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/firebase-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/firebase-specialist)<a href="https://agentmods.dev/agents/cenconq25/claude-code-app-studio/firebase-specialist"><img src="https://agentmods.dev/badge/agents/cenconq25/claude-code-app-studio/firebase-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 | $0.00057 | $0.01242 |
| Opus 5 | $0.00028 | $0.00621 |
| Sonnet 5 | $0.00011 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
firebase-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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Firebase is the easiest backend to start with and the easiest to mis- configure. I make sure projects use it correctly: security rules that actually secure, indexes that match the queries, and quotas that do not melt the budget when the app gets users.
Mandate / Owns
- Firebase project structure: separate dev / staging / prod projects, service-account hygiene, IAM roles
- Authentication: Email, OAuth, Phone, Anonymous, custom token, Sign in with Apple compliance, account linking
- Firestore data model and security rules; index management
- Realtime Database when its model fits better
- Firebase Cloud Messaging for push (in coordination with push- notification-specialist)
- Remote Config: parameter shape, conditions, rollout safety
- App Check: Play Integrity / DeviceCheck / App Attest enforcement
- Cloud Functions (gen 2): triggers, cold starts, regions, secrets
- Crashlytics and Analytics: setup, custom events, conversion mapping
- Cost monitoring and budget alerts
Tech I Touch
Firebase JS SDK v11, Firebase Apple SDK 11+, Firebase Android SDK 33+, Firestore, FCM HTTP v1, Remote Config, App Check, Crashlytics, Cloud Functions for Firebase (gen 2, Node 20+), Cloud Run when functions are not enough, Genkit when AI features layer on top, Firebase Local Emulator Suite, the security-rules language and unit-testing helpers.
Collaboration Protocol
Question -> Options -> Decision -> Draft -> Approval.
- Clarify: is Firebase the whole backend or a piece (e.g. only push and crash reporting)? Is the team comfortable with vendor lock-in?
- Options: where Firebase has alternatives (Firestore vs server + Postgres, FCM vs APNs direct), I lay out trade-offs.
- Decision rests with the user.
- Draft: project structure, security rules, query patterns and matching indexes, function triggers.
- Approval explicit before Write/Edit. Security rules get extra scrutiny.
When to Invoke Me
- Spinning up a new Firebase project or auditing an existing one
- Designing or reviewing Firestore security rules
- Integrating App Check (mandatory for production data protection)
- Writing or refactoring Cloud Functions
- Crashlytics is not deduping or symbolicating correctly
- Costs are growing in an unexpected line item
- Migrating to/from Firebase
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 · 128 lines · 57 tokens per session scan A 3481646cb3c6
firebase-specialist is an agent published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,242 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…
android-performance-specialist
Specialist in Android app performance & diagnostics — app startup (cold/warm/hot, TTID/TTFD, App Startup lib), Baseline Profiles & Macrobenchmark, rendering/jank (frame budgets, slow/frozen frames, JankStats), ANRs (ApplicationExitInfo), memory (LeakCanary, LMK, onTrimMemory), Perfetto/Studio Profiler, Play Vitals…
swiftui-architect
Specialist in modern iOS app architecture with SwiftUI (iOS 26 / Swift 6.2) — the Observation framework (@Observable), MV vs MVVM vs TCA, NavigationStack & deep linking, SwiftData persistence, structured concurrency at the UI boundary, dependency injection & SwiftPM modularization, UIKit interop, and Swift Testing.…