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 ariaramin/flutter-skills --skill flutter-firebase-messaginggit clone --depth 1 https://github.com/ariaramin/flutter-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/skills/ariaramin/flutter-skills/flutter-firebase-messaging)<a href="https://agentmods.dev/skills/ariaramin/flutter-skills/flutter-firebase-messaging"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/flutter-firebase-messaging/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/ariaramin/flutter-skills/flutter-firebase-messaging"><img src="https://agentmods.dev/badge/skills/ariaramin/flutter-skills/flutter-firebase-messaging.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 | $0.00150 | $0.01116 |
| Opus 5.5 | $0.00060 | $0.00446 |
| Sonnet 5.5 | $0.00030 | $0.00223 |
| Haiku 4.5 | $0.00015 | $0.00112 |
Grade A, and why
flutter-firebase-messaging 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 6d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter Firebase Messaging
Build or repair production Firebase Messaging integrations without importing stale native or Web assumptions into FlutterFire.
Workflow
- Inspect before editing:
- Read
pubspec.yaml,pubspec.lock, Flutter/Dart constraints, and the installedfirebase_messagingchangelog. - Identify every supported platform and inspect its existing Firebase/native configuration.
- Search every messaging listener, token call, background handler, permission request, topic operation, payload parser, presentation path, and notification route.
- Identify the trusted sender, payload schema, backend registration model, permission UX, and reliability assumptions.
- Read
- Read the relevant sections of
references/production-guide.md. Userg -n '^#|^##' references/production-guide.mdto locate sections; do not load the entire reference when a focused section is sufficient. - Revalidate version-sensitive facts against current official FlutterFire, Firebase, Android, Apple, or Flutter documentation before relying on them. Prefer installed package source and current official documentation over the reference when they conflict.
- Fix the shared root cause with the smallest complete change. Reuse the application's existing lifecycle, routing, persistence, authentication, and networking patterns.
- Validate the affected lifecycle on every supported platform, including release mode where background execution or tree shaking matters.
Reference Routing
- For architecture or implementation: read
Core Principles,Recommended Architecture,Initialization, andProduction Decision Rules. - For permissions or consent: read
Permission HandlingandPrivacy-Aware Auto Initialization. - For tokens and accounts: read
Token and Registration Managementand the backend registration sections. - For callbacks or routing: read the foreground, background, interaction, payload, deduplication, and navigation sections.
- For Android: read the Android permission, channel, priority, Doze, and release-handler sections.
- For iOS or macOS: read the APNs, capabilities, swizzling, UIScene, foreground presentation, and initial-message sections.
- For Web: read the Web capability, VAPID, service-worker, routing, topic, and token-reconciliation sections.
- For review or debugging: use
Code Review Checklist, anti-patterns,Version Sensitivity, andRelease Validation. - For security or sending: read the payload, trusted backend, HTTP v1, authorization, topic, logging, and deep-link sections.
What ships with it
2 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.
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.
- 6d ago First seen · 69 lines · 150 tokens per session scan A 02d2bc3d4331
flutter-firebase-messaging is a skill published in the GitHub repository ariaramin/flutter-skills (6 stars, last pushed 7d ago), licensed MIT. It adds 150 tokens to every session and 1,116 once invoked, about $0.0006 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 2026-10-11.
Other skills, from other repositories
cloudkit-sync
Generate CloudKit sync infrastructure using CKSyncEngine with conflict resolution, sharing, and account monitoring. Use when adding iCloud sync to an iOS/macOS app.
offline-queue
Generates an offline operation queue with persistence, automatic retry on connectivity, and conflict resolution. Use when user needs offline-first behavior, queued mutations, or pending operations that sync when back online.
push-notifications
Generate push notification infrastructure with APNs registration, handling, and rich notifications. Use when adding push notifications, configuring APNs, notification categories/actions, or rich notifications with images and custom UI.
event-driven-design
When designing loosely coupled systems that react to state changes asynchronously.
error-handling-architecture
When designing how a system recovers from and reports failures.
api-design-rest
When creating or extending an HTTP API for client consumption.