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 FoneClaw-AI/foneclaw-android --skill navigationgit clone --depth 1 https://github.com/FoneClaw-AI/foneclaw-androidWrote 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/foneclaw-ai/foneclaw-android/navigation)<a href="https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/navigation"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/navigation/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/foneclaw-ai/foneclaw-android/navigation"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/navigation.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 | $0.00027 | $0.01013 |
| Opus 5 | $0.00014 | $0.00507 |
| Sonnet 5 | $0.00005 | $0.00203 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
RoutePlanningNavigationSkill 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 8d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Route Navigation Planning Agent Skill
Skill Name
Route Navigation Planning
Description
This skill is used by an Android agent to plan and start route navigation based on the user’s destination, preferred map application, current phone location, installed map applications, last used map application, and travel mode.
The agent should determine the map application name and package name, starting point, destination, and travel mode, then invoke the corresponding map navigation tool and monitor the screen until the target map application enters navigation mode.
Goal
Start route navigation for the user using an appropriate map application and travel mode.
Required Tools
get_installed_map_appsget_locationmap_navigate
Workflow
1. Determine the Map Application
The selected map application must include both the application display name and the package name. The package name is required when invoking the map navigation tool because deep links may fail or open the wrong target without it.
-
Get the list of currently installed map applications on the phone, including each application’s display name and package name.
-
If no map application is installed, notify the user:
No map application is currently available. Task terminated. -
Select the map application using the following priority order:
- The map application explicitly specified in the user’s current input.
- The map application extracted from user preferences.
- The last used map application.
- A randomly selected installed map application.
-
If a selected application is not installed or its package name cannot be resolved, skip it and continue to the next priority.
-
If randomly selecting a map application, choose only from installed map applications with a known package name.
-
The final selected map application must be represented as:
map_app_namemap_app_package_name
2. Determine the Starting Point
- Use the phone’s current location to get the latitude and longitude.
- If location retrieval fails, notify the user:
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.
- 8d ago First seen · 113 lines · 27 tokens per session scan A 00a90b658bd8
RoutePlanningNavigationSkill is a skill published in the GitHub repository FoneClaw-AI/foneclaw-android (6 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 1,013 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
reverse-engineering-android-malware-with-jadx
Reverse engineers malicious Android APK files using JADX decompiler to analyze Java/Kotlin source code, identify malicious functionality including data theft, C2 communication, privilege escalation, and overlay attacks. Examines manifest permissions, receivers, services, and native libraries. Activates for requests…
navigate
Call the unintent tool with the following exact parameters.
earllm-build
Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.
mobile-design
Mobile UX patterns, touch interactions, gesture design, mobile-first principles, app navigation, and mobile performance.
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…
solopi-ai
A command-line framework for testing Android apps and devices with SoloPi, including on-device or cloud AI decision models. It manages devices, test cases, recorded interactions, replays, performance history, and evidence.