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 skills/andrzejchm/fdb/skillnpx skills add andrzejchm/fdb --skill skillgit clone --depth 1 https://github.com/andrzejchm/fdbWhat 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 | $0.00247 | $0.00933 |
| Opus 5 | $0.00123 | $0.00466 |
| Sonnet 5 | $0.00049 | $0.00187 |
| Haiku 4.5 | $0.00025 | $0.00093 |
Grade A, and why
using-fdb 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview - skill version 1.11.1
Version check: Run
fdb --version. Expected:fdb 1.11.1. This skill may describe unreleased branch behavior. Update:dart pub global activate --source git https://github.com/andrzejchm/fdb.git
Install
dart pub global activate --source git https://github.com/andrzejchm/fdb.git
Verify: fdb status
fdb_helper setup (required for in-app UI/data commands)
The describe, tap, double-tap, longpress, input, scroll, scroll-to, wait, swipe, swipe-path, back, clean, and shared-prefs commands require fdb_helper in the Flutter app under test. Some platform screenshot fallbacks also use it. Adding fdb_helper also enables automatic VM service URI discovery for fdb attach on Android and iOS — no manual --debug-url needed.
pubspec.yaml:
dev_dependencies:
fdb_helper: ^1.11.1
main.dart:
import 'package:fdb_helper/fdb_helper.dart';
import 'package:flutter/foundation.dart';
void main() {
if (!kReleaseMode) {
FdbBinding.ensureInitialized();
}
runApp(MyApp());
}
After adding fdb_helper, run flutter pub get and relaunch the app.
Command index
Run fdb skill <topic> to print full docs, flags, output tokens, and best practices for a topic.
| Topic | Commands | Run |
|---|---|---|
| launch | devices, launch, attach, doctor, reload, restart, status, kill, deeplink |
fdb skill launch |
| interact | screenshot, tree, describe, select, selected, native-tap, tap, longpress, double-tap, input, scroll, scroll-to, swipe, swipe-path, back |
fdb skill interact |
| data | shared-prefs, clean, ext, grant-permission |
fdb skill data |
| diagnostics | logs, syslog, crash-report + websocat fallback |
fdb skill diagnostics |
| memory | mem, gc, heap |
fdb skill memory |
| simulator | simulator (appearance, text-size, status-bar, location, push, defaults) |
fdb skill simulator |
What ships with it
6 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.
- 2d ago First seen · 62 lines · 247 tokens per session scan A 632c06915af9
using-fdb is a skill published in the GitHub repository andrzejchm/fdb (45 stars, last pushed 5d ago), licensed MIT. It adds 247 tokens to every session and 933 once invoked, about $0.0012 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 skills, from other repositories
edge-to-edge
Use this skill to migrate your Jetpack Compose app to add adaptive edge-to-edge support and troubleshoot common issues. Use this skill to fix UI components (like buttons or lists) that are obscured by or overlapping with the navigation bar or status bar, fix IME insets, and fix system bar legibility.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
flutter-fix-layout-issues
Fixes Flutter layout errors (overflows, unbounded constraints) using Dart and Flutter MCP tools. Use when addressing "RenderFlex overflowed", "Vertical viewport was given unbounded height", or similar layout issues.
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
ios-hig-design
Design native iOS interfaces following Apple Human Interface Guidelines. Use when the user mentions "iPhone app", "iPad layout", "SwiftUI", "UIKit", "Dynamic Island", "safe areas", "HIG compliance", "SF Symbols", "haptic feedback", "iOS accessibility", "make my app feel native", or "follow Apple design guidelines".…