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 anasfik/FlutterGuard --skill skillgit clone --depth 1 https://github.com/anasfik/FlutterGuardWrote 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/anasfik/flutterguard/skill)<a href="https://agentmods.dev/skills/anasfik/flutterguard/skill"><img src="https://agentmods.dev/badge/skills/anasfik/flutterguard/skill/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/anasfik/flutterguard/skill"><img src="https://agentmods.dev/badge/skills/anasfik/flutterguard/skill.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 | $0.00044 | $0.03117 |
| Opus 5.5 | $0.00018 | $0.01247 |
| Sonnet 5.5 | $0.00009 | $0.00623 |
| Haiku 4.5 | $0.00004 | $0.00312 |
Grade A, and why
flutter-apk-security 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 yesterday.
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 — 260 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flutter APK Security
Use this skill when the user provides an Android APK/AAB, asks whether a Flutter Android release artifact is safe, or asks for review of Android artifact security, permissions, embedded secrets, manifest risks, or release signing signals.
This is an agent workflow first: inspect the artifact, report evidence, and keep the human in the loop. The repository also ships an Android app that automates part of this workflow on-device (see Companion App); the manual workflow below stays the reference for anything the app cannot see.
Do not silently change a user app's permissions, signing, dependencies, auth, payments, privacy behavior, production environment, publishing config, or API key migration strategy.
Companion App
This repository also contains FlutterGuard for Android (app/, package com.flutterguard.app): a Kotlin + Jetpack Compose app that runs the same rule families on the phone. It has no INTERNET permission and performs every scan locally; it requests only QUERY_ALL_PACKAGES, enumerates installed apps, and reads each app's base.apk plus splits through publicSourceDir. Results are written to app-specific external storage, /sdcard/Android/data/com.flutterguard.app/files/reports/<package>.json (pullable with adb pull even on the signed release build) (dots replaced by underscores, schema flutterguard/report/1), with a <package>.hist snapshot beside it.
Prefer the app when:
- the same phone must be scanned repeatedly (e.g. before each release) without pulling APKs to a desktop;
- you want a sweep over many installed apps: there is no in-app batch button, but
adb shell am start -n com.flutterguard.app/.MainActivity -e scan <package>runs one package per invocation and logsFG_REPORT <path>when the JSON is written; - you care about what an update changed: rescanning the same package computes a "Changes since last scan" diff of hosts, API routes, findings (
severity|id), pub dependencies and version against the previous.hist.
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.
- yesterday First seen · 260 lines · 44 tokens per session scan A 37e21e4e3a04
flutter-apk-security is a skill published in the GitHub repository anasfik/FlutterGuard (26 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,117 once invoked, about $0.0002 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 2026-10-29.
Other skills, from other repositories
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware samples using apktool for decompilation, jadx for Java source recovery, and androguard for permission analysis, manifest inspection, and suspicious API call detection.
analyzing-android-malware-with-apktool
Perform static analysis of Android APK malware using apktool for resource decompilation, jadx for Java source recovery, and androguard for manifest inspection, dangerous permission-combination detection, and identification of obfuscated code, dynamic code loading, and reflection-based API calls. Use to statically…
flutter
Use when building, structuring, testing or optimizing a Flutter app — feature-first layering, Riverpod 3 or Bloc, typed gorouter, freezed models, a dio data layer, Material 3, jank hunting, widget/golden tests. Targets Flutter 3.44 / Dart 3.12. NOT React Native (that is react-native), NOT Compose Multiplatform (that…
analyzing-android-malware-with-apktool
Use when perform static analysis of Android APK malware samples using apktool for decompilation, jadx for Java source recovery, and androguard for permission analysis, manifest inspection, and suspicious API call detection. Use when performing static analysis of android apk malware samples using apktool.
mobiloop-mobile-qa
Test mobile apps with MobiLoop MCP, collect device evidence, and fix and retest confirmed failures within the user's scope. Use for Flutter, React Native, Android, or iOS QA on an emulator, simulator, or device, including relevant mobile security checks.
android-reverse-engineering
Decompile Android APK, XAPK, JAR, and AAR files using jadx or Fernflower/Vineflower. Reverse engineer Android apps, extract HTTP API endpoints, trace call flows from UI to network layer, and analyze runtime behavior with Frida, network capture, JNI/SO inspection, and signature generation. Use when the user wants to…