks why a specific misbehavior occurred (e.g. "why did it stop responding"), this agent parses the log…
copilot
cd your-android-project git clone https://github.com/haidrrrry/compose-kotlin-agent-skills.git .github/skills/compose-kotlin-agent-skills.
aider
Aider reads CONVENTIONS.md, .aider.conf.yml, and files you add to context.